Remove module level lora CACHE and a long module docstring.

Signed-off-by: bigcat88 <bigcat88@icloud.com>

.ci/windows_amd_base_files/README_VERY_IMPORTANT.txt

@@ -1,5 +1,4 @@
-As of the time of writing this you need this driver for best results:
-https://www.amd.com/en/resources/support-articles/release-notes/RN-AMDGPU-WINDOWS-PYTORCH-7-1-1.html
+As of the time of writing this you need a recent driver. Updating to the latest driver is recommended.
 
 HOW TO RUN:
 
@@ -7,9 +6,9 @@ If you have a AMD gpu:
 
 run_amd_gpu.bat
 
-If you have memory issues you can try disabling the smart memory management by running comfyui with:
+If you have memory issues you can try enabling the new dynamic memory management by running comfyui with:
 
-run_amd_gpu_disable_smart_memory.bat
+run_amd_gpu_enable_dynamic_vram.bat
 
 IF YOU GET A RED ERROR IN THE UI MAKE SURE YOU HAVE A MODEL/CHECKPOINT IN: ComfyUI\models\checkpoints
 

.coderabbit.yaml

@@ -4,12 +4,12 @@ early_access: false
 tone_instructions: "Only comment on issues introduced by this PR's changes. Do not flag pre-existing problems in moved, re-indented, or reformatted code."
 
 reviews:
-  profile: "chill"
-  request_changes_workflow: false
+  profile: "assertive"
+  request_changes_workflow: true
   high_level_summary: false
   poem: false
   review_status: false
-  review_details: false
+  review_details: true
   commit_status: true
   collapse_walkthrough: true
   changed_files_summary: false
@@ -39,6 +39,14 @@ reviews:
     - path: "**"
       instructions: |
         IMPORTANT: Only comment on issues directly introduced by this PR's code changes.
+        Treat AGENTS.md as mandatory repository policy, not optional style guidance.
+        Flag PR changes that violate AGENTS.md even when the code is otherwise functional.
+        In particular, enforce architecture boundaries, dtype/device/memory rules,
+        interface contracts, import style, no unnecessary try/except blocks, no inline
+        imports, no outbound internet paths in core ComfyUI, and narrow scoped fixes.
+        Prefer direct findings over suggestions when a rule is violated. Only ignore
+        AGENTS.md when it clearly conflicts with a newer explicit maintainer instruction
+        in the PR.
         Do NOT flag pre-existing issues in code that was merely moved, re-indented,
         de-indented, or reformatted without logic changes. If code appears in the diff
         only due to whitespace or structural reformatting (e.g., removing a `with:` block),
@@ -123,5 +131,10 @@ chat:
 
 knowledge_base:
   opt_out: false
+  code_guidelines:
+    enabled: true
+    filePatterns:
+      - files: "AGENTS.md"
+        applyTo: "**"
   learnings:
     scope: "auto"

.github/workflows/check-line-endings.yml

@@ -17,7 +17,7 @@ jobs:
       - name: Check for Windows line endings (CRLF)
         run: |
           # Get the list of changed files in the PR
-          CHANGED_FILES=$(git diff --name-only ${{ github.event.pull_request.base.sha }}..${{ github.event.pull_request.head.sha }})
+          CHANGED_FILES=$(git diff --name-only ${{ github.event.pull_request.base.sha }}..${{ github.event.pull_request.head.sha }} -- ':!.ci')
 
           # Flag to track if CRLF is found
           CRLF_FOUND=false

.github/workflows/ci-cursor-review.yml

@@ -0,0 +1,38 @@
+name: CI - Cursor Review
+
+# Thin caller for the shared reusable cursor-review workflow in
+# Comfy-Org/github-workflows. The review logic (panel matrix, judge
+# consolidation, prompts, extract/post/notify scripts) lives there as the
+# single source of truth, so this repo only carries the repo-specific diff
+# excludes.
+
+on:
+  pull_request:
+    types: [labeled, unlabeled]
+
+concurrency:
+  group: cursor-review-pr-${{ github.event.pull_request.number }}-${{ github.event.label.name }}
+  cancel-in-progress: true
+
+jobs:
+  cursor-review:
+    if: github.event.label.name == 'cursor-review'
+    permissions:
+      contents: read
+      pull-requests: write
+    # SHA-pinned per zizmor `unpinned-uses: hash-pin`. Bump this SHA to pick up
+    # upstream changes; keep `workflows_ref` matching so prompts/scripts load
+    # from the same commit as the workflow definition.
+    uses: Comfy-Org/github-workflows/.github/workflows/cursor-review.yml@047ca48febe3a6647608ed2e0c4331b491cb9d6a # github-workflows#9
+    with:
+      workflows_ref: 047ca48febe3a6647608ed2e0c4331b491cb9d6a
+      diff_excludes: >-
+        :!**/.claude/**
+        :!**/dist/**
+        :!**/vendor/**
+        :!**/*.generated.*
+        :!**/*.min.js
+        :!**/*.min.css
+    secrets:
+      CURSOR_API_KEY: ${{ secrets.CURSOR_API_KEY }}
+      SLACK_BOT_TOKEN: ${{ secrets.SLACK_BOT_TOKEN }}

AGENTS.md

@@ -0,0 +1,294 @@
+## Engineering Style
+
+- Keep changes small and direct. Most fixes should touch the narrowest code path
+  that explains the bug, performance issue, dtype issue, model-format issue, or
+  user-facing behavior.
+- Change the least amount of files possible. A change that touches many files is
+  more likely to be a bad change than a good one unless the broader scope is
+  directly required.
+- Prefer practical fixes over broad architecture work. Add abstractions only
+  when they remove real repeated logic or match an existing ComfyUI pattern.
+- Prefer fewer dependencies. Do not add new dependencies to ComfyUI unless they
+  are absolutely necessary.
+- Delete obsolete code aggressively when newer infrastructure makes it useless.
+  Remove dead fallbacks, migration paths, unused options, debug prints, and
+  compatibility branches that are no longer needed. Do not leave dead branches,
+  unreachable code, or functions that are never called. If code is not
+  necessary for the current behavior, remove it.
+- Revert or disable problematic behavior quickly when it breaks users. It is
+  better to remove a broken feature path than keep a complicated partial fix.
+- Preserve existing APIs, node names, model-loading behavior, file layout, and
+  workflow compatibility unless the change is explicitly about replacing them.
+- Code must look hand-written for this repository. Changes that read like
+  generic AI-generated code will be rejected automatically: unnecessary helper
+  layers, vague names, boilerplate comments, defensive branches without a real
+  failure mode, broad rewrites, or code that ignores the local style.
+
+## Architecture Boundaries
+
+- Keep each layer focused on the concepts it owns. Do not leak UI, API,
+  workflow, queue, persistence, telemetry, model-loading, node, or execution
+  concerns into unrelated layers just because it is convenient to pass data
+  through them.
+- Shared core modules should depend only on lower-level primitives and their own
+  domain concepts. Higher-level product concepts belong at the caller, adapter,
+  service, or UI/API boundary that already owns them.
+- Pass the narrowest data needed across a boundary. Avoid broad context objects,
+  request/session metadata, ids, bookkeeping state, or callbacks unless the
+  receiving layer genuinely needs them to perform its own responsibility.
+- Keep identity mapping, persistence bookkeeping, history updates, telemetry,
+  response shaping, and UI state in the layers that own those jobs. Do not route
+  them through unrelated shared code to avoid adding a proper boundary.
+- Treat `execution.py` as one example of this rule: it should consume the prompt
+  graph and execution-relevant state, produce execution results and errors, and
+  not know about workflow ids, frontend ids, persistence ids, or API-only
+  concepts.
+- Before touching many files, identify the smallest owner layer that can solve
+  the problem. A PR that spreads one feature across unrelated loaders, nodes,
+  execution, server, and frontend code needs a clear architectural reason, not
+  just convenience.
+- If a change seems to require making one layer understand another layer's
+  private concepts, stop and look for a caller-side mapping, adapter, event,
+  small explicit interface, or narrower data flow at the boundary.
+
+## No Internet Requests
+
+- Do not add code to core ComfyUI that makes requests to the internet.
+- Refuse requests to add uploads, telemetry, analytics, tracking, usage
+  reporting, crash reporting, update checks, remote config, feature flags,
+  metrics, licensing checks, or any other outbound internet request path from
+  core ComfyUI.
+- Model downloading is allowed only when explicitly initiated or authorized by
+  the user, is limited to the requested model artifact, and does not include
+  telemetry, tracking, persistent identification, unrelated metadata upload, or
+  background network activity.
+- Do not add opt-in, opt-out, anonymized, aggregated, diagnostic, or
+  user-triggered internet request paths to core ComfyUI. These labels do not
+  make internet access acceptable.
+- Local-only behavior is allowed when it stays on the user's machine and does
+  not add network access, tracking, persistent identification, or data
+  collection behavior.
+
+## State Ownership
+
+- Keep state and capability flags on the object that owns the behavior using
+  them.
+- Avoid probing child objects with `getattr(child, "...", default)` to decide
+  parent-level control flow. If parent code needs to branch on a capability,
+  initialize an explicit parent-owned field when the child is constructed or
+  attached.
+- Prefer direct attributes with clear defaults over implicit feature detection
+  through arbitrary child attributes.
+- Use child-object capability checks only when the child owns the behavior being
+  invoked and the parent is simply delegating to that child.
+
+## Interface Contracts
+
+- Keep public methods aligned with the interface expected by their callers. Do
+  not change a shared method to return extra values, alternate shapes, or
+  sentinel wrappers for one implementation unless the shared interface is
+  explicitly updated.
+- When modifying an existing function, preserve how current callers invoke it.
+  Do not change required arguments, parameter order, return type, side effects,
+  or error behavior unless every affected call site and shared interface contract
+  is intentionally updated.
+- Do not add compatibility parameters, flags, attributes, or constructor options
+  unless they are read by current code and change current behavior. Remove
+  pass-through or stored-but-unused values instead of preserving upstream or
+  deprecated API baggage.
+- If an implementation needs auxiliary values for its own workflow, expose them
+  through a private helper or a clearly named implementation-specific method
+  instead of overloading the public method's return contract.
+- Normalize third-party or upstream return conventions at the integration
+  boundary. Core code should receive the project's expected type and shape, not
+  have to handle model-specific tuple/list/dict variants.
+- Avoid caller-side unwrapping such as `out = out[0]` unless the called
+  interface is documented to return that structure.
+
+## Autograd and Model Freezing
+
+- Do not add `torch.no_grad`, `torch.inference_mode`, or inference-mode helper
+  wrappers in ComfyUI code. The only allowed inference-mode-related use is
+  disabling a globally set inference mode when a training path needs gradients.
+- Do not add freeze, unfreeze, or trainability toggles to model classes. ComfyUI
+  models are always treated as frozen for inference, so explicit freeze
+  functionality is redundant and should not be added.
+- Remove training-only behavior such as dropout from inference model code, but
+  preserve checkpoint and state-dict compatibility when doing so. If deleting a
+  module would change state-dict keys, module ordering, or checkpoint loading
+  behavior, replace it with a no-op such as `nn.Identity` instead of removing the
+  slot outright.
+
+## Python Style
+
+- Keep imports at module scope. Avoid inline imports unless they are already part
+  of an established optional-backend probe or are needed to avoid an import
+  cycle.
+- Do not add unnecessary `try`/`except` blocks. Use them for optional dependency,
+  platform, or backend capability detection only when the program has a useful
+  fallback. Prefer specific exception types when changing new code.
+- Remove any workarounds for PyTorch versions that ComfyUI no longer officially
+  supports. Deprecated workarounds include catching an exception and rerunning
+  the same op with the input cast to float. If a workaround does not have a
+  comment naming the exact PyTorch version or versions that still need it,
+  remove it.
+- Let unsupported model formats, invalid quantization metadata, and bad states
+  fail with clear errors instead of silently producing lower quality output.
+- Match the existing local style in the file you edit. This codebase tolerates
+  long lines, simple helper functions, module-level state, and direct tensor
+  operations when they make the code easier to follow.
+- Keep comments sparse and useful. Strip useless comments that restate the code
+  or describe obvious behavior. Short TODOs are fine when they name the concrete
+  missing follow-up.
+
+## Model, Device, and Memory Behavior
+
+- Treat dtype, device placement, VRAM usage, and offloading behavior as core
+  correctness concerns. Check CPU, CUDA, ROCm, MPS, DirectML, XPU, NPU, and low
+  VRAM implications when touching shared execution or loading code.
+- Prefer native ComfyUI formats and existing quantization/offload helpers over
+  adding parallel code paths. Use `comfy.quant_ops`, `comfy.model_management`,
+  `comfy.memory_management`, `comfy.pinned_memory`, `comfy_aimdo`, and
+  `comfy-kitchen` helpers where they already solve the problem.
+- Use optimized comfy-kitchen ops in places where they improve performance
+  without changing the expected dtype, device, memory, or interface behavior.
+- All models should use the optimized attention function selected by ComfyUI.
+  Treat optimized backend functions, dispatch helpers, and capability-selected
+  callables as opaque. Higher-level code must not inspect function identity,
+  names, modules, or implementation details to decide behavior.
+- Apply the same opacity rule to similar patterns beyond attention: callers
+  should depend on the documented interface and result contract, not on which
+  backend implementation was selected underneath.
+- Do not use custom inference ops that only duplicate an existing op while
+  upcasting to float32, such as custom RMSNorm variants. Use the generic ComfyUI
+  ops and/or native torch ops instead.
+- If a model class `__init__` has an `operations` parameter, assume
+  `operations` is never `None`. Do not add fallback branches or default torch
+  ops for a missing `operations` object.
+- Do not add unnecessary parameters to model, model block, or model ops related
+  classes. Constructor and forward signatures should carry only values that are
+  actually needed by that object for inference.
+- Reuse existing model classes, blocks, ops, and helper modules when appropriate.
+  Before implementing a new version of a model component, search the existing
+  model code for a class or helper that already provides the behavior.
+- Model detection code that inspects linear weight shapes should only use the
+  first dimension. The second dimension may be half the original size for
+  NVFP4 or other 4-bit quantized models.
+- Avoid adding `einops` usage in core inference code. Use native torch tensor
+  ops such as `reshape`, `view`, `permute`, `transpose`, `flatten`, `unflatten`,
+  `unsqueeze`, and `squeeze` instead.
+- Do not use tensors as general-purpose Python data structures. Keep metadata,
+  bookkeeping, counters, flags, shape math, padding math, index planning, memory
+  estimates, and control-flow decisions in plain Python values unless the data
+  must participate directly in tensor computation. Do not create tensors for
+  structural metadata that is only used for Python-side control flow. Sequence
+  lengths, cumulative offsets, split indices, window counts, slice boundaries,
+  and repeat counts should be kept as Python ints/lists from the point they are
+  computed. Do not build them as CPU/GPU tensors and then cast, move, validate,
+  or convert them back to Python for `split`, `tensor_split`, indexing plans,
+  loops, or cache keys. Avoid creating temporary tensors just to use tensor
+  methods for scalar or structural calculations.
+- Avoid unnecessary casts and transfers. Preserve the intended compute dtype,
+  storage dtype, bias dtype, and original tensor shape metadata.
+- Keep model-native latent layout handling inside the model or latent-format
+  owner, not in helper nodes. Do not collapse, expand, pack, or unpack latent
+  dimensions in nodes or other caller-side adapters just to satisfy a model
+  forward; the model path should consume and return the native latent shape for
+  that model family.
+- Assume inputs to the main model forward are already in the compute dtype by
+  default, except integer inputs such as some model timestep tensors. Do not add
+  defensive or convenience casts in model code; it is better for invalid dtype
+  plumbing to error clearly than to hide it with unnecessary casts.
+- Raw model parameters that are not owned by an op and may be initialized in a
+  dtype different from the compute dtype should be cast at use in forward or
+  inference code with `comfy.ops.cast_to_input` or
+  `comfy.model_management.cast_to` to avoid dtype mismatches.
+- Model code should not care what dtype it is initialized in, and model
+  `__init__` methods should not contain workarounds for specific dtypes. Dtype
+  workaround code, such as making a model work with fp16 compute, belongs in the
+  execution or model-management layer that owns compute policy.
+- Model code should not perform unnecessary device-to-CPU or CPU-to-device
+  transfers. New allocations must be created on the correct device and dtype;
+  never allocate on CPU and then move to GPU, or allocate in one dtype and then
+  convert to another.
+- Model code itself should not perform memory management. Loading, unloading,
+  offloading, device movement, VRAM policy, cache lifetime, and cleanup belong
+  in the relevant model-management and execution layers, not inside model
+  implementations.
+- Do not add global, module-level, class-level, singleton, or model-owned stores
+  for tensors or other large memory that persist across executions. Temporary
+  caches must be scoped to a single execution or forward/encode/decode call:
+  allocate them in the owning top-level call, pass them explicitly through the
+  call stack, and let them be discarded when that call returns.
+- Follow the Wan VAE temporal cache pattern for temporary caches: create a local
+  cache such as `feat_map` for the encode/decode operation, pass it into the
+  blocks that need it, and do not retain it on the model or in global state.
+- In model init code, prefer `torch.empty` for parameter/buffer placeholders
+  that are populated from the model state dict instead of zero-initializing with
+  `torch.zeros` or similar. If an allocation is not loaded from the state dict
+  and is useless for inference, do not include it.
+- `nn.Parameter` tensors that are stored in and populated from the model state
+  dict should be initialized with `torch.empty`, not with zero, random, or
+  otherwise meaningful initialization.
+- Model initialization should describe module structure, not fabricate
+  checkpoint-owned tensor contents. Parameters and buffers that are loaded from
+  the state dict must not be manually initialized, reassigned, or filled with
+  fallback values unless that value is actually used when no checkpoint key
+  exists.
+- When slicing large tensors, copy the slice if the sliced tensor's lifetime
+  exceeds the current function scope. Do not keep a long-lived view into a large
+  backing tensor when a smaller copy would release memory sooner.
+- Use fused or compound torch operations such as `addcmul` when they naturally
+  match the math. Reducing Python and torch dispatch overhead is a valid
+  optimization when it does not obscure the code or change dtype/device
+  behavior.
+- Avoid caches that persist across different executions as much as possible.
+  Persistent caches are acceptable only when they use a very minimal amount of
+  memory and have a clear ownership and invalidation story.
+- When optimizing, favor small measurable changes: fewer allocations, fewer
+  device transfers, less peak memory, better batching, or use of a faster
+  existing backend op.
+
+## Nodes and User-Facing Behavior
+
+- Follow existing node conventions: `INPUT_TYPES`, `RETURN_TYPES`, `FUNCTION`,
+  `CATEGORY`, and registration through the local mapping used by that file.
+- Keep node changes backward compatible by default. Add inputs with sensible
+  defaults and avoid changing output types unless the request requires it.
+- Model implementations should add the minimal number of ComfyUI nodes required
+  to run the model. Reuse existing nodes as much as possible; adapting the model
+  to work with existing nodes is strongly preferred over creating new nodes.
+- Nodes should output only values they own. Do not add pass-through outputs for
+  workflow convenience unless the node is explicitly an output node. Existing
+  models, latents, conditioning, or other inputs should flow directly to the
+  next consumer instead of being re-emitted unchanged.
+- Nodes should expose only inputs they actually read to produce current
+  behavior. Do not add placeholder, pass-through, compatibility, or
+  workflow-shaping inputs that are ignored or could flow directly to another
+  node.
+- Node-level code must not patch model code directly. Any node behavior that
+  modifies, wraps, hooks, or changes model behavior must go through the model
+  patcher class instead of reaching into model internals.
+- The official mascot of ComfyUI is a very cute anime girl with massive fennec
+  ears, a big fluffy tail, long blonde wavy hair, and blue eyes. Feel free to
+  use her in ComfyUI materials, UI text, examples, tests, generated assets, or
+  comments, but do not disrespect her.
+- Warning and info messages should be short and actionable. Remove noisy or
+  misleading messages rather than adding more logging.
+- Documentation and README edits should be concise, factual, and tied to the
+  changed behavior.
+
+## Commit and Review Habits
+
+- If asked to write commit messages, use short direct subjects like the existing
+  history: `Fix ...`, `Add ...`, `Support ...`, `Remove ...`, `Update ...`,
+  `Make ...`, `Use ...`, `Disable ...`, `Bump ...`, or `Revert ...`.
+- Keep PR descriptions short and reviewable. State the problem, the behavioral
+  change, and the tests run; avoid long narrative explanations, implementation
+  diaries, or exhaustive file-by-file summaries unless the reviewer explicitly
+  needs that context.
+- Prefer one coherent behavioral change per commit. Dependency pins, tests, and
+  the code that needs them may be in the same commit when they are inseparable.
+- In reviews, prioritize real user impact: crashes, wrong dtype/device behavior,
+  memory regressions, broken model loading, workflow incompatibility, and noisy
+  or misleading user-facing output.

CLAUDE.md

@@ -0,0 +1 @@
+AGENTS.md

README.md

@@ -140,7 +140,7 @@ ComfyUI follows a weekly release cycle targeting Monday but this regularly chang
    - Commits outside of the stable release tags may be very unstable and break many custom nodes.
    - Serves as the foundation for the desktop release
 
-2. **[ComfyUI Desktop](https://github.com/Comfy-Org/desktop)**
+2. **[Comfy Desktop](https://github.com/Comfy-Org/Comfy-Desktop)**
    - Builds a new release using the latest stable core version
 
 3. **[ComfyUI Frontend](https://github.com/Comfy-Org/ComfyUI_frontend)**
@@ -309,7 +309,7 @@ After this you should have everything installed and can proceed to running Comfy
 
 #### Apple Mac silicon
 
-You can install ComfyUI in Apple Mac silicon (M1 or M2) with any recent macOS version.
+You can install ComfyUI in Apple Mac silicon (M1, M2, M3 or M4) with any recent macOS version.
 
 1. Install pytorch nightly. For instructions, read the [Accelerated PyTorch training on Mac](https://developer.apple.com/metal/pytorch/) Apple Developer guide (make sure to install the latest pytorch nightly).
 1. Follow the [ComfyUI manual installation](#manual-install-windows-linux) instructions for Windows and Linux.
@@ -364,7 +364,7 @@ For models compatible with Iluvatar Extension for PyTorch. Here's a step-by-step
 | Flag | Description |
 |------|-------------|
 | `--enable-manager` | Enable ComfyUI-Manager |
-| `--enable-manager-legacy-ui` | Use the legacy manager UI instead of the new UI (requires `--enable-manager`) |
+| `--enable-manager-legacy-ui` | Use the legacy manager UI instead of the new UI (implies `--enable-manager`) |
 | `--disable-manager-ui` | Disable the manager UI and endpoints while keeping background features like security checks and scheduled installation completion (requires `--enable-manager`) |
 
 
@@ -382,11 +382,7 @@ For AMD 7600 and maybe other RDNA3 cards: ```HSA_OVERRIDE_GFX_VERSION=11.0.0 pyt
 
 ### AMD ROCm Tips
 
-You can enable experimental memory efficient attention on recent pytorch in ComfyUI on some AMD GPUs using this command, it should already be enabled by default on RDNA3. If this improves speed for you on latest pytorch on your GPU please report it so that I can enable it by default.
-
-```TORCH_ROCM_AOTRITON_ENABLE_EXPERIMENTAL=1 python main.py --use-pytorch-cross-attention```
-
-You can also try setting this env variable `PYTORCH_TUNABLEOP_ENABLED=1` which might speed things up at the cost of a very slow initial run.
+You can try setting this env variable `PYTORCH_TUNABLEOP_ENABLED=1` which might speed things up at the cost of a very slow initial run.
 
 # Notes
 
@@ -462,16 +458,6 @@ To use the most up-to-date frontend version:
 
 This approach allows you to easily switch between the stable fortnightly release and the cutting-edge daily updates, or even specific versions for testing purposes.
 
-### Accessing the Legacy Frontend
-
-If you need to use the legacy frontend for any reason, you can access it using the following command line argument:
-
-```
---front-end-version Comfy-Org/ComfyUI_legacy_frontend@latest
-```
-
-This will use a snapshot of the legacy frontend preserved in the [ComfyUI Legacy Frontend repository](https://github.com/Comfy-Org/ComfyUI_legacy_frontend).
-
 # QA
 
 ### Which GPU should I buy for this?

alembic_db/versions/0004_drop_tag_type.py

@@ -0,0 +1,39 @@
+"""
+Drop the vestigial tags.tag_type column.
+
+tag_type was always "user" in practice — no code path ever set it to anything
+else (no system/seeded classification was ever wired up) and nothing queried it.
+The column, its index (ix_tags_tag_type), and the corresponding API field were
+dead weight, so they are removed.
+
+Revision ID: 0004_drop_tag_type
+Revises: 0003_add_metadata_job_id
+Create Date: 2026-06-03
+"""
+
+from alembic import op
+import sqlalchemy as sa
+
+revision = "0004_drop_tag_type"
+down_revision = "0003_add_metadata_job_id"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    with op.batch_alter_table("tags") as batch_op:
+        batch_op.drop_index("ix_tags_tag_type")
+        batch_op.drop_column("tag_type")
+
+
+def downgrade() -> None:
+    with op.batch_alter_table("tags") as batch_op:
+        batch_op.add_column(
+            sa.Column(
+                "tag_type",
+                sa.String(length=32),
+                nullable=False,
+                server_default="user",
+            )
+        )
+        batch_op.create_index("ix_tags_tag_type", ["tag_type"])

app/assets/api/routes.py

@@ -39,6 +39,7 @@ from app.assets.services import (
     update_asset_metadata,
     upload_from_temp_path,
 )
+from app.assets.services.cursor import InvalidCursorError
 from app.assets.services.tagging import list_tag_histogram
 
 ROUTES = web.RouteTableDef()
@@ -174,7 +175,7 @@ def _build_asset_response(result: schemas.AssetDetailResult | schemas.UploadResu
         user_metadata=result.ref.user_metadata or {},
         metadata=result.ref.system_metadata,
         job_id=result.ref.job_id,
-        prompt_id=result.ref.job_id,  # deprecated: mirrors job_id for cloud compat
+        prompt_id=result.ref.job_id,  # deprecated alias of job_id, kept for compatibility
         created_at=result.ref.created_at,
         updated_at=result.ref.updated_at,
         last_access_time=result.ref.last_access_time,
@@ -211,24 +212,37 @@ async def list_assets_route(request: web.Request) -> web.Response:
     order_candidate = (q.order or "desc").lower()
     order = order_candidate if order_candidate in {"asc", "desc"} else "desc"
 
-    result = list_assets_page(
-        owner_id=USER_MANAGER.get_request_user_id(request),
-        include_tags=q.include_tags,
-        exclude_tags=q.exclude_tags,
-        name_contains=q.name_contains,
-        metadata_filter=q.metadata_filter,
-        limit=q.limit,
-        offset=q.offset,
-        sort=sort,
-        order=order,
-    )
+    try:
+        result = list_assets_page(
+            owner_id=USER_MANAGER.get_request_user_id(request),
+            include_tags=q.include_tags,
+            exclude_tags=q.exclude_tags,
+            name_contains=q.name_contains,
+            metadata_filter=q.metadata_filter,
+            limit=q.limit,
+            offset=q.offset,
+            sort=sort,
+            order=order,
+            after=q.after,
+        )
+    except InvalidCursorError as e:
+        return _build_error_response(400, "INVALID_CURSOR", str(e))
 
     summaries = [_build_asset_response(item) for item in result.items]
 
+    # has_more semantics differ by mode:
+    #   - cursor mode: a non-empty next_cursor means there are more results.
+    #   - offset mode: derived from total - (offset + page size).
+    if q.after is not None:
+        has_more = result.next_cursor is not None
+    else:
+        has_more = (q.offset + len(summaries)) < result.total
+
     payload = schemas_out.AssetsList(
         assets=summaries,
         total=result.total,
-        has_more=(q.offset + len(summaries)) < result.total,
+        has_more=has_more,
+        next_cursor=result.next_cursor,
     )
     return web.json_response(payload.model_dump(mode="json", exclude_none=True))
 
@@ -292,12 +306,15 @@ async def download_asset_content(request: web.Request) -> web.Response:
             404, "FILE_NOT_FOUND", "Underlying file not found on disk."
         )
 
-    _DANGEROUS_MIME_TYPES = {
-        "text/html", "text/html-sandboxed", "application/xhtml+xml",
-        "text/javascript", "text/css",
-    }
-    if content_type in _DANGEROUS_MIME_TYPES:
+    # User-controlled asset content must never render inline in the app origin
+    # (stored XSS via SVG/HTML/XML). Force dangerous types to download and
+    # override any requested inline disposition. Centralised through
+    # folder_paths.is_dangerous_content_type so this can't drift from /view and
+    # /userdata (the previous inline set here omitted image/svg+xml and missed
+    # the charset/casing/+xml-dialect bypasses).
+    if folder_paths.is_dangerous_content_type(content_type):
         content_type = "application/octet-stream"
+        disposition = "attachment"
 
     safe_name = (filename or "").replace("\r", "").replace("\n", "")
     encoded = urllib.parse.quote(safe_name)
@@ -519,18 +536,14 @@ async def update_asset_route(request: web.Request) -> web.Response:
 @_require_assets_feature_enabled
 async def delete_asset_route(request: web.Request) -> web.Response:
     reference_id = str(uuid.UUID(request.match_info["id"]))
-    delete_content_param = request.query.get("delete_content")
-    delete_content = (
-        False
-        if delete_content_param is None
-        else delete_content_param.lower() not in {"0", "false", "no"}
-    )
 
     try:
+        # Deleting an asset is a soft delete of the reference; the underlying
+        # content is preserved (it may be shared with other references).
         deleted = delete_asset_reference(
             reference_id=reference_id,
             owner_id=USER_MANAGER.get_request_user_id(request),
-            delete_content_if_orphan=delete_content,
+            delete_content_if_orphan=False,
         )
     except Exception:
         logging.exception(
@@ -575,8 +588,8 @@ async def get_tags(request: web.Request) -> web.Response:
     )
 
     tags = [
-        schemas_out.TagUsage(name=name, count=count, type=tag_type)
-        for (name, tag_type, count) in rows
+        schemas_out.TagUsage(name=name, count=count)
+        for (name, count) in rows
     ]
     payload = schemas_out.TagsList(
         tags=tags, total=total, has_more=(query.offset + len(tags)) < total

app/assets/api/schemas_in.py

@@ -59,6 +59,11 @@ class ListAssetsQuery(BaseModel):
 
     limit: conint(ge=1, le=500) = 20
     offset: conint(ge=0) = 0
+    # Opaque keyset cursor. When supplied, `offset` is ignored. Cursor pagination
+    # is supported for sort values `created_at`, `updated_at`, `name`, `size`.
+    # Supplying `after` together with `sort=last_access_time` returns
+    # 400 INVALID_CURSOR; that sort only supports offset/limit.
+    after: str | None = None
 
     sort: Literal["name", "created_at", "updated_at", "size", "last_access_time"] = (
         "created_at"

app/assets/api/schemas_out.py

@@ -41,12 +41,13 @@ class AssetsList(BaseModel):
     assets: list[Asset]
     total: int
     has_more: bool
+    # Opaque cursor for the next page. Omitted when there are no more results.
+    next_cursor: str | None = None
 
 
 class TagUsage(BaseModel):
     name: str
     count: int
-    type: str
 
 
 class TagsList(BaseModel):

app/assets/database/models.py

@@ -227,7 +227,6 @@ class Tag(Base):
     __tablename__ = "tags"
 
     name: Mapped[str] = mapped_column(String(512), primary_key=True)
-    tag_type: Mapped[str] = mapped_column(String(32), nullable=False, default="user")
 
     asset_reference_links: Mapped[list[AssetReferenceTag]] = relationship(
         back_populates="tag",
@@ -240,7 +239,5 @@ class Tag(Base):
         overlaps="asset_reference_links,tag_links,tags,asset_reference",
     )
 
-    __table_args__ = (Index("ix_tags_tag_type", "tag_type"),)
-
     def __repr__(self) -> str:
         return f"<Tag {self.name}>"

app/assets/database/queries/asset_reference.py

@@ -266,9 +266,18 @@ def list_references_page(
     metadata_filter: dict | None = None,
     sort: str | None = None,
     order: str | None = None,
+    after_cursor_value: object | None = None,
+    after_cursor_id: str | None = None,
 ) -> tuple[list[AssetReference], dict[str, list[str]], int]:
     """List references with pagination, filtering, and sorting.
 
+    When ``after_cursor_value``/``after_cursor_id`` are supplied the query uses
+    keyset pagination — ``offset`` is ignored and a WHERE clause selects rows
+    strictly after the given ``(sort_col, id)`` position in the active sort
+    direction. The cursor value must already be typed for the column
+    (datetime for time sorts, int for size, str for name); the caller decodes
+    the opaque cursor string and resolves to the typed value.
+
     Returns (references, tag_map, total_count).
     """
     base = (
@@ -297,9 +306,31 @@ def list_references_page(
         "size": Asset.size_bytes,
     }
     sort_col = sort_map.get(sort, AssetReference.created_at)
-    sort_exp = sort_col.desc() if order == "desc" else sort_col.asc()
+    descending = order == "desc"
 
-    base = base.order_by(sort_exp).limit(limit).offset(offset)
+    # Keyset WHERE: (sort_col, id) strictly less-than / greater-than the cursor.
+    # Equivalent to: sort_col <op> v  OR  (sort_col = v AND id <op> cursor_id).
+    if after_cursor_value is not None and after_cursor_id is not None:
+        if descending:
+            keyset = sa.or_(
+                sort_col < after_cursor_value,
+                sa.and_(sort_col == after_cursor_value, AssetReference.id < after_cursor_id),
+            )
+        else:
+            keyset = sa.or_(
+                sort_col > after_cursor_value,
+                sa.and_(sort_col == after_cursor_value, AssetReference.id > after_cursor_id),
+            )
+        base = base.where(keyset)
+
+    # Secondary ORDER BY id (matching the primary direction) gives the keyset
+    # comparison a deterministic tiebreaker on duplicate sort_col values.
+    id_exp = AssetReference.id.desc() if descending else AssetReference.id.asc()
+    sort_exp = sort_col.desc() if descending else sort_col.asc()
+
+    base = base.order_by(sort_exp, id_exp).limit(limit)
+    if after_cursor_id is None:
+        base = base.offset(offset)
 
     count_stmt = (
         select(sa.func.count())

app/assets/database/queries/tags.py

@@ -55,13 +55,11 @@ def validate_tags_exist(session: Session, tags: list[str]) -> None:
         raise ValueError(f"Unknown tags: {missing}")
 
 
-def ensure_tags_exist(
-    session: Session, names: Iterable[str], tag_type: str = "user"
-) -> None:
+def ensure_tags_exist(session: Session, names: Iterable[str]) -> None:
     wanted = normalize_tags(list(names))
     if not wanted:
         return
-    rows = [{"name": n, "tag_type": tag_type} for n in list(dict.fromkeys(wanted))]
+    rows = [{"name": n} for n in list(dict.fromkeys(wanted))]
     ins = (
         sqlite.insert(Tag)
         .values(rows)
@@ -97,7 +95,7 @@ def set_reference_tags(
     to_remove = [t for t in current if t not in desired]
 
     if to_add:
-        ensure_tags_exist(session, to_add, tag_type="user")
+        ensure_tags_exist(session, to_add)
         session.add_all(
             [
                 AssetReferenceTag(
@@ -142,7 +140,7 @@ def add_tags_to_reference(
         return AddTagsResult(added=[], already_present=[], total_tags=total)
 
     if create_if_missing:
-        ensure_tags_exist(session, norm, tag_type="user")
+        ensure_tags_exist(session, norm)
 
     current = set(get_reference_tags(session, reference_id))
 
@@ -289,7 +287,6 @@ def list_tags_with_usage(
     q = (
         select(
             Tag.name,
-            Tag.tag_type,
             func.coalesce(counts_sq.c.cnt, 0).label("count"),
         )
         .select_from(Tag)
@@ -331,7 +328,7 @@ def list_tags_with_usage(
     rows = (session.execute(q.limit(limit).offset(offset))).all()
     total = (session.execute(total_q)).scalar_one()
 
-    rows_norm = [(name, ttype, int(count or 0)) for (name, ttype, count) in rows]
+    rows_norm = [(name, int(count or 0)) for (name, count) in rows]
     return rows_norm, int(total or 0)
 
 

app/assets/scanner.py

@@ -33,6 +33,7 @@ from app.assets.services.file_utils import (
     verify_file_unchanged,
 )
 from app.assets.services.hashing import HashCheckpoint, compute_blake3_hash
+from app.assets.services.image_dimensions import extract_image_dimensions
 from app.assets.services.metadata_extract import extract_file_metadata
 from app.assets.services.path_utils import (
     compute_relative_filename,
@@ -354,7 +355,7 @@ def insert_asset_specs(specs: list[SeedAssetSpec], tag_pool: set[str]) -> int:
         return 0
     with create_session() as sess:
         if tag_pool:
-            ensure_tags_exist(sess, tag_pool, tag_type="user")
+            ensure_tags_exist(sess, tag_pool)
         result = batch_insert_seed_assets(sess, specs=specs, owner_id="")
         sess.commit()
         return result.inserted_refs
@@ -506,6 +507,10 @@ def enrich_asset(
 
     if extract_metadata and metadata:
         system_metadata = metadata.to_user_metadata()
+        if mime_type and mime_type.startswith("image/"):
+            dims = extract_image_dimensions(file_path, mime_type=mime_type)
+            if dims:
+                system_metadata.update(dims)
         set_reference_system_metadata(session, reference_id, system_metadata)
 
     if full_hash:

app/assets/services/asset_management.py

@@ -1,8 +1,19 @@
 import contextlib
 import mimetypes
 import os
+from datetime import timezone
 from typing import Sequence
 
+from app.assets.services.cursor import (
+    CursorPayload,
+    InvalidCursorError,
+    decode_cursor,
+    decode_cursor_int,
+    decode_cursor_time,
+    encode_cursor,
+    encode_cursor_from_time,
+)
+
 
 from app.assets.database.models import Asset
 from app.assets.database.queries import (
@@ -149,6 +160,16 @@ def delete_asset_reference(
     owner_id: str,
     delete_content_if_orphan: bool = True,
 ) -> bool:
+    """Delete an asset reference.
+
+    With ``delete_content_if_orphan=False`` (a soft delete), the reference is
+    hidden and the underlying content is preserved. With ``True``, the content
+    is also removed once it becomes orphaned.
+
+    Note: the public DELETE /api/assets/{id} endpoint always soft-deletes
+    (passes ``False``); the orphan-reclamation path is intentionally
+    internal-only, retained for a future GC/admin caller.
+    """
     with create_session() as session:
         if not delete_content_if_orphan:
             # Soft delete: mark the reference as deleted but keep everything
@@ -242,6 +263,11 @@ def get_asset_by_hash(asset_hash: str) -> AssetData | None:
         return extract_asset_data(asset)
 
 
+# Sort fields that support cursor pagination. `last_access_time` is not
+# in this list — it falls back to offset/limit.
+_CURSOR_SORT_FIELDS = ("created_at", "updated_at", "name", "size")
+
+
 def list_assets_page(
     owner_id: str = "",
     include_tags: Sequence[str] | None = None,
@@ -252,7 +278,39 @@ def list_assets_page(
     offset: int = 0,
     sort: str = "created_at",
     order: str = "desc",
+    after: str | None = None,
 ) -> ListAssetsResult:
+    """List assets with optional cursor pagination.
+
+    When ``after`` is supplied it overrides ``offset``. The cursor's sort field
+    must match ``sort`` and be in the cursor-supported allowlist; mismatches
+    raise InvalidCursorError so the handler can map to 400 INVALID_CURSOR.
+    """
+    cursor_value: object | None = None
+    cursor_id: str | None = None
+    # Mint next_cursor on every page where the sort is cursor-supported, not
+    # only when the request itself arrived with a cursor. Otherwise a first
+    # request (no `after`) returns next_cursor=None and the client can never
+    # enter cursor mode.
+    mint_cursor = sort in _CURSOR_SORT_FIELDS
+
+    if after is not None:
+        if sort not in _CURSOR_SORT_FIELDS:
+            raise InvalidCursorError(
+                f"cursor pagination is not supported for sort={sort!r}"
+            )
+        payload = decode_cursor(after, _CURSOR_SORT_FIELDS, expected_order=order)
+        if payload.sort_field != sort:
+            raise InvalidCursorError(
+                f"cursor sort field {payload.sort_field!r} does not match request sort {sort!r}"
+            )
+        cursor_value, cursor_id = _resolve_cursor_value(payload), payload.id
+
+    # Over-fetch by one row so we can distinguish "exactly `limit` rows total
+    # remaining" from "more rows past this page" without a second query. Drop
+    # the sentinel before returning.
+    fetch_limit = limit + 1 if mint_cursor else limit
+
     with create_session() as session:
         refs, tag_map, total = list_references_page(
             session,
@@ -261,12 +319,22 @@ def list_assets_page(
             exclude_tags=exclude_tags,
             name_contains=name_contains,
             metadata_filter=metadata_filter,
-            limit=limit,
+            limit=fetch_limit,
             offset=offset,
             sort=sort,
             order=order,
+            after_cursor_value=cursor_value,
+            after_cursor_id=cursor_id,
         )
 
+        next_cursor: str | None = None
+        if mint_cursor and len(refs) > limit:
+            # There's at least one more row past this page — mint a cursor from
+            # the last row of the page (i.e. index `limit - 1`, since we
+            # over-fetched), and drop the sentinel.
+            next_cursor = _encode_next_cursor(refs[limit - 1], sort, order)
+            refs = refs[:limit]
+
         items: list[AssetSummaryData] = []
         for ref in refs:
             items.append(
@@ -277,7 +345,39 @@ def list_assets_page(
                 )
             )
 
-        return ListAssetsResult(items=items, total=total)
+        return ListAssetsResult(items=items, total=total, next_cursor=next_cursor)
+
+
+def _resolve_cursor_value(payload: CursorPayload) -> object:
+    """Map a decoded cursor payload to a column-typed Python value."""
+    if payload.sort_field in ("created_at", "updated_at"):
+        # DB stores naive UTC; strip tzinfo so the comparison binds against a
+        # `TIMESTAMP WITHOUT TIME ZONE` column without an offset shift.
+        return decode_cursor_time(payload).replace(tzinfo=None)
+    if payload.sort_field == "size":
+        return decode_cursor_int(payload)
+    return payload.value  # name, str-typed
+
+
+def _encode_next_cursor(ref, sort: str, order: str) -> str | None:
+    """Mint a cursor pointing at *ref* for the given sort dimension.
+
+    Returns None when the boundary row carries a NULL sort value (e.g. an asset
+    record whose size_bytes hasn't been backfilled). Continuing pagination
+    across a NULL boundary is undefined under keyset ordering — better to
+    truncate cleanly here than to mint a cursor that mis-positions.
+    """
+    if sort == "name":
+        return encode_cursor("name", ref.name, ref.id, order=order)
+    if sort == "size":
+        if ref.asset is None or ref.asset.size_bytes is None:
+            return None
+        return encode_cursor("size", str(ref.asset.size_bytes), ref.id, order=order)
+    # created_at / updated_at — DB datetimes are naive UTC; attach tz before encoding.
+    value = ref.created_at if sort == "created_at" else ref.updated_at
+    if value is None:
+        return None
+    return encode_cursor_from_time(sort, value.replace(tzinfo=timezone.utc), ref.id, order=order)
 
 
 def resolve_hash_to_path(

app/assets/services/cursor.py

@@ -0,0 +1,213 @@
+"""Opaque keyset-pagination cursor for /api/assets.
+
+Payload JSON uses short keys to keep the encoded length small:
+
+    {"s": <sort_field>, "v": <value>, "id": <id>, "o": <order>}
+
+The `o` key binds the cursor to the sort direction it was minted under,
+so replaying a `desc` cursor against an `asc` request fails with
+``INVALID_CURSOR`` rather than silently walking the wrong direction.
+`o` is mandatory on every payload — a cursor without it is rejected as
+malformed.
+
+Encoding is base64url with no padding. Cursors are opaque tokens: the
+payload format is internal to this server, and clients must treat a
+cursor as a black box handed back via `next_cursor`. No byte-level
+compatibility with any other implementation is required.
+
+Time values are serialized as Unix microseconds (UTC) — microsecond
+precision is sufficient to round-trip the timestamps stored by the
+database without rounding rows in the same millisecond bucket.
+"""
+from __future__ import annotations
+
+import base64
+import json
+from dataclasses import dataclass
+from datetime import datetime, timezone
+from typing import Iterable, Optional
+
+
+class InvalidCursorError(ValueError):
+    """Raised on a malformed, oversized, or unsupported-sort-field cursor.
+
+    Map to a 400 response with code ``INVALID_CURSOR`` at the handler.
+    """
+
+
+# Wire-format length caps. Cursors are user-controlled, so caps protect the
+# decode path from oversized allocations and downstream SQL predicates from
+# unbounded strings.
+#
+# MAX_CURSOR_VALUE_LENGTH is 512 to fit the `AssetReference.name` column max
+# (`String(512)`) — otherwise a long-named asset would mint a cursor the same
+# server then refuses on the next request.
+#
+# MAX_ENCODED_CURSOR_LENGTH is the decode-path guard, sized comfortably above
+# the largest cursor the per-field caps can produce. Worst case is value + id
+# at their caps with every character JSON-escaping to the six-byte `\uXXXX`
+# form (control characters), which is ~5.2 KB once base64url-encoded. At 8192
+# the encoder can never mint a cursor that exceeds it, so a freshly minted
+# cursor always decodes on the next request and there is no user-visible
+# "cursor too long" failure.
+MAX_ENCODED_CURSOR_LENGTH = 8192
+MAX_CURSOR_VALUE_LENGTH = 512
+MAX_CURSOR_ID_LENGTH = 128
+
+
+@dataclass(frozen=True)
+class CursorPayload:
+    sort_field: str
+    value: str
+    id: str
+    order: str
+
+
+_VALID_ORDERS = ("asc", "desc")
+
+
+def encode_cursor(sort_field: str, value: str, id: str, order: str = "desc") -> str:
+    """Encode a cursor payload as a base64url (no-padding) string.
+
+    `order` binds the cursor to the sort direction it was minted under so a
+    later request with a flipped `order` query parameter is rejected with
+    ``INVALID_CURSOR`` rather than silently walking the wrong direction.
+    """
+    if order not in _VALID_ORDERS:
+        raise InvalidCursorError(f"order must be one of {_VALID_ORDERS}, got {order!r}")
+    # Symmetric input validation: the encoder must reject anything the
+    # decoder rejects, or the same server will mint cursors it then 400s on
+    # the next request.
+    if not id:
+        raise InvalidCursorError("id must be non-empty")
+    if len(id) > MAX_CURSOR_ID_LENGTH:
+        raise InvalidCursorError("id exceeds maximum length")
+    if len(value) > MAX_CURSOR_VALUE_LENGTH:
+        raise InvalidCursorError("value exceeds maximum length")
+    payload = {"s": sort_field, "v": value, "id": id, "o": order}
+    raw = json.dumps(payload, separators=(",", ":"), ensure_ascii=False)
+    # No mint-time length guard is needed: the per-field caps above bound the
+    # encoded length well below MAX_ENCODED_CURSOR_LENGTH (see its definition),
+    # so the encoder can never produce a cursor the decode path would reject.
+    return base64.urlsafe_b64encode(raw.encode("utf-8")).rstrip(b"=").decode("ascii")
+
+
+def encode_cursor_from_time(sort_field: str, t: datetime, id: str, order: str = "desc") -> str:
+    """Encode a time-typed cursor at Unix microsecond precision.
+
+    Accepts an aware datetime (any timezone) and normalizes to UTC. Naive
+    datetimes are rejected so callers can't accidentally encode the local
+    wall-clock value of a UTC-stored timestamp.
+    """
+    if t.tzinfo is None:
+        raise ValueError("encode_cursor_from_time requires an aware datetime")
+    micros = _datetime_to_unix_micros(t.astimezone(timezone.utc))
+    return encode_cursor(sort_field, str(micros), id, order=order)
+
+
+def decode_cursor(
+    cursor: str,
+    allowed_sort_fields: Iterable[str],
+    expected_order: str | None = None,
+) -> CursorPayload:
+    """Parse an opaque cursor.
+
+    ``allowed_sort_fields`` is the endpoint's accepted sort-field list — a
+    cursor carrying a field outside this set is rejected so a cursor minted
+    for one column can't be replayed against another (e.g. a ``created_at``
+    timestamp string compared against a ``name`` column).
+
+    ``expected_order`` (``"asc"``/``"desc"``), when supplied, must match the
+    payload's ``o`` field. ``o`` is required on every payload; a cursor
+    missing it is rejected as malformed.
+
+    Passing no allowed fields rejects every cursor.
+    """
+    if len(cursor) > MAX_ENCODED_CURSOR_LENGTH:
+        raise InvalidCursorError("cursor exceeds maximum length")
+
+    try:
+        # urlsafe_b64decode requires correct padding; we strip on encode, so
+        # restore the trailing '=' pad here.
+        padding = "=" * (-len(cursor) % 4)
+        raw = base64.urlsafe_b64decode(cursor + padding)
+    except (ValueError, base64.binascii.Error) as e:
+        raise InvalidCursorError(f"encoding: {e}") from e
+
+    try:
+        decoded = json.loads(raw)
+    except (json.JSONDecodeError, UnicodeDecodeError) as e:
+        raise InvalidCursorError(f"payload: {e}") from e
+
+    if not isinstance(decoded, dict):
+        raise InvalidCursorError("payload: expected object")
+
+    sort_field = decoded.get("s")
+    value = decoded.get("v")
+    id = decoded.get("id")
+    order = decoded.get("o")
+
+    if not isinstance(sort_field, str) or not isinstance(value, str) or not isinstance(id, str):
+        raise InvalidCursorError("payload: missing or non-string s/v/id")
+
+    if id == "":
+        raise InvalidCursorError("missing id")
+    if len(id) > MAX_CURSOR_ID_LENGTH:
+        raise InvalidCursorError("id exceeds maximum length")
+    if len(value) > MAX_CURSOR_VALUE_LENGTH:
+        raise InvalidCursorError("value exceeds maximum length")
+
+    if sort_field not in allowed_sort_fields:
+        raise InvalidCursorError(f"unsupported sort field {sort_field!r}")
+
+    if not isinstance(order, str):
+        raise InvalidCursorError("missing or non-string o")
+    if order not in _VALID_ORDERS:
+        raise InvalidCursorError(f"unsupported order {order!r}")
+    if expected_order is not None and order != expected_order:
+        raise InvalidCursorError(
+            f"cursor order {order!r} does not match request order {expected_order!r}"
+        )
+
+    return CursorPayload(sort_field=sort_field, value=value, id=id, order=order)
+
+
+def decode_cursor_time(payload: Optional[CursorPayload]) -> datetime:
+    """Parse a time-typed cursor value as Unix microseconds, returning UTC."""
+    if payload is None:
+        raise InvalidCursorError("nil cursor payload")
+    try:
+        micros = int(payload.value)
+    except ValueError as e:
+        raise InvalidCursorError(f"value is not a valid timestamp: {e}") from e
+    try:
+        return _unix_micros_to_datetime(micros)
+    except (OverflowError, OSError, ValueError) as e:
+        # Crafted out-of-range microseconds (e.g. > datetime.MAX_YEAR) blow up
+        # in fromtimestamp / datetime construction. Map to 400, not 500.
+        raise InvalidCursorError(f"value is out of representable range: {e}") from e
+
+
+def decode_cursor_int(payload: Optional[CursorPayload]) -> int:
+    """Parse a cursor value as a base-10 integer."""
+    if payload is None:
+        raise InvalidCursorError("nil cursor payload")
+    try:
+        return int(payload.value)
+    except ValueError as e:
+        raise InvalidCursorError(f"value is not a valid integer: {e}") from e
+
+
+_EPOCH = datetime(1970, 1, 1, tzinfo=timezone.utc)
+
+
+def _datetime_to_unix_micros(t: datetime) -> int:
+    """Convert an aware UTC datetime to Unix microseconds (integer math)."""
+    delta = t - _EPOCH
+    return (delta.days * 86_400 + delta.seconds) * 1_000_000 + delta.microseconds
+
+
+def _unix_micros_to_datetime(micros: int) -> datetime:
+    """Convert Unix microseconds to a UTC datetime, preserving precision."""
+    seconds, micro_remainder = divmod(micros, 1_000_000)
+    return datetime.fromtimestamp(seconds, tz=timezone.utc).replace(microsecond=micro_remainder)

app/assets/services/image_dimensions.py

@@ -0,0 +1,63 @@
+"""Image dimension extraction for asset ingest.
+
+Reads only the image header via Pillow to capture width/height cheaply,
+without a full pixel decode. Returns a metadata dict suitable for merging
+into ``AssetReference.system_metadata``.
+"""
+from __future__ import annotations
+
+import logging
+from typing import Any
+
+logger = logging.getLogger(__name__)
+
+
+def extract_image_dimensions(
+    file_path: str, mime_type: str | None = None
+) -> dict[str, Any] | None:
+    """Extract image dimensions for the file at ``file_path``.
+
+    Args:
+        file_path: Absolute path to a file on disk.
+        mime_type: Optional MIME type hint. When provided and not prefixed
+            with ``image/``, extraction is skipped without touching the file.
+
+    Returns:
+        ``{"kind": "image", "width": W, "height": H}`` when the file is a
+        recognizable image with positive dimensions, otherwise ``None``.
+
+    The dict shape is intended to be merged into ``system_metadata`` so the
+    asset response surfaces ``metadata.kind`` plus dimension fields for image
+    assets. Forward-compatible: future media kinds (e.g. ``"video"`` with
+    duration/fps) can extend this shape without schema changes.
+    """
+    if mime_type is not None and not mime_type.startswith("image/"):
+        return None
+
+    try:
+        from PIL import Image, UnidentifiedImageError
+    except ImportError:
+        logger.debug(
+            "Pillow not available; skipping image dimension extraction for %s",
+            file_path,
+        )
+        return None
+
+    try:
+        with Image.open(file_path) as img:
+            width, height = img.size
+    except (OSError, UnidentifiedImageError, ValueError) as exc:
+        logger.debug(
+            "Failed to read image dimensions from %s: %s", file_path, exc
+        )
+        return None
+
+    if (
+        not isinstance(width, int)
+        or not isinstance(height, int)
+        or width <= 0
+        or height <= 0
+    ):
+        return None
+
+    return {"kind": "image", "width": width, "height": height}

app/assets/services/ingest.py

@@ -17,9 +17,11 @@ from app.assets.database.queries import (
     get_reference_by_file_path,
     get_reference_tags,
     get_or_create_reference,
+    list_references_by_asset_id,
     reference_exists,
     remove_missing_tag_for_asset_id,
     set_reference_metadata,
+    set_reference_system_metadata,
     set_reference_tags,
     update_asset_hash_and_mime,
     upsert_asset,
@@ -29,6 +31,7 @@ from app.assets.database.queries import (
 from app.assets.helpers import get_utc_now, normalize_tags
 from app.assets.services.bulk_ingest import batch_insert_seed_assets
 from app.assets.services.file_utils import get_size_and_mtime_ns
+from app.assets.services.image_dimensions import extract_image_dimensions
 from app.assets.services.path_utils import (
     compute_relative_filename,
     get_name_and_tags_from_asset_path,
@@ -118,6 +121,14 @@ def _ingest_file_from_path(
                 user_metadata=user_metadata,
             )
 
+            _maybe_store_image_dimensions(
+                session,
+                reference_id=reference_id,
+                file_path=locator,
+                mime_type=mime_type,
+                current_system_metadata=ref.system_metadata,
+            )
+
         try:
             remove_missing_tag_for_asset_id(session, asset_id=asset.id)
         except Exception:
@@ -288,6 +299,13 @@ def _register_existing_asset(
                 user_metadata=new_meta,
             )
 
+        _backfill_image_dimensions_from_siblings(
+            session,
+            asset_id=asset.id,
+            new_reference_id=ref.id,
+            current_system_metadata=ref.system_metadata,
+        )
+
         if tags is not None:
             set_reference_tags(
                 session,
@@ -334,6 +352,87 @@ def _update_metadata_with_filename(
         )
 
 
+_IMAGE_DIMENSION_KEYS = ("kind", "width", "height")
+
+
+def _maybe_store_image_dimensions(
+    session: Session,
+    reference_id: str,
+    file_path: str,
+    mime_type: str | None,
+    current_system_metadata: dict | None,
+) -> None:
+    """Populate ``kind``/``width``/``height`` on system_metadata for image refs.
+
+    Non-image MIME types are a no-op. Pre-existing keys (e.g. enricher-written
+    safetensors metadata, download provenance) are preserved by merge.
+    """
+    if not mime_type or not mime_type.startswith("image/"):
+        return
+
+    dims = extract_image_dimensions(file_path, mime_type=mime_type)
+    if not dims:
+        return
+
+    current = current_system_metadata or {}
+    merged = dict(current)
+    merged.update(dims)
+    if merged != current:
+        set_reference_system_metadata(
+            session,
+            reference_id=reference_id,
+            system_metadata=merged,
+        )
+
+
+def _backfill_image_dimensions_from_siblings(
+    session: Session,
+    asset_id: str,
+    new_reference_id: str,
+    current_system_metadata: dict | None,
+) -> None:
+    """Copy image dimension keys from any sibling reference of the same asset.
+
+    The from-hash path doesn't read the file bytes, so dimensions can't be
+    extracted there directly. When another reference of the same asset already
+    carries image dimensions, copy them onto the new reference so consumers
+    see consistent metadata regardless of how the asset was registered.
+
+    Best-effort: missing siblings, non-image siblings, or absent dimension
+    keys leave the target reference unchanged.
+    """
+    current = current_system_metadata or {}
+    if current.get("kind") == "image" and "width" in current and "height" in current:
+        return
+
+    for sibling in list_references_by_asset_id(session, asset_id):
+        if sibling.id == new_reference_id:
+            continue
+        meta = sibling.system_metadata or {}
+        if meta.get("kind") != "image":
+            continue
+        width = meta.get("width")
+        height = meta.get("height")
+        if (
+            type(width) is not int
+            or type(height) is not int
+            or width <= 0
+            or height <= 0
+        ):
+            continue
+        merged = dict(current)
+        merged["kind"] = "image"
+        merged["width"] = width
+        merged["height"] = height
+        if merged != current:
+            set_reference_system_metadata(
+                session,
+                reference_id=new_reference_id,
+                system_metadata=merged,
+            )
+        return
+
+
 def _sanitize_filename(name: str | None, fallback: str) -> str:
     n = os.path.basename((name or "").strip() or fallback)
     return n if n else fallback

app/assets/services/schemas.py

@@ -56,7 +56,6 @@ class IngestResult:
 
 class TagUsage(NamedTuple):
     name: str
-    tag_type: str
     count: int
 
 
@@ -71,6 +70,7 @@ class AssetSummaryData:
 class ListAssetsResult:
     items: list[AssetSummaryData]
     total: int
+    next_cursor: str | None = None
 
 
 @dataclass(frozen=True)

app/assets/services/tagging.py

@@ -75,7 +75,7 @@ def list_tags(
             owner_id=owner_id,
         )
 
-    return [TagUsage(name, tag_type, count) for name, tag_type, count in rows], total
+    return [TagUsage(name, count) for name, count in rows], total
 
 
 def list_tag_histogram(

app/model_manager.py

@@ -50,21 +50,45 @@ class ModelFileManager:
         @routes.get("/experiment/models/preview/{folder}/{path_index}/{filename:.*}")
         async def get_model_preview(request):
             folder_name = request.match_info.get("folder", None)
-            path_index = int(request.match_info.get("path_index", None))
             filename = request.match_info.get("filename", None)
 
             if folder_name not in folder_paths.folder_names_and_paths:
                 return web.Response(status=404)
 
+            # The "{filename:.*}" capture also matches the empty string, which
+            # would resolve to the folder itself; reject it explicitly.
+            if not filename:
+                return web.Response(status=400)
+
+            try:
+                path_index = int(request.match_info.get("path_index", None))
+            except (TypeError, ValueError):
+                return web.Response(status=400)
+
             folders = folder_paths.folder_names_and_paths[folder_name]
+            if path_index < 0 or path_index >= len(folders[0]):
+                return web.Response(status=404)
             folder = folders[0][path_index]
-            full_filename = os.path.join(folder, filename)
+            full_filename = os.path.normpath(os.path.join(folder, filename))
+
+            # Prevent path traversal: the requested file must stay within the
+            # configured model folder. `filename` is an unrestricted ".*" capture,
+            # so values like "../../../../etc/passwd" would otherwise escape it.
+            if not folder_paths.is_within_directory(folder, full_filename):
+                return web.Response(status=403)
 
             previews = self.get_model_previews(full_filename)
             default_preview = previews[0] if len(previews) > 0 else None
             if default_preview is None or (isinstance(default_preview, str) and not os.path.isfile(default_preview)):
                 return web.Response(status=404)
 
+            # The preview is selected by a glob inside get_model_previews, so a
+            # companion file (e.g. "model.preview.png") could itself be a symlink
+            # resolving outside the model folder. Re-validate the file actually
+            # opened: is_within_directory realpaths it, catching symlink escape.
+            if isinstance(default_preview, str) and not folder_paths.is_within_directory(folder, default_preview):
+                return web.Response(status=403)
+
             try:
                 with Image.open(default_preview) as img:
                     img_bytes = BytesIO()

app/user_manager.py

@@ -6,6 +6,7 @@ import glob
 import shutil
 import logging
 import tempfile
+import mimetypes
 from aiohttp import web
 from urllib import parse
 from comfy.cli_args import args
@@ -336,7 +337,20 @@ class UserManager():
             if not isinstance(path, str):
                 return path
 
-            return web.FileResponse(path)
+            # User data files are arbitrary user-supplied content and are never
+            # meant to render inline. Disable MIME sniffing and force a download
+            # so uploaded markup/scripts can't execute in the app origin (stored
+            # XSS). Content-Disposition: attachment is the load-bearing guard;
+            # the content-type override and nosniff are defence in depth.
+            content_type = mimetypes.guess_type(path)[0] or 'application/octet-stream'
+            if folder_paths.is_dangerous_content_type(content_type):
+                content_type = 'application/octet-stream'
+
+            return web.FileResponse(path, headers={
+                "Content-Type": content_type,
+                "X-Content-Type-Options": "nosniff",
+                "Content-Disposition": "attachment",
+            })
 
         @routes.post("/userdata/{file}")
         async def post_userdata(request):

blueprints/Image Depth Estimation (Depth Anything 3).json

@@ -0,0 +1,569 @@
+{
+  "revision": 0,
+  "last_node_id": 89,
+  "last_link_id": 0,
+  "nodes": [
+    {
+      "id": 89,
+      "type": "85e595bd-af9e-40ee-85c5-b98bb15da47a",
+      "pos": [
+        320,
+        520
+      ],
+      "size": [
+        400,
+        360
+      ],
+      "flags": {},
+      "order": 3,
+      "mode": 0,
+      "inputs": [
+        {
+          "localized_name": "image",
+          "name": "image",
+          "type": "IMAGE",
+          "link": null
+        },
+        {
+          "name": "resolution",
+          "type": "INT",
+          "widget": {
+            "name": "resolution"
+          },
+          "link": null
+        },
+        {
+          "name": "resize_method",
+          "type": "COMBO",
+          "widget": {
+            "name": "resize_method"
+          },
+          "link": null
+        },
+        {
+          "label": "output_type",
+          "name": "output",
+          "type": "COMFY_DYNAMICCOMBO_V3",
+          "widget": {
+            "name": "output"
+          },
+          "link": null
+        },
+        {
+          "label": "output_normalization",
+          "name": "output.normalization",
+          "type": "COMBO",
+          "widget": {
+            "name": "output.normalization"
+          },
+          "link": null
+        },
+        {
+          "label": "apply_sky_clip",
+          "name": "output.apply_sky_clip",
+          "type": "BOOLEAN",
+          "widget": {
+            "name": "output.apply_sky_clip"
+          },
+          "link": null
+        },
+        {
+          "name": "model_name",
+          "type": "COMBO",
+          "widget": {
+            "name": "model_name"
+          },
+          "link": null
+        }
+      ],
+      "outputs": [
+        {
+          "localized_name": "IMAGE",
+          "name": "IMAGE",
+          "type": "IMAGE",
+          "links": []
+        }
+      ],
+      "properties": {
+        "proxyWidgets": [
+          [
+            "87",
+            "resolution"
+          ],
+          [
+            "87",
+            "resize_method"
+          ],
+          [
+            "86",
+            "output"
+          ],
+          [
+            "86",
+            "output.normalization"
+          ],
+          [
+            "86",
+            "output.apply_sky_clip"
+          ],
+          [
+            "88",
+            "model_name"
+          ]
+        ],
+        "cnr_id": "comfy-core",
+        "ver": "0.24.0"
+      },
+      "widgets_values": [],
+      "title": "Image Depth Estimation (Depth Anything 3)"
+    }
+  ],
+  "links": [],
+  "version": 0.4,
+  "definitions": {
+    "subgraphs": [
+      {
+        "id": "85e595bd-af9e-40ee-85c5-b98bb15da47a",
+        "version": 1,
+        "state": {
+          "lastGroupId": 4,
+          "lastNodeId": 89,
+          "lastLinkId": 109,
+          "lastRerouteId": 0
+        },
+        "revision": 2,
+        "config": {},
+        "name": "Image Depth Estimation (Depth Anything 3)",
+        "inputNode": {
+          "id": -10,
+          "bounding": [
+            400,
+            90,
+            166.998046875,
+            188
+          ]
+        },
+        "outputNode": {
+          "id": -20,
+          "bounding": [
+            1250,
+            146,
+            128,
+            68
+          ]
+        },
+        "inputs": [
+          {
+            "id": "43cf3118-495a-487d-8eb3-a17c7e92f64f",
+            "name": "image",
+            "type": "IMAGE",
+            "linkIds": [
+              19
+            ],
+            "localized_name": "image",
+            "pos": [
+              542.998046875,
+              114
+            ]
+          },
+          {
+            "id": "1089a0a1-6db1-45a8-84b0-0bfdc2ed920a",
+            "name": "resolution",
+            "type": "INT",
+            "linkIds": [
+              22
+            ],
+            "pos": [
+              542.998046875,
+              134
+            ]
+          },
+          {
+            "id": "25fb64ac-26d5-466d-995b-6d51b9afa2c4",
+            "name": "resize_method",
+            "type": "COMBO",
+            "linkIds": [
+              23
+            ],
+            "pos": [
+              542.998046875,
+              154
+            ]
+          },
+          {
+            "id": "8acafb7c-6c8b-46b3-9d74-c563498a3af1",
+            "name": "output",
+            "type": "COMFY_DYNAMICCOMBO_V3",
+            "linkIds": [
+              24
+            ],
+            "label": "output_type",
+            "pos": [
+              542.998046875,
+              174
+            ]
+          },
+          {
+            "id": "1da5009b-4648-43e8-a257-16426630cf22",
+            "name": "output.normalization",
+            "type": "COMBO",
+            "linkIds": [
+              25
+            ],
+            "label": "output_normalization",
+            "pos": [
+              542.998046875,
+              194
+            ]
+          },
+          {
+            "id": "fd7edb33-5fb1-4538-a411-26e5039a9321",
+            "name": "output.apply_sky_clip",
+            "type": "BOOLEAN",
+            "linkIds": [
+              26
+            ],
+            "label": "apply_sky_clip",
+            "pos": [
+              542.998046875,
+              214
+            ]
+          },
+          {
+            "id": "b5be4c8a-b833-4f1e-8c94-3ed1dd722190",
+            "name": "model_name",
+            "type": "COMBO",
+            "linkIds": [
+              106
+            ],
+            "pos": [
+              542.998046875,
+              234
+            ]
+          }
+        ],
+        "outputs": [
+          {
+            "id": "478ab537-63bc-4d74-a9f0-c975f550880f",
+            "name": "IMAGE",
+            "type": "IMAGE",
+            "linkIds": [
+              7
+            ],
+            "localized_name": "IMAGE",
+            "pos": [
+              1274,
+              170
+            ]
+          }
+        ],
+        "widgets": [],
+        "nodes": [
+          {
+            "id": 86,
+            "type": "DA3Render",
+            "pos": [
+              800,
+              310
+            ],
+            "size": [
+              380,
+              130
+            ],
+            "flags": {},
+            "order": 0,
+            "mode": 0,
+            "inputs": [
+              {
+                "localized_name": "da3_geometry",
+                "name": "da3_geometry",
+                "type": "DA3_GEOMETRY",
+                "link": 12
+              },
+              {
+                "localized_name": "output",
+                "name": "output",
+                "type": "COMFY_DYNAMICCOMBO_V3",
+                "widget": {
+                  "name": "output"
+                },
+                "link": 24
+              },
+              {
+                "localized_name": "output.normalization",
+                "name": "output.normalization",
+                "type": "COMBO",
+                "widget": {
+                  "name": "output.normalization"
+                },
+                "link": 25
+              },
+              {
+                "localized_name": "output.apply_sky_clip",
+                "name": "output.apply_sky_clip",
+                "type": "BOOLEAN",
+                "widget": {
+                  "name": "output.apply_sky_clip"
+                },
+                "link": 26
+              },
+              {
+                "name": "geometry",
+                "type": "DA3_GEOMETRY",
+                "link": null
+              }
+            ],
+            "outputs": [
+              {
+                "localized_name": "IMAGE",
+                "name": "IMAGE",
+                "type": "IMAGE",
+                "slot_index": 0,
+                "links": [
+                  7
+                ]
+              }
+            ],
+            "properties": {
+              "Node name for S&R": "DA3Render",
+              "cnr_id": "comfy-core",
+              "ver": "0.19.0"
+            },
+            "widgets_values": [
+              "depth",
+              "v2_style",
+              false
+            ]
+          },
+          {
+            "id": 87,
+            "type": "DA3Inference",
+            "pos": [
+              800,
+              50
+            ],
+            "size": [
+              390,
+              130
+            ],
+            "flags": {},
+            "order": 1,
+            "mode": 0,
+            "inputs": [
+              {
+                "localized_name": "da3_model",
+                "name": "da3_model",
+                "type": "DA3_MODEL",
+                "link": 107
+              },
+              {
+                "localized_name": "image",
+                "name": "image",
+                "type": "IMAGE",
+                "link": 19
+              },
+              {
+                "localized_name": "resolution",
+                "name": "resolution",
+                "type": "INT",
+                "widget": {
+                  "name": "resolution"
+                },
+                "link": 22
+              },
+              {
+                "localized_name": "resize_method",
+                "name": "resize_method",
+                "type": "COMBO",
+                "widget": {
+                  "name": "resize_method"
+                },
+                "link": 23
+              },
+              {
+                "localized_name": "mode",
+                "name": "mode",
+                "type": "COMFY_DYNAMICCOMBO_V3",
+                "widget": {
+                  "name": "mode"
+                },
+                "link": null
+              }
+            ],
+            "outputs": [
+              {
+                "localized_name": "da3_geometry",
+                "name": "da3_geometry",
+                "type": "DA3_GEOMETRY",
+                "slot_index": 0,
+                "links": [
+                  12
+                ]
+              }
+            ],
+            "properties": {
+              "Node name for S&R": "DA3Inference",
+              "cnr_id": "comfy-core",
+              "ver": "0.19.0"
+            },
+            "widgets_values": [
+              504,
+              "upper_bound_resize",
+              "mono"
+            ]
+          },
+          {
+            "id": 88,
+            "type": "LoadDA3Model",
+            "pos": [
+              810,
+              -160
+            ],
+            "size": [
+              400,
+              140
+            ],
+            "flags": {},
+            "order": 2,
+            "mode": 0,
+            "inputs": [
+              {
+                "localized_name": "model_name",
+                "name": "model_name",
+                "type": "COMBO",
+                "widget": {
+                  "name": "model_name"
+                },
+                "link": 106
+              },
+              {
+                "localized_name": "weight_dtype",
+                "name": "weight_dtype",
+                "type": "COMBO",
+                "widget": {
+                  "name": "weight_dtype"
+                },
+                "link": null
+              }
+            ],
+            "outputs": [
+              {
+                "localized_name": "DA3_MODEL",
+                "name": "DA3_MODEL",
+                "type": "DA3_MODEL",
+                "links": [
+                  107
+                ]
+              }
+            ],
+            "properties": {
+              "Node name for S&R": "LoadDA3Model",
+              "cnr_id": "comfy-core",
+              "ver": "0.24.0",
+              "models": [
+                {
+                  "name": "depth_anything_3_mono_large.safetensors",
+                  "url": "https://huggingface.co/Comfy-Org/Depth-Anything-3/resolve/main/geometry_estimation/depth_anything_3_mono_large.safetensors",
+                  "directory": "geometry_estimation"
+                }
+              ]
+            },
+            "widgets_values": [
+              "depth_anything_3_mono_large.safetensors",
+              "default"
+            ]
+          }
+        ],
+        "groups": [],
+        "links": [
+          {
+            "id": 12,
+            "origin_id": 87,
+            "origin_slot": 0,
+            "target_id": 86,
+            "target_slot": 0,
+            "type": "DA3_GEOMETRY"
+          },
+          {
+            "id": 19,
+            "origin_id": -10,
+            "origin_slot": 0,
+            "target_id": 87,
+            "target_slot": 1,
+            "type": "IMAGE"
+          },
+          {
+            "id": 7,
+            "origin_id": 86,
+            "origin_slot": 0,
+            "target_id": -20,
+            "target_slot": 0,
+            "type": "IMAGE"
+          },
+          {
+            "id": 22,
+            "origin_id": -10,
+            "origin_slot": 1,
+            "target_id": 87,
+            "target_slot": 2,
+            "type": "INT"
+          },
+          {
+            "id": 23,
+            "origin_id": -10,
+            "origin_slot": 2,
+            "target_id": 87,
+            "target_slot": 3,
+            "type": "COMBO"
+          },
+          {
+            "id": 24,
+            "origin_id": -10,
+            "origin_slot": 3,
+            "target_id": 86,
+            "target_slot": 1,
+            "type": "COMFY_DYNAMICCOMBO_V3"
+          },
+          {
+            "id": 25,
+            "origin_id": -10,
+            "origin_slot": 4,
+            "target_id": 86,
+            "target_slot": 2,
+            "type": "COMBO"
+          },
+          {
+            "id": 26,
+            "origin_id": -10,
+            "origin_slot": 5,
+            "target_id": 86,
+            "target_slot": 3,
+            "type": "BOOLEAN"
+          },
+          {
+            "id": 106,
+            "origin_id": -10,
+            "origin_slot": 6,
+            "target_id": 88,
+            "target_slot": 0,
+            "type": "COMBO"
+          },
+          {
+            "id": 107,
+            "origin_id": 88,
+            "origin_slot": 0,
+            "target_id": 87,
+            "target_slot": 0,
+            "type": "DA3_MODEL"
+          }
+        ],
+        "extra": {},
+        "category": "Conditioning & Preprocessors/Depth",
+        "description": "This subgraph takes an input image and produces a depth map using the Depth Anything 3 model, which recovers spatially consistent geometry from any number of views. It is ideal for single or multi-view images, videos, and 3D scenes where accurate depth estimation is needed for tasks like SLAM, novel view synthesis, or spatial perception. The model uses a plain transformer backbone and supports both monocular and multi-view inputs without."
+      }
+    ]
+  },
+  "extra": {
+    "BlueprintDescription": "This subgraph takes an input image and produces a depth map using the Depth Anything 3 model, which recovers spatially consistent geometry from any number of views. It is ideal for single or multi-view images, videos, and 3D scenes where accurate depth estimation is needed for tasks like SLAM, novel view synthesis, or spatial perception. The model uses a plain transformer backbone and supports both monocular and multi-view inputs without."
+  }
+}

blueprints/Text to Image (Anima).json

@@ -1077,9 +1077,12 @@
           }
         ],
         "extra": {},
-        "category": "Image generation and editing/Text to image"
+        "category": "Image generation and editing/Text to image",
+        "description": "This subgraph converts text prompts into non-photorealistic illustrations using a 2-billion-parameter model optimized for anime and artistic styles. It is ideal for generating concept art, character designs, or stylized illustrations where photorealism is not required. The model excels with anime and artistic content but performs poorly on realistic subjects."
       }
     ]
   },
-  "extra": {}
+  "extra": {
+    "BlueprintDescription": "This subgraph converts text prompts into non-photorealistic illustrations using a 2-billion-parameter model optimized for anime and artistic styles. It is ideal for generating concept art, character designs, or stylized illustrations where photorealism is not required. The model excels with anime and artistic content but performs poorly on realistic subjects."
+  }
 }

blueprints/Video Depth Estimation (Depth Anything 3).json

@@ -0,0 +1,825 @@
+{
+  "revision": 0,
+  "last_node_id": 97,
+  "last_link_id": 0,
+  "nodes": [
+    {
+      "id": 97,
+      "type": "253ec5ca-8333-4ddf-a036-9fc0923651b9",
+      "pos": [
+        410,
+        500
+      ],
+      "size": [
+        400,
+        400
+      ],
+      "flags": {},
+      "order": 3,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "video",
+          "type": "VIDEO",
+          "link": null
+        },
+        {
+          "name": "start_time",
+          "type": "FLOAT",
+          "widget": {
+            "name": "start_time"
+          },
+          "link": null
+        },
+        {
+          "name": "duration",
+          "type": "FLOAT",
+          "widget": {
+            "name": "duration"
+          },
+          "link": null
+        },
+        {
+          "name": "resolution",
+          "type": "INT",
+          "widget": {
+            "name": "resolution"
+          },
+          "link": null
+        },
+        {
+          "name": "resize_method",
+          "type": "COMBO",
+          "widget": {
+            "name": "resize_method"
+          },
+          "link": null
+        },
+        {
+          "label": "output_type",
+          "name": "output",
+          "type": "COMFY_DYNAMICCOMBO_V3",
+          "widget": {
+            "name": "output"
+          },
+          "link": null
+        },
+        {
+          "label": "normalization",
+          "name": "output.normalization",
+          "type": "COMBO",
+          "widget": {
+            "name": "output.normalization"
+          },
+          "link": null
+        },
+        {
+          "name": "output.apply_sky_clip",
+          "type": "BOOLEAN",
+          "widget": {
+            "name": "output.apply_sky_clip"
+          },
+          "link": null
+        },
+        {
+          "name": "model_name",
+          "type": "COMBO",
+          "widget": {
+            "name": "model_name"
+          },
+          "link": null
+        }
+      ],
+      "outputs": [
+        {
+          "localized_name": "IMAGE",
+          "name": "IMAGE",
+          "type": "IMAGE",
+          "links": []
+        },
+        {
+          "name": "audio",
+          "type": "AUDIO",
+          "links": []
+        },
+        {
+          "name": "fps",
+          "type": "FLOAT",
+          "links": []
+        }
+      ],
+      "properties": {
+        "proxyWidgets": [
+          [
+            "96",
+            "start_time"
+          ],
+          [
+            "96",
+            "duration"
+          ],
+          [
+            "93",
+            "resolution"
+          ],
+          [
+            "93",
+            "resize_method"
+          ],
+          [
+            "92",
+            "output"
+          ],
+          [
+            "92",
+            "output.normalization"
+          ],
+          [
+            "92",
+            "output.apply_sky_clip"
+          ],
+          [
+            "94",
+            "model_name"
+          ]
+        ],
+        "cnr_id": "comfy-core",
+        "ver": "0.24.0"
+      },
+      "widgets_values": [],
+      "title": "Video Depth Estimation (Depth Anything 3)"
+    }
+  ],
+  "links": [],
+  "version": 0.4,
+  "definitions": {
+    "subgraphs": [
+      {
+        "id": "253ec5ca-8333-4ddf-a036-9fc0923651b9",
+        "version": 1,
+        "state": {
+          "lastGroupId": 4,
+          "lastNodeId": 97,
+          "lastLinkId": 129,
+          "lastRerouteId": 0
+        },
+        "revision": 2,
+        "config": {},
+        "name": "Video Depth Estimation (Depth Anything 3)",
+        "inputNode": {
+          "id": -10,
+          "bounding": [
+            -230,
+            130,
+            167.912109375,
+            228
+          ]
+        },
+        "outputNode": {
+          "id": -20,
+          "bounding": [
+            1520,
+            140,
+            128,
+            108
+          ]
+        },
+        "inputs": [
+          {
+            "id": "698c28c6-cf92-4039-8b39-f3062868ea7c",
+            "name": "video",
+            "type": "VIDEO",
+            "linkIds": [
+              119
+            ],
+            "pos": [
+              -86.087890625,
+              154
+            ]
+          },
+          {
+            "id": "97a1f63e-1585-4a40-9dec-e2700120d84a",
+            "name": "start_time",
+            "type": "FLOAT",
+            "linkIds": [
+              121
+            ],
+            "pos": [
+              -86.087890625,
+              174
+            ]
+          },
+          {
+            "id": "4dbbd3b3-c5ee-4a56-a0d3-3268d3b2fd64",
+            "name": "duration",
+            "type": "FLOAT",
+            "linkIds": [
+              122
+            ],
+            "pos": [
+              -86.087890625,
+              194
+            ]
+          },
+          {
+            "id": "16f55101-f99d-4c0c-bebf-c3b31c54f13e",
+            "name": "resolution",
+            "type": "INT",
+            "linkIds": [
+              124
+            ],
+            "pos": [
+              -86.087890625,
+              214
+            ]
+          },
+          {
+            "id": "d9cd7693-4bb3-4ed7-9a75-276b997abcd9",
+            "name": "resize_method",
+            "type": "COMBO",
+            "linkIds": [
+              125
+            ],
+            "pos": [
+              -86.087890625,
+              234
+            ]
+          },
+          {
+            "id": "a6e90532-323b-462e-ba9c-1672384d5b31",
+            "name": "output",
+            "type": "COMFY_DYNAMICCOMBO_V3",
+            "linkIds": [
+              126
+            ],
+            "label": "output_type",
+            "pos": [
+              -86.087890625,
+              254
+            ]
+          },
+          {
+            "id": "69e6aeef-437d-4fde-b2fc-d5ab9369238d",
+            "name": "output.normalization",
+            "type": "COMBO",
+            "linkIds": [
+              127
+            ],
+            "label": "normalization",
+            "pos": [
+              -86.087890625,
+              274
+            ]
+          },
+          {
+            "id": "73206f72-f89a-4698-885e-5d9277df2998",
+            "name": "output.apply_sky_clip",
+            "type": "BOOLEAN",
+            "linkIds": [
+              128
+            ],
+            "pos": [
+              -86.087890625,
+              294
+            ]
+          },
+          {
+            "id": "dddbc7fc-9431-448a-9ed3-9aa62404288b",
+            "name": "model_name",
+            "type": "COMBO",
+            "linkIds": [
+              129
+            ],
+            "pos": [
+              -86.087890625,
+              314
+            ]
+          }
+        ],
+        "outputs": [
+          {
+            "id": "478ab537-63bc-4d74-a9f0-c975f550880f",
+            "name": "IMAGE",
+            "type": "IMAGE",
+            "linkIds": [
+              7
+            ],
+            "localized_name": "IMAGE",
+            "pos": [
+              1544,
+              164
+            ]
+          },
+          {
+            "id": "cdaf037e-79bc-4a94-b06c-0fd32e76f615",
+            "name": "audio",
+            "type": "AUDIO",
+            "linkIds": [
+              112
+            ],
+            "pos": [
+              1544,
+              184
+            ]
+          },
+          {
+            "id": "4c0e5484-d193-49c7-b107-92619628880a",
+            "name": "fps",
+            "type": "FLOAT",
+            "linkIds": [
+              113
+            ],
+            "pos": [
+              1544,
+              204
+            ]
+          }
+        ],
+        "widgets": [],
+        "nodes": [
+          {
+            "id": 92,
+            "type": "DA3Render",
+            "pos": [
+              740,
+              230
+            ],
+            "size": [
+              380,
+              130
+            ],
+            "flags": {},
+            "order": 0,
+            "mode": 0,
+            "inputs": [
+              {
+                "localized_name": "da3_geometry",
+                "name": "da3_geometry",
+                "type": "DA3_GEOMETRY",
+                "link": 12
+              },
+              {
+                "localized_name": "output",
+                "name": "output",
+                "type": "COMFY_DYNAMICCOMBO_V3",
+                "widget": {
+                  "name": "output"
+                },
+                "link": 126
+              },
+              {
+                "localized_name": "output.normalization",
+                "name": "output.normalization",
+                "type": "COMBO",
+                "widget": {
+                  "name": "output.normalization"
+                },
+                "link": 127
+              },
+              {
+                "localized_name": "output.apply_sky_clip",
+                "name": "output.apply_sky_clip",
+                "type": "BOOLEAN",
+                "widget": {
+                  "name": "output.apply_sky_clip"
+                },
+                "link": 128
+              },
+              {
+                "name": "geometry",
+                "type": "DA3_GEOMETRY",
+                "link": null
+              }
+            ],
+            "outputs": [
+              {
+                "localized_name": "IMAGE",
+                "name": "IMAGE",
+                "type": "IMAGE",
+                "slot_index": 0,
+                "links": [
+                  7
+                ]
+              }
+            ],
+            "properties": {
+              "Node name for S&R": "DA3Render",
+              "cnr_id": "comfy-core",
+              "ver": "0.19.0"
+            },
+            "widgets_values": [
+              "depth",
+              "v2_style",
+              false
+            ]
+          },
+          {
+            "id": 93,
+            "type": "DA3Inference",
+            "pos": [
+              740,
+              -30
+            ],
+            "size": [
+              390,
+              130
+            ],
+            "flags": {},
+            "order": 1,
+            "mode": 0,
+            "inputs": [
+              {
+                "localized_name": "da3_model",
+                "name": "da3_model",
+                "type": "DA3_MODEL",
+                "link": 107
+              },
+              {
+                "localized_name": "image",
+                "name": "image",
+                "type": "IMAGE",
+                "link": 111
+              },
+              {
+                "localized_name": "resolution",
+                "name": "resolution",
+                "type": "INT",
+                "widget": {
+                  "name": "resolution"
+                },
+                "link": 124
+              },
+              {
+                "localized_name": "resize_method",
+                "name": "resize_method",
+                "type": "COMBO",
+                "widget": {
+                  "name": "resize_method"
+                },
+                "link": 125
+              },
+              {
+                "localized_name": "mode",
+                "name": "mode",
+                "type": "COMFY_DYNAMICCOMBO_V3",
+                "widget": {
+                  "name": "mode"
+                },
+                "link": null
+              }
+            ],
+            "outputs": [
+              {
+                "localized_name": "da3_geometry",
+                "name": "da3_geometry",
+                "type": "DA3_GEOMETRY",
+                "slot_index": 0,
+                "links": [
+                  12
+                ]
+              }
+            ],
+            "properties": {
+              "Node name for S&R": "DA3Inference",
+              "cnr_id": "comfy-core",
+              "ver": "0.19.0"
+            },
+            "widgets_values": [
+              504,
+              "lower_bound_resize",
+              "mono"
+            ]
+          },
+          {
+            "id": 94,
+            "type": "LoadDA3Model",
+            "pos": [
+              50,
+              410
+            ],
+            "size": [
+              400,
+              140
+            ],
+            "flags": {},
+            "order": 2,
+            "mode": 0,
+            "inputs": [
+              {
+                "localized_name": "model_name",
+                "name": "model_name",
+                "type": "COMBO",
+                "widget": {
+                  "name": "model_name"
+                },
+                "link": 129
+              },
+              {
+                "localized_name": "weight_dtype",
+                "name": "weight_dtype",
+                "type": "COMBO",
+                "widget": {
+                  "name": "weight_dtype"
+                },
+                "link": null
+              }
+            ],
+            "outputs": [
+              {
+                "localized_name": "DA3_MODEL",
+                "name": "DA3_MODEL",
+                "type": "DA3_MODEL",
+                "links": [
+                  107
+                ]
+              }
+            ],
+            "properties": {
+              "Node name for S&R": "LoadDA3Model",
+              "cnr_id": "comfy-core",
+              "ver": "0.24.0",
+              "models": [
+                {
+                  "name": "depth_anything_3_mono_large.safetensors",
+                  "url": "https://huggingface.co/Comfy-Org/Depth-Anything-3/resolve/main/geometry_estimation/depth_anything_3_mono_large.safetensors",
+                  "directory": "geometry_estimation"
+                }
+              ]
+            },
+            "widgets_values": [
+              "depth_anything_3_mono_large.safetensors",
+              "default"
+            ]
+          },
+          {
+            "id": 95,
+            "type": "GetVideoComponents",
+            "pos": [
+              70,
+              -140
+            ],
+            "size": [
+              260,
+              120
+            ],
+            "flags": {},
+            "order": 3,
+            "mode": 0,
+            "inputs": [
+              {
+                "localized_name": "video",
+                "name": "video",
+                "type": "VIDEO",
+                "link": 120
+              }
+            ],
+            "outputs": [
+              {
+                "localized_name": "images",
+                "name": "images",
+                "type": "IMAGE",
+                "links": [
+                  111
+                ]
+              },
+              {
+                "localized_name": "audio",
+                "name": "audio",
+                "type": "AUDIO",
+                "links": [
+                  112
+                ]
+              },
+              {
+                "localized_name": "fps",
+                "name": "fps",
+                "type": "FLOAT",
+                "links": [
+                  113
+                ]
+              },
+              {
+                "localized_name": "bit_depth",
+                "name": "bit_depth",
+                "type": "INT",
+                "links": null
+              }
+            ],
+            "properties": {
+              "Node name for S&R": "GetVideoComponents",
+              "cnr_id": "comfy-core",
+              "ver": "0.24.0"
+            }
+          },
+          {
+            "id": 96,
+            "type": "Video Slice",
+            "pos": [
+              70,
+              -360
+            ],
+            "size": [
+              270,
+              170
+            ],
+            "flags": {},
+            "order": 4,
+            "mode": 0,
+            "inputs": [
+              {
+                "localized_name": "video",
+                "name": "video",
+                "type": "VIDEO",
+                "link": 119
+              },
+              {
+                "localized_name": "start_time",
+                "name": "start_time",
+                "type": "FLOAT",
+                "widget": {
+                  "name": "start_time"
+                },
+                "link": 121
+              },
+              {
+                "localized_name": "duration",
+                "name": "duration",
+                "type": "FLOAT",
+                "widget": {
+                  "name": "duration"
+                },
+                "link": 122
+              },
+              {
+                "localized_name": "strict_duration",
+                "name": "strict_duration",
+                "type": "BOOLEAN",
+                "widget": {
+                  "name": "strict_duration"
+                },
+                "link": null
+              }
+            ],
+            "outputs": [
+              {
+                "localized_name": "VIDEO",
+                "name": "VIDEO",
+                "type": "VIDEO",
+                "links": [
+                  120
+                ]
+              }
+            ],
+            "properties": {
+              "Node name for S&R": "Video Slice",
+              "cnr_id": "comfy-core",
+              "ver": "0.24.0"
+            },
+            "widgets_values": [
+              0,
+              5,
+              false
+            ]
+          }
+        ],
+        "groups": [],
+        "links": [
+          {
+            "id": 12,
+            "origin_id": 93,
+            "origin_slot": 0,
+            "target_id": 92,
+            "target_slot": 0,
+            "type": "DA3_GEOMETRY"
+          },
+          {
+            "id": 7,
+            "origin_id": 92,
+            "origin_slot": 0,
+            "target_id": -20,
+            "target_slot": 0,
+            "type": "IMAGE"
+          },
+          {
+            "id": 107,
+            "origin_id": 94,
+            "origin_slot": 0,
+            "target_id": 93,
+            "target_slot": 0,
+            "type": "DA3_MODEL"
+          },
+          {
+            "id": 111,
+            "origin_id": 95,
+            "origin_slot": 0,
+            "target_id": 93,
+            "target_slot": 1,
+            "type": "IMAGE"
+          },
+          {
+            "id": 112,
+            "origin_id": 95,
+            "origin_slot": 1,
+            "target_id": -20,
+            "target_slot": 1,
+            "type": "AUDIO"
+          },
+          {
+            "id": 113,
+            "origin_id": 95,
+            "origin_slot": 2,
+            "target_id": -20,
+            "target_slot": 2,
+            "type": "FLOAT"
+          },
+          {
+            "id": 119,
+            "origin_id": -10,
+            "origin_slot": 0,
+            "target_id": 96,
+            "target_slot": 0,
+            "type": "VIDEO"
+          },
+          {
+            "id": 120,
+            "origin_id": 96,
+            "origin_slot": 0,
+            "target_id": 95,
+            "target_slot": 0,
+            "type": "VIDEO"
+          },
+          {
+            "id": 121,
+            "origin_id": -10,
+            "origin_slot": 1,
+            "target_id": 96,
+            "target_slot": 1,
+            "type": "FLOAT"
+          },
+          {
+            "id": 122,
+            "origin_id": -10,
+            "origin_slot": 2,
+            "target_id": 96,
+            "target_slot": 2,
+            "type": "FLOAT"
+          },
+          {
+            "id": 124,
+            "origin_id": -10,
+            "origin_slot": 3,
+            "target_id": 93,
+            "target_slot": 2,
+            "type": "INT"
+          },
+          {
+            "id": 125,
+            "origin_id": -10,
+            "origin_slot": 4,
+            "target_id": 93,
+            "target_slot": 3,
+            "type": "COMBO"
+          },
+          {
+            "id": 126,
+            "origin_id": -10,
+            "origin_slot": 5,
+            "target_id": 92,
+            "target_slot": 1,
+            "type": "COMFY_DYNAMICCOMBO_V3"
+          },
+          {
+            "id": 127,
+            "origin_id": -10,
+            "origin_slot": 6,
+            "target_id": 92,
+            "target_slot": 2,
+            "type": "COMBO"
+          },
+          {
+            "id": 128,
+            "origin_id": -10,
+            "origin_slot": 7,
+            "target_id": 92,
+            "target_slot": 3,
+            "type": "BOOLEAN"
+          },
+          {
+            "id": 129,
+            "origin_id": -10,
+            "origin_slot": 8,
+            "target_id": 94,
+            "target_slot": 0,
+            "type": "COMBO"
+          }
+        ],
+        "extra": {},
+        "category": "Conditioning & Preprocessors/Depth",
+        "description": "This subgraph processes a video input through Depth Anything 3 to produce temporally consistent depth maps for each frame, outputting a depth video. It is ideal for video content requiring spatial geometry estimation, such as 3D reconstruction, SLAM, or novel view synthesis from moving cameras. The model uses a plain transformer backbone trained with a depth-ray representation, supporting any number of views without requiring known camera poses."
+      }
+    ]
+  },
+  "extra": {
+    "BlueprintDescription": "This subgraph processes a video input through Depth Anything 3 to produce temporally consistent depth maps for each frame, outputting a depth video. It is ideal for video content requiring spatial geometry estimation, such as 3D reconstruction, SLAM, or novel view synthesis from moving cameras. The model uses a plain transformer backbone trained with a depth-ray representation, supporting any number of views without requiring known camera poses."
+  }
+}

comfy/cli_args.py

@@ -115,6 +115,7 @@ cache_group.add_argument("--cache-ram", nargs='*', type=float, default=[], metav
 cache_group.add_argument("--cache-classic", action="store_true", help="Use the old style (aggressive) caching.")
 cache_group.add_argument("--cache-lru", type=int, default=0, help="Use LRU caching with a maximum of N node results cached. May use more RAM/VRAM.")
 cache_group.add_argument("--cache-none", action="store_true", help="Reduced RAM/VRAM usage at the expense of executing every node for each run.")
+cache_group.add_argument("--high-ram", action="store_true", help="Can improve performance slightly on high RAM or on systems where pagefile use is preferred over model loading.")
 
 attn_group = parser.add_mutually_exclusive_group()
 attn_group.add_argument("--use-split-cross-attention", action="store_true", help="Use the split cross attention optimization. Ignored when xformers is used.")
@@ -133,7 +134,7 @@ upcast.add_argument("--dont-upcast-attention", action="store_true", help="Disabl
 parser.add_argument("--enable-manager", action="store_true", help="Enable the ComfyUI-Manager feature.")
 manager_group = parser.add_mutually_exclusive_group()
 manager_group.add_argument("--disable-manager-ui", action="store_true", help="Disables only the ComfyUI-Manager UI and endpoints. Scheduled installations and similar background tasks will still operate.")
-manager_group.add_argument("--enable-manager-legacy-ui", action="store_true", help="Enables the legacy UI of ComfyUI-Manager")
+manager_group.add_argument("--enable-manager-legacy-ui", action="store_true", help="Enables the legacy UI of ComfyUI-Manager. Implies --enable-manager.")
 
 
 vram_group = parser.add_mutually_exclusive_group()
@@ -144,6 +145,7 @@ vram_group.add_argument("--novram", action="store_true", help="When lowvram isn'
 vram_group.add_argument("--cpu", action="store_true", help="To use the CPU for everything (slow).")
 
 parser.add_argument("--reserve-vram", type=float, default=None, help="Set the amount of vram in GB you want to reserve for use by your OS/other software. By default some amount is reserved depending on your OS.")
+parser.add_argument("--vram-headroom", type=float, default=0, help="Set the amount of vram in GB for DynamicVRAM to maintain as extra headroom above default. ComfyUI will try and keep this much VRAM completely free and unused, even counting VRAM from other apps.")
 
 parser.add_argument("--async-offload", nargs='?', const=2, type=int, default=None, metavar="NUM_STREAMS", help="Use async weight offloading. An optional argument controls the amount of offload streams. Default is 2. Enabled by default on Nvidia.")
 parser.add_argument("--disable-async-offload", action="store_true", help="Disable async weight offloading.")
@@ -166,6 +168,8 @@ class PerformanceFeature(enum.Enum):
 
 parser.add_argument("--fast", nargs="*", type=PerformanceFeature, help="Enable some untested and potentially quality deteriorating optimizations. This is used to test new features so using it might crash your comfyui. --fast with no arguments enables everything. You can pass a list specific optimizations if you only want to enable specific ones. Current valid optimizations: {}".format(" ".join(map(lambda c: c.value, PerformanceFeature))))
 
+parser.add_argument("--debug-hang", action="store_true", help="Enable stack trace dumps on Ctrl-C for debugging hangs.")
+
 parser.add_argument("--disable-pinned-memory", action="store_true", help="Disable pinned memory use.")
 
 parser.add_argument("--mmap-torch-files", action="store_true", help="Use mmap when loading ckpt/pt files.")
@@ -236,6 +240,7 @@ database_default_path = os.path.abspath(
 )
 parser.add_argument("--database-url", type=str, default=f"sqlite:///{database_default_path}", help="Specify the database URL, e.g. for an in-memory database you can use 'sqlite:///:memory:'.")
 parser.add_argument("--enable-assets", action="store_true", help="Enable the assets system (API routes, database synchronization, and background scanning).")
+parser.add_argument("--enable-asset-hashing", action="store_true", help="Compute blake3 content hashes when scanning assets. Hashing enables future asset-portability features (deduplication, cross-machine model resolution) but adds startup cost and per-output cost on large models directories. Off by default; enable to opt in.")
 parser.add_argument("--feature-flag", type=str, action='append', default=[], metavar="KEY[=VALUE]", help="Set a server feature flag. Use KEY=VALUE to set an explicit value, or bare KEY to set it to true. Can be specified multiple times. Boolean values (true/false) and numbers are auto-converted. Examples: --feature-flag show_signin_button=true  or  --feature-flag show_signin_button")
 parser.add_argument("--list-feature-flags", action="store_true", help="Print the registry of known CLI-settable feature flags as JSON and exit.")
 
@@ -247,6 +252,9 @@ else:
 if args.cache_ram is not None and len(args.cache_ram) > 2:
     parser.error("--cache-ram accepts at most two values: active GB and inactive GB")
 
+if args.high_ram:
+    args.cache_classic = True
+
 if args.windows_standalone_build:
     args.auto_launch = True
 
@@ -256,6 +264,10 @@ if args.disable_auto_launch:
 if args.force_fp16:
     args.fp16_unet = True
 
+# '--enable-manager-legacy-ui' is meaningless unless the manager is enabled, so imply '--enable-manager'.
+if args.enable_manager_legacy_ui:
+    args.enable_manager = True
+
 
 # '--fast' is not provided, use an empty set
 if args.fast is None:

comfy/context_windows.py

@@ -8,6 +8,8 @@ from abc import ABC, abstractmethod
 import logging
 import comfy.model_management
 import comfy.patcher_extension
+import comfy.utils
+import comfy.conds
 if TYPE_CHECKING:
     from comfy.model_base import BaseModel
     from comfy.model_patcher import ModelPatcher
@@ -51,12 +53,18 @@ class ContextHandlerABC(ABC):
 
 
 class IndexListContextWindow(ContextWindowABC):
-    def __init__(self, index_list: list[int], dim: int=0, total_frames: int=0):
+    def __init__(self, index_list: list[int], dim: int=0, total_frames: int=0, modality_windows: dict=None, context_overlap: int=0):
         self.index_list = index_list
         self.context_length = len(index_list)
+        self.context_overlap = context_overlap
         self.dim = dim
         self.total_frames = total_frames
         self.center_ratio = (min(index_list) + max(index_list)) / (2 * total_frames)
+        self.modality_windows = modality_windows  # dict of {mod_idx: IndexListContextWindow}
+        self.guide_frames_indices: list[int] = []
+        self.guide_overlap_info: list[tuple[int, int]] = []
+        self.guide_kf_local_positions: list[int] = []
+        self.guide_downscale_factors: list[int] = []
 
     def get_tensor(self, full: torch.Tensor, device=None, dim=None, retain_index_list=[]) -> torch.Tensor:
         if dim is None:
@@ -85,6 +93,11 @@ class IndexListContextWindow(ContextWindowABC):
         region_idx = int(self.center_ratio * num_regions)
         return min(max(region_idx, 0), num_regions - 1)
 
+    def get_window_for_modality(self, modality_idx: int) -> 'IndexListContextWindow':
+        if modality_idx == 0:
+            return self
+        return self.modality_windows[modality_idx]
+
 
 class IndexListCallbacks:
     EVALUATE_CONTEXT_WINDOWS = "evaluate_context_windows"
@@ -148,6 +161,172 @@ def slice_cond(cond_value, window: IndexListContextWindow, x_in: torch.Tensor, d
     return cond_value._copy_with(sliced)
 
 
+def compute_guide_overlap(guide_entries: list[dict], keyframe_idxs: torch.Tensor, temporal_downscale_ratio: int, window_index_list: list[int]):
+    """Compute which concatenated guide frames overlap with a context window.
+
+    Each guide's latent-space start is derived from its first token's pixel-t-start
+    in keyframe_idxs (shape (B, [t,h,w], num_tokens, [start, end])), divided by the
+    model's temporal_downscale_ratio.
+
+    Args:
+        guide_entries: list of guide_attention_entry dicts
+        keyframe_idxs: per-token pixel coords cond tensor for the modality
+        temporal_downscale_ratio: model's pixel-to-latent temporal compression ratio
+        window_index_list: the window's frame indices into the video portion
+
+    Returns:
+        suffix_indices: indices into the guide_frames tensor for frame selection
+        overlap_info: list of (entry_idx, overlap_count) for guide_attention_entries adjustment
+        kf_local_positions: window-local frame positions for keyframe_idxs regeneration
+        total_overlap: total number of overlapping guide frames
+    """
+    window_set = set(window_index_list)
+    window_list = list(window_index_list)
+    suffix_indices = []
+    overlap_info = []
+    kf_local_positions = []
+    suffix_base = 0
+    token_offset = 0
+
+    for entry_idx, entry in enumerate(guide_entries):
+        first_t_pixel = int(keyframe_idxs[0, 0, token_offset, 0].item())
+        latent_start = (first_t_pixel + temporal_downscale_ratio - 1) // temporal_downscale_ratio
+        guide_len = entry["latent_shape"][0]
+        entry_overlap = 0
+
+        for local_offset in range(guide_len):
+            video_pos = latent_start + local_offset
+            if video_pos in window_set:
+                suffix_indices.append(suffix_base + local_offset)
+                kf_local_positions.append(window_list.index(video_pos))
+                entry_overlap += 1
+
+        if entry_overlap > 0:
+            overlap_info.append((entry_idx, entry_overlap))
+        suffix_base += guide_len
+        token_offset += entry["pre_filter_count"]
+
+    return suffix_indices, overlap_info, kf_local_positions, len(suffix_indices)
+
+
+@dataclass
+class WindowingState:
+    """Per-modality context windowing state for each step,
+    built using IndexListContextHandler._build_window_state().
+    For non-multimodal models the lists are length 1
+    """
+    latents: list[torch.Tensor]                  # per-modality working latents (guide frames stripped)
+    guide_latents: list[torch.Tensor | None]     # per-modality guide frames stripped from latents
+    guide_entries: list[list[dict] | None]       # per-modality guide_attention_entry metadata
+    keyframe_idxs: list[torch.Tensor | None]     # per-modality keyframe_idxs tensor for guide latent_start derivation
+    latent_shapes: list | None                   # original packed shapes for unpack/pack (None if not multimodal)
+    dim: int = 0                                 # primary modality temporal dim for context windowing
+    is_multimodal: bool = False
+    temporal_downscale_ratio: int = 1            # model's pixel-to-latent temporal compression ratio
+
+    def prepare_window(self, window: IndexListContextWindow, model) -> IndexListContextWindow:
+        """Reformat window for multimodal contexts by deriving per-modality index lists.
+        Non-multimodal contexts return the input window unchanged.
+        """
+        if not self.is_multimodal:
+            return window
+
+        x = self.latents[0]
+        primary_total = self.latent_shapes[0][self.dim]
+        primary_overlap = window.context_overlap
+        map_shapes = self.latent_shapes
+        if x.size(self.dim) != primary_total:
+            map_shapes = list(self.latent_shapes)
+            video_shape = list(self.latent_shapes[0])
+            video_shape[self.dim] = x.size(self.dim)
+            map_shapes[0] = torch.Size(video_shape)
+        try:
+            per_modality_indices = model.map_context_window_to_modalities(
+                window.index_list, map_shapes, self.dim)
+        except AttributeError:
+            raise NotImplementedError(
+                f"{type(model).__name__} must implement map_context_window_to_modalities for multimodal context windows.")
+        modality_windows = {}
+        for mod_idx in range(1, len(self.latents)):
+            modality_total_frames = self.latents[mod_idx].shape[self.dim]
+            ratio = modality_total_frames / primary_total if primary_total > 0 else 1
+            modality_overlap = max(round(primary_overlap * ratio), 0)
+            modality_windows[mod_idx] = IndexListContextWindow(
+                per_modality_indices[mod_idx], dim=self.dim,
+                total_frames=modality_total_frames,
+                context_overlap=modality_overlap)
+        return IndexListContextWindow(
+            window.index_list, dim=self.dim, total_frames=x.shape[self.dim],
+            modality_windows=modality_windows, context_overlap=primary_overlap)
+
+    def slice_for_window(self, window: IndexListContextWindow, retain_index_list: list[int], device=None) -> tuple[list[torch.Tensor], list[int]]:
+        """Slice latents for a context window, injecting guide frames where applicable.
+        For multimodal contexts, uses the modality-specific windows derived in prepare_window().
+        """
+        sliced = []
+        guide_frame_counts = []
+        for idx in range(len(self.latents)):
+            modality_window = window.get_window_for_modality(idx)
+            retain = retain_index_list if idx == 0 else []
+            s = modality_window.get_tensor(self.latents[idx], device, retain_index_list=retain)
+            if self.guide_entries[idx] is not None:
+                s, ng = self._inject_guide_frames(s, modality_window, modality_idx=idx)
+            else:
+                ng = 0
+            sliced.append(s)
+            guide_frame_counts.append(ng)
+        return sliced, guide_frame_counts
+
+    def strip_guide_frames(self, out_per_modality: list[list[torch.Tensor]], guide_frame_counts: list[int], window: IndexListContextWindow):
+        """Strip injected guide frames from per-cond, per-modality outputs in place."""
+        for idx in range(len(self.latents)):
+            if guide_frame_counts[idx] > 0:
+                window_len = len(window.get_window_for_modality(idx).index_list)
+                for ci in range(len(out_per_modality)):
+                    out_per_modality[ci][idx] = out_per_modality[ci][idx].narrow(self.dim, 0, window_len)
+
+    def _inject_guide_frames(self, latent_slice: torch.Tensor, window: IndexListContextWindow, modality_idx: int = 0) -> tuple[torch.Tensor, int]:
+        guide_entries = self.guide_entries[modality_idx]
+        guide_frames = self.guide_latents[modality_idx]
+        keyframe_idxs = self.keyframe_idxs[modality_idx]
+        suffix_idx, overlap_info, kf_local_pos, guide_frame_count = compute_guide_overlap(
+            guide_entries, keyframe_idxs, self.temporal_downscale_ratio, window.index_list)
+        # Shift keyframe positions to account for causal_window_fix anchor occupying sub-pos 0.
+        anchor_idx = getattr(window, 'causal_anchor_index', None)
+        if anchor_idx is not None and anchor_idx >= 0:
+            kf_local_pos = [p + 1 for p in kf_local_pos]
+        window.guide_frames_indices = suffix_idx
+        window.guide_overlap_info = overlap_info
+        window.guide_kf_local_positions = kf_local_pos
+
+        # Derive per-overlap-entry latent_downscale_factor from guide entry latent_shape vs guide frame spatial dims.
+        # guide_frames has full (post-dilation) spatial dims; entry["latent_shape"] has pre-dilation dims.
+        guide_downscale_factors = []
+        if guide_frame_count > 0:
+            full_H = guide_frames.shape[3]
+            for entry_idx, _ in overlap_info:
+                entry_H = guide_entries[entry_idx]["latent_shape"][1]
+                guide_downscale_factors.append(full_H // entry_H)
+        window.guide_downscale_factors = guide_downscale_factors
+
+        if guide_frame_count > 0:
+            idx = tuple([slice(None)] * self.dim + [suffix_idx])
+            return torch.cat([latent_slice, guide_frames[idx]], dim=self.dim), guide_frame_count
+        return latent_slice, 0
+
+    def patch_latent_shapes(self, sub_conds, new_shapes):
+        if not self.is_multimodal:
+            return
+
+        for cond_list in sub_conds:
+            if cond_list is None:
+                continue
+            for cond_dict in cond_list:
+                model_conds = cond_dict.get('model_conds', {})
+                if 'latent_shapes' in model_conds:
+                    model_conds['latent_shapes'] = comfy.conds.CONDConstant(new_shapes)
+
+
 @dataclass
 class ContextSchedule:
     name: str
@@ -162,7 +341,7 @@ ContextResults = collections.namedtuple("ContextResults", ['window_idx', 'sub_co
 class IndexListContextHandler(ContextHandlerABC):
     def __init__(self, context_schedule: ContextSchedule, fuse_method: ContextFuseMethod, context_length: int=1, context_overlap: int=0, context_stride: int=1,
                  closed_loop: bool=False, dim:int=0, freenoise: bool=False, cond_retain_index_list: list[int]=[], split_conds_to_windows: bool=False,
-                 causal_window_fix: bool=True):
+                 latent_retain_index_list: list[int]=[], causal_window_fix: bool=True):
         self.context_schedule = context_schedule
         self.fuse_method = fuse_method
         self.context_length = context_length
@@ -174,17 +353,118 @@ class IndexListContextHandler(ContextHandlerABC):
         self.freenoise = freenoise
         self.cond_retain_index_list = [int(x.strip()) for x in cond_retain_index_list.split(",")] if cond_retain_index_list else []
         self.split_conds_to_windows = split_conds_to_windows
+        self.latent_retain_index_list = [int(x.strip()) for x in latent_retain_index_list.split(",")] if latent_retain_index_list else []
         self.causal_window_fix = causal_window_fix
 
         self.callbacks = {}
 
+    @staticmethod
+    def _get_latent_shapes(conds):
+        for cond_list in conds:
+            if cond_list is None:
+                continue
+            for cond_dict in cond_list:
+                model_conds = cond_dict.get('model_conds', {})
+                if 'latent_shapes' in model_conds:
+                    return model_conds['latent_shapes'].cond
+        return None
+
+    @staticmethod
+    def _get_guide_entries(conds):
+        for cond_list in conds:
+            if cond_list is None:
+                continue
+            for cond_dict in cond_list:
+                model_conds = cond_dict.get('model_conds', {})
+                entries = model_conds.get('guide_attention_entries')
+                if entries is not None and hasattr(entries, 'cond') and entries.cond:
+                    return entries.cond
+        return None
+
+    @staticmethod
+    def _get_keyframe_idxs(conds):
+        for cond_list in conds:
+            if cond_list is None:
+                continue
+            for cond_dict in cond_list:
+                model_conds = cond_dict.get('model_conds', {})
+                kf = model_conds.get('keyframe_idxs')
+                if kf is not None and hasattr(kf, 'cond') and kf.cond is not None:
+                    return kf.cond
+        return None
+
+    def _apply_freenoise(self, noise: torch.Tensor, conds: list[list[dict]], seed: int) -> torch.Tensor:
+        """Apply FreeNoise shuffling, scaling context length/overlap per-modality by frame ratio.
+        If guide frames are present on the primary modality, only the video portion is shuffled.
+        """
+        guide_entries = self._get_guide_entries(conds)
+        guide_count = sum(e["latent_shape"][0] for e in guide_entries) if guide_entries else 0
+
+        latent_shapes = self._get_latent_shapes(conds)
+        if latent_shapes is not None and len(latent_shapes) > 1:
+            modalities = comfy.utils.unpack_latents(noise, latent_shapes)
+            primary_total = latent_shapes[0][self.dim]
+            primary_video_count = modalities[0].size(self.dim) - guide_count
+            apply_freenoise(modalities[0].narrow(self.dim, 0, primary_video_count), self.dim, self.context_length, self.context_overlap, seed)
+            for i in range(1, len(modalities)):
+                mod_total = latent_shapes[i][self.dim]
+                ratio = mod_total / primary_total if primary_total > 0 else 1
+                mod_ctx_len = max(round(self.context_length * ratio), 1)
+                mod_ctx_overlap = max(round(self.context_overlap * ratio), 0)
+                modalities[i] = apply_freenoise(modalities[i], self.dim, mod_ctx_len, mod_ctx_overlap, seed)
+            noise, _ = comfy.utils.pack_latents(modalities)
+            return noise
+        video_count = noise.size(self.dim) - guide_count
+        apply_freenoise(noise.narrow(self.dim, 0, video_count), self.dim, self.context_length, self.context_overlap, seed)
+        return noise
+
+    def _build_window_state(self, x_in: torch.Tensor, conds: list[list[dict]], model: BaseModel) -> WindowingState:
+        """Build windowing state for the current step, including unpacking latents and extracting guide frame info from conds."""
+        latent_shapes = self._get_latent_shapes(conds)
+        is_multimodal = latent_shapes is not None and len(latent_shapes) > 1
+        unpacked_latents = comfy.utils.unpack_latents(x_in, latent_shapes) if is_multimodal else [x_in]
+
+        unpacked_latents_list = list(unpacked_latents)
+        guide_latents_list = [None] * len(unpacked_latents)
+        guide_entries_list = [None] * len(unpacked_latents)
+        keyframe_idxs_list = [None] * len(unpacked_latents)
+
+        extracted_guide_entries = self._get_guide_entries(conds)
+        extracted_keyframe_idxs = self._get_keyframe_idxs(conds)
+
+        # Strip guide frames (only from first modality for now)
+        if extracted_guide_entries is not None:
+            guide_count = sum(e["latent_shape"][0] for e in extracted_guide_entries)
+            if guide_count > 0:
+                x = unpacked_latents[0]
+                latent_count = x.size(self.dim) - guide_count
+                unpacked_latents_list[0] = x.narrow(self.dim, 0, latent_count)
+                guide_latents_list[0] = x.narrow(self.dim, latent_count, guide_count)
+                guide_entries_list[0] = extracted_guide_entries
+                keyframe_idxs_list[0] = extracted_keyframe_idxs
+
+
+        return WindowingState(
+            latents=unpacked_latents_list,
+            guide_latents=guide_latents_list,
+            guide_entries=guide_entries_list,
+            keyframe_idxs=keyframe_idxs_list,
+            latent_shapes=latent_shapes,
+            dim=self.dim,
+            is_multimodal=is_multimodal,
+            temporal_downscale_ratio=model.latent_format.temporal_downscale_ratio)
+
     def should_use_context(self, model: BaseModel, conds: list[list[dict]], x_in: torch.Tensor, timestep: torch.Tensor, model_options: dict[str]) -> bool:
-        # for now, assume first dim is batch - should have stored on BaseModel in actual implementation
-        if x_in.size(self.dim) > self.context_length:
-            logging.info(f"Using context windows {self.context_length} with overlap {self.context_overlap} for {x_in.size(self.dim)} frames.")
+        window_state = self._build_window_state(x_in, conds, model) # build window_state to check frame counts, will be built again in execute
+        total_frame_count = window_state.latents[0].size(self.dim)
+        if total_frame_count > self.context_length:
+            logging.info(f"\nUsing context windows: Context length {self.context_length} with overlap {self.context_overlap} for {total_frame_count} frames.")
             if self.cond_retain_index_list:
                 logging.info(f"Retaining original cond for indexes: {self.cond_retain_index_list}")
+            if self.latent_retain_index_list:
+                logging.info(f"Retaining original latent for indexes: {self.latent_retain_index_list}")
             return True
+        logging.info(f"\nNot using context windows since context length ({self.context_length}) exceeds input frames ({total_frame_count}).")
         return False
 
     def prepare_control_objects(self, control: ControlBase, device=None) -> ControlBase:
@@ -275,7 +555,9 @@ class IndexListContextHandler(ContextHandlerABC):
         return resized_cond
 
     def set_step(self, timestep: torch.Tensor, model_options: dict[str]):
-        mask = torch.isclose(model_options["transformer_options"]["sample_sigmas"], timestep[0], rtol=0.0001)
+        sample_sigmas = model_options["transformer_options"]["sample_sigmas"]
+        current_timestep = timestep[0].to(sample_sigmas.dtype)
+        mask = torch.isclose(sample_sigmas, current_timestep, rtol=0.0001)
         matches = torch.nonzero(mask)
         if torch.numel(matches) == 0:
             return  # substep from multi-step sampler: keep self._step from the last full step
@@ -284,54 +566,98 @@ class IndexListContextHandler(ContextHandlerABC):
     def get_context_windows(self, model: BaseModel, x_in: torch.Tensor, model_options: dict[str]) -> list[IndexListContextWindow]:
         full_length = x_in.size(self.dim) # TODO: choose dim based on model
         context_windows = self.context_schedule.func(full_length, self, model_options)
-        context_windows = [IndexListContextWindow(window, dim=self.dim, total_frames=full_length) for window in context_windows]
+        context_windows = [IndexListContextWindow(window, dim=self.dim, total_frames=full_length, context_overlap=self.context_overlap) for window in context_windows]
         return context_windows
 
     def execute(self, calc_cond_batch: Callable, model: BaseModel, conds: list[list[dict]], x_in: torch.Tensor, timestep: torch.Tensor, model_options: dict[str]):
         self._model = model
         self.set_step(timestep, model_options)
-        context_windows = self.get_context_windows(model, x_in, model_options)
-        enumerated_context_windows = list(enumerate(context_windows))
 
-        conds_final = [torch.zeros_like(x_in) for _ in conds]
+        window_state = self._build_window_state(x_in, conds, model)
+        num_modalities = len(window_state.latents)
+
+        context_windows = self.get_context_windows(model, window_state.latents[0], model_options)
+        enumerated_context_windows = list(enumerate(context_windows))
+        total_windows = len(enumerated_context_windows)
+
+        # Initialize per-modality accumulators (length 1 for single-modality)
+        accum = [[torch.zeros_like(m) for _ in conds] for m in window_state.latents]
         if self.fuse_method.name == ContextFuseMethods.RELATIVE:
-            counts_final = [torch.ones(get_shape_for_dim(x_in, self.dim), device=x_in.device) for _ in conds]
+            counts = [[torch.ones(get_shape_for_dim(m, self.dim), device=m.device) for _ in conds] for m in window_state.latents]
         else:
-            counts_final = [torch.zeros(get_shape_for_dim(x_in, self.dim), device=x_in.device) for _ in conds]
-        biases_final = [([0.0] * x_in.shape[self.dim]) for _ in conds]
+            counts = [[torch.zeros(get_shape_for_dim(m, self.dim), device=m.device) for _ in conds] for m in window_state.latents]
+        biases = [[([0.0] * m.shape[self.dim]) for _ in conds] for m in window_state.latents]
 
         for callback in comfy.patcher_extension.get_all_callbacks(IndexListCallbacks.EXECUTE_START, self.callbacks):
             callback(self, model, x_in, conds, timestep, model_options)
 
+        # accumulate results from each context window
         for enum_window in enumerated_context_windows:
-            results = self.evaluate_context_windows(calc_cond_batch, model, x_in, conds, timestep, [enum_window], model_options)
+            results = self.evaluate_context_windows(
+                calc_cond_batch, model, x_in, conds, timestep, [enum_window],
+                model_options, window_state=window_state, total_windows=total_windows)
             for result in results:
-                self.combine_context_window_results(x_in, result.sub_conds_out, result.sub_conds, result.window, result.window_idx, len(enumerated_context_windows), timestep,
-                                            conds_final, counts_final, biases_final)
+                # result.sub_conds_out is per-cond, per-modality: list[list[Tensor]]
+                for mod_idx in range(num_modalities):
+                    mod_out = [result.sub_conds_out[ci][mod_idx] for ci in range(len(conds))]
+                    modality_window = result.window.get_window_for_modality(mod_idx)
+                    self.combine_context_window_results(
+                        window_state.latents[mod_idx], mod_out, result.sub_conds, modality_window,
+                        result.window_idx, total_windows, timestep,
+                        accum[mod_idx], counts[mod_idx], biases[mod_idx])
+
+        # fuse accumulated results into final conds
         try:
-            # finalize conds
-            if self.fuse_method.name == ContextFuseMethods.RELATIVE:
-                # relative is already normalized, so return as is
-                del counts_final
-                return conds_final
-            else:
-                # normalize conds via division by context usage counts
-                for i in range(len(conds_final)):
-                    conds_final[i] /= counts_final[i]
-                del counts_final
-                return conds_final
+            result_out = []
+            for ci in range(len(conds)):
+                finalized = []
+                for mod_idx in range(num_modalities):
+                    if self.fuse_method.name != ContextFuseMethods.RELATIVE:
+                        accum[mod_idx][ci] /= counts[mod_idx][ci]
+                    f = accum[mod_idx][ci]
+
+                    # if guide frames were injected, append them to the end of the fused latents for the next step
+                    if window_state.guide_latents[mod_idx] is not None:
+                        f = torch.cat([f, window_state.guide_latents[mod_idx]], dim=self.dim)
+                    finalized.append(f)
+
+                # pack modalities together if needed
+                if window_state.is_multimodal and len(finalized) > 1:
+                    packed, _ = comfy.utils.pack_latents(finalized)
+                else:
+                    packed = finalized[0]
+
+                result_out.append(packed)
+            return result_out
         finally:
             for callback in comfy.patcher_extension.get_all_callbacks(IndexListCallbacks.EXECUTE_CLEANUP, self.callbacks):
                 callback(self, model, x_in, conds, timestep, model_options)
 
-    def evaluate_context_windows(self, calc_cond_batch: Callable, model: BaseModel, x_in: torch.Tensor, conds, timestep: torch.Tensor, enumerated_context_windows: list[tuple[int, IndexListContextWindow]],
-                                model_options, device=None, first_device=None):
+    def evaluate_context_windows(self, calc_cond_batch: Callable, model: BaseModel, x_in: torch.Tensor, conds,
+                                timestep: torch.Tensor, enumerated_context_windows: list[tuple[int, IndexListContextWindow]],
+                                model_options, window_state: WindowingState, total_windows: int = None,
+                                device=None, first_device=None):
+        """Evaluate context windows and return per-cond, per-modality outputs in ContextResults.sub_conds_out
+
+        For each window:
+        1. Builds windows (for each modality if multimodal)
+        2. Slices window for each modality
+        3. Injects concatenated latent guide frames where present
+        4. Packs together if needed and calls model
+        5. Unpacks and strips any guides from outputs
+        """
+        x = window_state.latents[0]
+
         results: list[ContextResults] = []
         for window_idx, window in enumerated_context_windows:
             # allow processing to end between context window executions for faster Cancel
             comfy.model_management.throw_exception_if_processing_interrupted()
 
-            # causal_window_fix: prepend a pre-window frame that will be stripped post-forward
+            # prepare the window accounting for multimodal windows
+            window = window_state.prepare_window(window, model)
+
+            # causal_window_fix: prepend a pre-window frame that will be stripped post-forward.
+            # Set anchor before slice_for_window so the latent slice and downstream cond slices both pick it up.
             anchor_applied = False
             if self.causal_window_fix:
                 anchor_idx = window.index_list[0] - 1
@@ -339,27 +665,46 @@ class IndexListContextHandler(ContextHandlerABC):
                     window.causal_anchor_index = anchor_idx
                     anchor_applied = True
 
+            # slice the window for each modality, injecting guide frames where applicable
+            sliced, guide_frame_counts_per_modality = window_state.slice_for_window(window, self.latent_retain_index_list, device)
+
             for callback in comfy.patcher_extension.get_all_callbacks(IndexListCallbacks.EVALUATE_CONTEXT_WINDOWS, self.callbacks):
                 callback(self, model, x_in, conds, timestep, model_options, window_idx, window, model_options, device, first_device)
 
-            # update exposed params
+            logging.info(f"Context window {window_idx + 1}/{total_windows or len(enumerated_context_windows)}: frames {window.index_list[0]}-{window.index_list[-1]} of {x.shape[self.dim]}"
+                         + (f" (+{guide_frame_counts_per_modality[0]} guide frames)" if guide_frame_counts_per_modality[0] > 0 else "")
+                         )
+
+            # if multimodal, pack modalities together
+            if window_state.is_multimodal and len(sliced) > 1:
+                sub_x, sub_shapes = comfy.utils.pack_latents(sliced)
+            else:
+                sub_x, sub_shapes = sliced[0], [sliced[0].shape]
+
+            # get resized conds for window
             model_options["transformer_options"]["context_window"] = window
-            # get subsections of x, timestep, conds
-            sub_x = window.get_tensor(x_in, device)
-            sub_timestep = window.get_tensor(timestep, device, dim=0)
-            sub_conds = [self.get_resized_cond(cond, x_in, window, device) for cond in conds]
+            sub_timestep = window.get_tensor(timestep, dim=0)
+            sub_conds = [self.get_resized_cond(cond, x, window) for cond in conds]
 
+            # if multimodal, patch latent_shapes in conds for correct unpacking in model
+            window_state.patch_latent_shapes(sub_conds, sub_shapes)
+
+            # call model on window
             sub_conds_out = calc_cond_batch(model, sub_conds, sub_x, sub_timestep, model_options)
-            if device is not None:
-                for i in range(len(sub_conds_out)):
-                    sub_conds_out[i] = sub_conds_out[i].to(x_in.device)
 
-            # strip causal_window_fix anchor if applied
+            # unpack outputs
+            out_per_modality = [comfy.utils.unpack_latents(sub_conds_out[i], sub_shapes) for i in range(len(sub_conds_out))]
+
+            # strip causal_window_fix anchor from primary modality before guide strip so window_len math stays correct
             if anchor_applied:
-                for i in range(len(sub_conds_out)):
-                    sub_conds_out[i] = sub_conds_out[i].narrow(self.dim, 1, sub_conds_out[i].shape[self.dim] - 1)
+                for ci in range(len(out_per_modality)):
+                    t = out_per_modality[ci][0]
+                    out_per_modality[ci][0] = t.narrow(self.dim, 1, t.shape[self.dim] - 1)
 
-            results.append(ContextResults(window_idx, sub_conds_out, sub_conds, window))
+            # strip injected guide frames
+            window_state.strip_guide_frames(out_per_modality, guide_frame_counts_per_modality, window)
+
+            results.append(ContextResults(window_idx, out_per_modality, sub_conds, window))
         return results
 
 
@@ -383,7 +728,7 @@ class IndexListContextHandler(ContextHandlerABC):
                     biases_final[i][idx] = bias_total + bias
         else:
             # add conds and counts based on weights of fuse method
-            weights = get_context_weights(window.context_length, x_in.shape[self.dim], window.index_list, self, sigma=timestep)
+            weights = get_context_weights(window.context_length, x_in.shape[self.dim], window.index_list, self, sigma=timestep, context_overlap=window.context_overlap)
             weights_tensor = match_weights_to_dim(weights, x_in, self.dim, device=x_in.device)
             for i in range(len(sub_conds_out)):
                 window.add_window(conds_final[i], sub_conds_out[i] * weights_tensor)
@@ -393,16 +738,22 @@ class IndexListContextHandler(ContextHandlerABC):
             callback(self, x_in, sub_conds_out, sub_conds, window, window_idx, total_windows, timestep, conds_final, counts_final, biases_final)
 
 
-def _prepare_sampling_wrapper(executor, model, noise_shape: torch.Tensor, *args, **kwargs):
-    # limit noise_shape length to context_length for more accurate vram use estimation
+def _prepare_sampling_wrapper(executor, model, noise_shape: torch.Tensor, conds, *args, **kwargs):
+    # Scale noise_shape to a single context window so VRAM estimation budgets per-window.
     model_options = kwargs.get("model_options", None)
     if model_options is None:
         raise Exception("model_options not found in prepare_sampling_wrapper; this should never happen, something went wrong.")
     handler: IndexListContextHandler = model_options.get("context_handler", None)
     if handler is not None:
         noise_shape = list(noise_shape)
-        noise_shape[handler.dim] = min(noise_shape[handler.dim], handler.context_length)
-    return executor(model, noise_shape, *args, **kwargs)
+        is_packed = len(noise_shape) == 3 and noise_shape[1] == 1
+        if is_packed:
+            # TODO: latent_shapes cond isn't attached yet at this point, so we can't compute a
+            # per-window flat latent here. Skipping the clamp over-estimates but prevents immediate OOM.
+            pass
+        elif handler.dim < len(noise_shape) and noise_shape[handler.dim] > handler.context_length:
+            noise_shape[handler.dim] = min(noise_shape[handler.dim], handler.context_length)
+    return executor(model, noise_shape, conds, *args, **kwargs)
 
 
 def create_prepare_sampling_wrapper(model: ModelPatcher):
@@ -422,11 +773,12 @@ def _sampler_sample_wrapper(executor, guider, sigmas, extra_args, callback, nois
         raise Exception("context_handler not found in sampler_sample_wrapper; this should never happen, something went wrong.")
     if not handler.freenoise:
         return executor(guider, sigmas, extra_args, callback, noise, *args, **kwargs)
-    noise = apply_freenoise(noise, handler.dim, handler.context_length, handler.context_overlap, extra_args["seed"])
+
+    conds = [guider.conds.get('positive', guider.conds.get('negative', []))]
+    noise = handler._apply_freenoise(noise, conds, extra_args["seed"])
 
     return executor(guider, sigmas, extra_args, callback, noise, *args, **kwargs)
 
-
 def create_sampler_sample_wrapper(model: ModelPatcher):
     model.add_wrapper_with_key(
         comfy.patcher_extension.WrappersMP.SAMPLER_SAMPLE,
@@ -434,7 +786,6 @@ def create_sampler_sample_wrapper(model: ModelPatcher):
         _sampler_sample_wrapper
     )
 
-
 def match_weights_to_dim(weights: list[float], x_in: torch.Tensor, dim: int, device=None) -> torch.Tensor:
     total_dims = len(x_in.shape)
     weights_tensor = torch.Tensor(weights).to(device=device)
@@ -580,8 +931,9 @@ def get_matching_context_schedule(context_schedule: str) -> ContextSchedule:
     return ContextSchedule(context_schedule, func)
 
 
-def get_context_weights(length: int, full_length: int, idxs: list[int], handler: IndexListContextHandler, sigma: torch.Tensor=None):
-    return handler.fuse_method.func(length, sigma=sigma, handler=handler, full_length=full_length, idxs=idxs)
+def get_context_weights(length: int, full_length: int, idxs: list[int], handler: IndexListContextHandler, sigma: torch.Tensor=None, context_overlap: int=None):
+    context_overlap = handler.context_overlap if context_overlap is None else context_overlap
+    return handler.fuse_method.func(length, sigma=sigma, handler=handler, full_length=full_length, idxs=idxs, context_overlap=context_overlap)
 
 
 def create_weights_flat(length: int, **kwargs) -> list[float]:
@@ -599,18 +951,18 @@ def create_weights_pyramid(length: int, **kwargs) -> list[float]:
         weight_sequence = list(range(1, max_weight, 1)) + [max_weight] + list(range(max_weight - 1, 0, -1))
     return weight_sequence
 
-def create_weights_overlap_linear(length: int, full_length: int, idxs: list[int], handler: IndexListContextHandler, **kwargs):
+def create_weights_overlap_linear(length: int, full_length: int, idxs: list[int], context_overlap: int, **kwargs):
     # based on code in Kijai's WanVideoWrapper: https://github.com/kijai/ComfyUI-WanVideoWrapper/blob/dbb2523b37e4ccdf45127e5ae33e31362f755c8e/nodes.py#L1302
     # only expected overlap is given different weights
     weights_torch = torch.ones((length))
     # blend left-side on all except first window
     if min(idxs) > 0:
-        ramp_up = torch.linspace(1e-37, 1, handler.context_overlap)
-        weights_torch[:handler.context_overlap] = ramp_up
+        ramp_up = torch.linspace(1e-37, 1, context_overlap)
+        weights_torch[:context_overlap] = ramp_up
     # blend right-side on all except last window
     if max(idxs) < full_length-1:
-        ramp_down = torch.linspace(1, 1e-37, handler.context_overlap)
-        weights_torch[-handler.context_overlap:] = ramp_down
+        ramp_down = torch.linspace(1, 1e-37, context_overlap)
+        weights_torch[-context_overlap:] = ramp_down
     return weights_torch
 
 class ContextFuseMethods:

comfy/image_encoders/dino2.py

@@ -1,7 +1,13 @@
 import torch
+import torch.nn.functional as F
+
 from comfy.text_encoders.bert import BertAttention
 import comfy.model_management
 from comfy.ldm.modules.attention import optimized_attention_for_device
+from comfy.ldm.depth_anything_3.reference_view_selector import (
+    select_reference_view, reorder_by_reference, restore_original_order,
+    THRESH_FOR_REF_SELECTION,
+)
 
 
 class Dino2AttentionOutput(torch.nn.Module):
@@ -14,13 +20,41 @@ class Dino2AttentionOutput(torch.nn.Module):
 
 
 class Dino2AttentionBlock(torch.nn.Module):
-    def __init__(self, embed_dim, heads, layer_norm_eps, dtype, device, operations):
+    def __init__(self, embed_dim, heads, layer_norm_eps, dtype, device, operations,
+                 qk_norm=False):
         super().__init__()
+        self.heads = heads
+        self.head_dim = embed_dim // heads
         self.attention = BertAttention(embed_dim, heads, dtype, device, operations)
         self.output = Dino2AttentionOutput(embed_dim, embed_dim, layer_norm_eps, dtype, device, operations)
+        if qk_norm:
+            self.q_norm = operations.LayerNorm(self.head_dim, dtype=dtype, device=device)
+            self.k_norm = operations.LayerNorm(self.head_dim, dtype=dtype, device=device)
+        else:
+            self.q_norm = None
+            self.k_norm = None
 
-    def forward(self, x, mask, optimized_attention):
-        return self.output(self.attention(x, mask, optimized_attention))
+    def forward(self, x, mask, optimized_attention, pos=None, rope=None):
+        # Fast path used by the existing CLIP-vision DINOv2 (no DA3 extensions).
+        if self.q_norm is None and rope is None:
+            return self.output(self.attention(x, mask, optimized_attention))
+
+        # DA3 path: do QKV manually so we can apply per-head QK-norm and 2D RoPE.
+        attn = self.attention
+        B, N, C = x.shape
+        h = self.heads
+        d = self.head_dim
+        q = attn.query(x).view(B, N, h, d).transpose(1, 2)
+        k = attn.key(x).view(B, N, h, d).transpose(1, 2)
+        v = attn.value(x).view(B, N, h, d).transpose(1, 2)
+        if self.q_norm is not None:
+            q = self.q_norm(q)
+            k = self.k_norm(k)
+        if rope is not None and pos is not None:
+            q = rope(q, pos)
+            k = rope(k, pos)
+        out = optimized_attention(q, k, v, h, mask=mask, skip_reshape=True)
+        return self.output(out)
 
 
 class LayerScale(torch.nn.Module):
@@ -64,9 +98,11 @@ class SwiGLUFFN(torch.nn.Module):
 
 
 class Dino2Block(torch.nn.Module):
-    def __init__(self, dim, num_heads, layer_norm_eps, dtype, device, operations, use_swiglu_ffn):
+    def __init__(self, dim, num_heads, layer_norm_eps, dtype, device, operations, use_swiglu_ffn,
+                 qk_norm=False):
         super().__init__()
-        self.attention = Dino2AttentionBlock(dim, num_heads, layer_norm_eps, dtype, device, operations)
+        self.attention = Dino2AttentionBlock(dim, num_heads, layer_norm_eps, dtype, device, operations,
+                                             qk_norm=qk_norm)
         self.layer_scale1 = LayerScale(dim, dtype, device, operations)
         self.layer_scale2 = LayerScale(dim, dtype, device, operations)
         if use_swiglu_ffn:
@@ -76,19 +112,90 @@ class Dino2Block(torch.nn.Module):
         self.norm1 = operations.LayerNorm(dim, eps=layer_norm_eps, dtype=dtype, device=device)
         self.norm2 = operations.LayerNorm(dim, eps=layer_norm_eps, dtype=dtype, device=device)
 
-    def forward(self, x, optimized_attention):
-        x = x + self.layer_scale1(self.attention(self.norm1(x), None, optimized_attention))
+    def forward(self, x, optimized_attention, pos=None, rope=None, attn_mask=None):
+        x = x + self.layer_scale1(self.attention(self.norm1(x), attn_mask, optimized_attention,
+                                                 pos=pos, rope=rope))
         x = x + self.layer_scale2(self.mlp(self.norm2(x)))
         return x
 
 
-class Dino2Encoder(torch.nn.Module):
-    def __init__(self, dim, num_heads, layer_norm_eps, num_layers, dtype, device, operations, use_swiglu_ffn):
+# -----------------------------------------------------------------------------
+# 2D Rotary position embedding (DA3 extension)
+# -----------------------------------------------------------------------------
+
+
+class _PositionGetter:
+    """Cache (h, w) -> flat (y, x) position grid used to feed ``rope``."""
+
+    def __init__(self):
+        self._cache: dict = {}
+
+    def __call__(self, batch_size: int, height: int, width: int, device) -> torch.Tensor:
+        key = (height, width, device)
+        if key not in self._cache:
+            y = torch.arange(height, device=device)
+            x = torch.arange(width, device=device)
+            self._cache[key] = torch.cartesian_prod(y, x)
+        cached = self._cache[key]
+        return cached.view(1, height * width, 2).expand(batch_size, -1, -1).clone()
+
+
+class RotaryPositionEmbedding2D(torch.nn.Module):
+    """2D RoPE used by DA3-Small/Base. No learnable parameters."""
+
+    def __init__(self, frequency: float = 100.0):
         super().__init__()
-        self.layer = torch.nn.ModuleList([Dino2Block(dim, num_heads, layer_norm_eps, dtype, device, operations, use_swiglu_ffn = use_swiglu_ffn)
-                                          for _ in range(num_layers)])
+        self.base_frequency = frequency
+        self._freq_cache: dict = {}
+
+    def _components(self, dim: int, seq_len: int, device, dtype):
+        key = (dim, seq_len, device, dtype)
+        if key not in self._freq_cache:
+            exp = torch.arange(0, dim, 2, device=device).float() / dim
+            inv_freq = 1.0 / (self.base_frequency ** exp)
+            pos = torch.arange(seq_len, device=device, dtype=inv_freq.dtype)
+            ang = torch.einsum("i,j->ij", pos, inv_freq)
+            ang = ang.to(dtype)
+            ang = torch.cat((ang, ang), dim=-1)
+            self._freq_cache[key] = (ang.cos().to(dtype), ang.sin().to(dtype))
+        return self._freq_cache[key]
+
+    @staticmethod
+    def _rotate(x: torch.Tensor) -> torch.Tensor:
+        d = x.shape[-1]
+        x1, x2 = x[..., : d // 2], x[..., d // 2:]
+        return torch.cat((-x2, x1), dim=-1)
+
+    def _apply_1d(self, tokens, positions, cos_c, sin_c):
+        cos = F.embedding(positions, cos_c)[:, None, :, :]
+        sin = F.embedding(positions, sin_c)[:, None, :, :]
+        return (tokens * cos) + (self._rotate(tokens) * sin)
+
+    def forward(self, tokens: torch.Tensor, positions: torch.Tensor) -> torch.Tensor:
+        feature_dim = tokens.size(-1) // 2
+        max_pos = int(positions.max()) + 1
+        cos_c, sin_c = self._components(feature_dim, max_pos, tokens.device, tokens.dtype)
+        v, h = tokens.chunk(2, dim=-1)
+        v = self._apply_1d(v, positions[..., 0], cos_c, sin_c)
+        h = self._apply_1d(h, positions[..., 1], cos_c, sin_c)
+        return torch.cat((v, h), dim=-1)
+
+
+class Dino2Encoder(torch.nn.Module):
+    def __init__(self, dim, num_heads, layer_norm_eps, num_layers, dtype, device, operations, use_swiglu_ffn,
+                 qknorm_start: int = -1):
+        super().__init__()
+        self.layer = torch.nn.ModuleList([
+            Dino2Block(
+                dim, num_heads, layer_norm_eps, dtype, device, operations,
+                use_swiglu_ffn=use_swiglu_ffn,
+                qk_norm=(qknorm_start != -1 and i >= qknorm_start),
+            )
+            for i in range(num_layers)
+        ])
 
     def forward(self, x, intermediate_output=None):
+        # Backward-compat path used by ``ClipVisionModel`` (no DA3 extensions).
         optimized_attention = optimized_attention_for_device(x.device, False, small_input=True)
 
         if intermediate_output is not None:
@@ -122,16 +229,27 @@ class Dino2PatchEmbeddings(torch.nn.Module):
 
 
 class Dino2Embeddings(torch.nn.Module):
-    def __init__(self, dim, dtype, device, operations):
+    def __init__(self, dim, dtype, device, operations,
+                 patch_size: int = 14, image_size: int = 518,
+                 use_mask_token: bool = True,
+                 num_camera_tokens: int = 0):
         super().__init__()
-        patch_size = 14
-        image_size = 518
         self.patch_size = patch_size
+        self.image_size = image_size
 
         self.patch_embeddings = Dino2PatchEmbeddings(dim, patch_size=patch_size, image_size=image_size, dtype=dtype, device=device, operations=operations)
         self.position_embeddings = torch.nn.Parameter(torch.empty(1, (image_size // patch_size) ** 2 + 1, dim, dtype=dtype, device=device))
         self.cls_token = torch.nn.Parameter(torch.empty(1, 1, dim, dtype=dtype, device=device)) # mask_token is a pre-training param, kept only so strict loading accepts the key.
-        self.mask_token = torch.nn.Parameter(torch.empty(1, dim, dtype=dtype, device=device))
+        if use_mask_token:
+            self.mask_token = torch.nn.Parameter(torch.empty(1, dim, dtype=dtype, device=device))
+        else:
+            self.mask_token = None
+        if num_camera_tokens > 0:
+            # DA3 stores (ref_token, src_token) pairs that get injected at the
+            # alt-attn boundary; see ``Dinov2Model._inject_camera_token``.
+            self.camera_token = torch.nn.Parameter(torch.empty(1, num_camera_tokens, dim, dtype=dtype, device=device))
+        else:
+            self.camera_token = None
 
     def interpolate_pos_encoding(self, x, h_pixels, w_pixels):
         pos_embed = comfy.model_management.cast_to_device(self.position_embeddings, x.device, torch.float32)
@@ -140,12 +258,22 @@ class Dino2Embeddings(torch.nn.Module):
         patch_pos = pos_embed[:, 1:]
         N = patch_pos.shape[1]
         M = int(N ** 0.5)
+        assert N == M * M, f"DINOv2 position grid must be square, got N={N} patches (sqrt={M})"
         h0 = h_pixels // self.patch_size
         w0 = w_pixels // self.patch_size
-        scale_factor = ((h0 + 0.1) / M, (w0 + 0.1) / M)  # +0.1 matches upstream DINOv2's FP-rounding workaround so the interpolate output size lands on (h0, w0).
+        # +0.1 matches upstream DINOv2's FP-rounding workaround so the interpolate output size lands on (h0, w0).
+        # scale_factor is (height_scale, width_scale) -- height MUST come first;
+        # swapping these only happens to work for square inputs and breaks
+        # non-square paths like DA3-Small / DA3-Base multi-view.
+        scale_factor = ((h0 + 0.1) / M, (w0 + 0.1) / M)
 
         patch_pos = patch_pos.reshape(1, M, M, -1).permute(0, 3, 1, 2)
         patch_pos = torch.nn.functional.interpolate(patch_pos, scale_factor=scale_factor, mode="bicubic", antialias=False)
+        assert (h0, w0) == patch_pos.shape[-2:], (
+            f"Interpolated pos-embed grid {tuple(patch_pos.shape[-2:])} does not match "
+            f"target patch grid ({h0}, {w0}) for input {h_pixels}x{w_pixels} (patch_size={self.patch_size}); "
+            f"check scale_factor axis order and +0.1 rounding workaround"
+        )
         patch_pos = patch_pos.permute(0, 2, 3, 1).flatten(1, 2)
         return torch.cat((class_pos, patch_pos), dim=1).to(x.dtype)
 
@@ -168,12 +296,51 @@ class Dinov2Model(torch.nn.Module):
         heads = config_dict["num_attention_heads"]
         layer_norm_eps = config_dict["layer_norm_eps"]
         use_swiglu_ffn = config_dict["use_swiglu_ffn"]
+        patch_size = config_dict.get("patch_size", 14)
+        image_size = config_dict.get("image_size", 518)
+        use_mask_token = config_dict.get("use_mask_token", True)
 
-        self.embeddings = Dino2Embeddings(dim, dtype, device, operations)
-        self.encoder = Dino2Encoder(dim, heads, layer_norm_eps, num_layers, dtype, device, operations, use_swiglu_ffn = use_swiglu_ffn)
+        # DA3 extensions (all default to disabled).
+        self.alt_start = config_dict.get("alt_start", -1)
+        self.qknorm_start = config_dict.get("qknorm_start", -1)
+        self.rope_start = config_dict.get("rope_start", -1)
+        self.cat_token = config_dict.get("cat_token", False)
+        rope_freq = config_dict.get("rope_freq", 100.0)
+
+        self.embed_dim = dim
+        self.patch_size = patch_size
+        self.num_register_tokens = 0
+        self.patch_start_idx = 1
+
+        if self.rope_start != -1 and rope_freq > 0:
+            self.rope = RotaryPositionEmbedding2D(frequency=rope_freq)
+            self._position_getter = _PositionGetter()
+        else:
+            self.rope = None
+            self._position_getter = None
+
+        # camera_token shape: (1, 2, dim) -> (ref_token, src_token).
+        num_cam_tokens = 2 if self.alt_start != -1 else 0
+
+        self.embeddings = Dino2Embeddings(
+            dim, dtype, device, operations,
+            patch_size=patch_size, image_size=image_size,
+            use_mask_token=use_mask_token, num_camera_tokens=num_cam_tokens,
+        )
+        self.encoder = Dino2Encoder(
+            dim, heads, layer_norm_eps, num_layers, dtype, device, operations,
+            use_swiglu_ffn=use_swiglu_ffn,
+            qknorm_start=self.qknorm_start,
+        )
         self.layernorm = operations.LayerNorm(dim, eps=layer_norm_eps, dtype=dtype, device=device)
 
     def forward(self, pixel_values, attention_mask=None, intermediate_output=None):
+        if self.alt_start != -1:
+            raise RuntimeError(
+                "Dinov2Model.forward() is the backward-compatible CLIP-vision path and does not "
+                "apply DA3 extensions (RoPE, alternating attention, camera-token injection). "
+                "Use get_intermediate_layers_da3() for Depth Anything 3 models."
+            )
         x = self.embeddings(pixel_values)
         x, i = self.encoder(x, intermediate_output=intermediate_output)
         x = self.layernorm(x)
@@ -181,6 +348,7 @@ class Dinov2Model(torch.nn.Module):
         return x, i, pooled_output, None
 
     def get_intermediate_layers(self, pixel_values, indices, apply_norm=True):
+        """Single-view multi-layer feature extraction."""
         x = self.embeddings(pixel_values)
         optimized_attention = optimized_attention_for_device(x.device, False, small_input=True)
         n_layers = len(self.encoder.layer)
@@ -197,3 +365,132 @@ class Dinov2Model(torch.nn.Module):
             if i >= max_idx:
                 break
         return [cache[i] for i in resolved]
+
+    # ------------------------------------------------------------------
+    # Depth Anything 3 forward
+    # ------------------------------------------------------------------
+    def _prepare_rope_positions(self, B, S, H, W, device):
+        if self.rope is None:
+            return None, None
+        ph, pw = H // self.patch_size, W // self.patch_size
+        pos = self._position_getter(B * S, ph, pw, device=device)
+        # Shift so the cls/cam token at position 0 is reserved for "no diff".
+        pos = pos + 1
+        cls_pos = torch.zeros(B * S, self.patch_start_idx, 2, device=device, dtype=pos.dtype)
+        # Per-view local: real grid positions for patches, 0 for cls token.
+        pos_local = torch.cat([cls_pos, pos], dim=1)
+        # Global (across views): same grid positions; cls token still at 0,
+        # but patches share the same positions in every view.
+        pos_global = torch.cat([cls_pos, torch.zeros_like(pos) + 1], dim=1)
+        return pos_local, pos_global
+
+    def _inject_camera_token(self, x: torch.Tensor, B: int, S: int, cam_token: "torch.Tensor | None") -> torch.Tensor:
+        # x: (B, S, N, C). Replace token at index 0 with the camera token.
+        if cam_token is not None:
+            inj = cam_token
+        else:
+            ct = comfy.model_management.cast_to_device(self.embeddings.camera_token, x.device, x.dtype)
+            ref_token = ct[:, :1].expand(B, -1, -1)
+            src_token = ct[:, 1:].expand(B, max(S - 1, 0), -1)
+            inj = torch.cat([ref_token, src_token], dim=1)
+        x = x.clone()
+        x[:, :, 0] = inj
+        return x
+
+    def get_intermediate_layers_da3(self, pixel_values, out_layers, cam_token=None, ref_view_strategy="saddle_balanced", export_feat_layers=None):
+        """Multi-view multi-layer feature extraction used by Depth Anything 3."""
+        if pixel_values.ndim == 4:
+            pixel_values = pixel_values.unsqueeze(1)
+        assert pixel_values.ndim == 5 and pixel_values.shape[2] == 3, \
+            f"expected (B,3,H,W) or (B,S,3,H,W); got {tuple(pixel_values.shape)}"
+        B, S, _, H, W = pixel_values.shape
+
+        # Patch + cls + (interpolated) pos embed for each view.
+        x = pixel_values.reshape(B * S, 3, H, W)
+        x = self.embeddings(x)                          # (B*S, 1+N, C)
+        x = x.reshape(B, S, x.shape[-2], x.shape[-1])    # (B, S, 1+N, C)
+
+        pos_local, pos_global = self._prepare_rope_positions(B, S, H, W, x.device)
+        # optimized_attention is only used by blocks without QK-norm/RoPE
+        # (vanilla DINOv2 path); enabling-aware blocks fall through to SDPA.
+        optimized_attention = optimized_attention_for_device(x.device, False, small_input=True)
+
+        out_set = set(out_layers)
+        export_set = set(export_feat_layers) if export_feat_layers else set()
+        outputs: list[torch.Tensor] = []
+        aux_outputs: list[torch.Tensor] = []
+        local_x = x
+        b_idx = None
+
+
+        for i, blk in enumerate(self.encoder.layer):
+            apply_rope = self.rope is not None and i >= self.rope_start
+            block_rope = self.rope if apply_rope else None
+            l_pos = pos_local if apply_rope else None
+            g_pos = pos_global if apply_rope else None
+
+            # Reference-view selection threshold: matches the upstream constant
+            # THRESH_FOR_REF_SELECTION = 3. Skipped when a user-supplied
+            # cam_token is provided (camera info already pins the geometry).
+            if (self.alt_start != -1 and i == self.alt_start - 1 and S >= THRESH_FOR_REF_SELECTION and cam_token is None):
+                b_idx = select_reference_view(x, strategy=ref_view_strategy)
+                x = reorder_by_reference(x, b_idx)
+                local_x = reorder_by_reference(local_x, b_idx)
+
+            if self.alt_start != -1 and i == self.alt_start:
+                x = self._inject_camera_token(x, B, S, cam_token)
+
+            if self.alt_start != -1 and i >= self.alt_start and (i % 2 == 1):
+                # Global attention across views: flatten S into the seq dim.
+                t = x.reshape(B, S * x.shape[-2], x.shape[-1])
+                p = g_pos.reshape(B, S * g_pos.shape[-2], g_pos.shape[-1]) if g_pos is not None else None
+                t = blk(t, optimized_attention=optimized_attention, pos=p, rope=block_rope)
+                x = t.reshape(B, S, x.shape[-2], x.shape[-1])
+            else:
+                # Per-view local attention.
+                t = x.reshape(B * S, x.shape[-2], x.shape[-1])
+                p = l_pos.reshape(B * S, l_pos.shape[-2], l_pos.shape[-1]) if l_pos is not None else None
+                t = blk(t, optimized_attention=optimized_attention, pos=p, rope=block_rope)
+                x = t.reshape(B, S, x.shape[-2], x.shape[-1])
+                local_x = x
+
+            if i in out_set:
+                if self.cat_token:
+                    out_x = torch.cat([local_x, x], dim=-1)
+                else:
+                    out_x = x
+                # Restore original view order on the way out so heads see views
+                # in the user's expected order.
+                if b_idx is not None and self.alt_start != -1:
+                    out_x = restore_original_order(out_x, b_idx)
+                outputs.append(out_x)
+
+            if i in export_set:
+                aux = x
+                if b_idx is not None and self.alt_start != -1:
+                    aux = restore_original_order(aux, b_idx)
+                aux_outputs.append(aux)
+
+        # Apply final norm. When cat_token is set, only the right half
+        # ("global" features) is normalised; the left half is left as-is to
+        # match the upstream DA3 head signature.
+        normed: list[torch.Tensor] = []
+        cls_tokens: list[torch.Tensor] = []
+        for out_x in outputs:
+            cls_tokens.append(out_x[:, :, 0])
+            if out_x.shape[-1] == self.embed_dim:
+                normed.append(self.layernorm(out_x))
+            elif out_x.shape[-1] == self.embed_dim * 2:
+                left = out_x[..., :self.embed_dim]
+                right = self.layernorm(out_x[..., self.embed_dim:])
+                normed.append(torch.cat([left, right], dim=-1))
+            else:
+                raise ValueError(f"Unexpected token width: {out_x.shape[-1]}")
+
+        # Drop cls/cam token from the patch sequence.
+        normed = [o[..., 1 + self.num_register_tokens:, :] for o in normed]
+
+        # Final layernorm + drop cls token from auxiliary features too.
+        aux_normed = [self.layernorm(o)[..., 1 + self.num_register_tokens:, :]
+                      for o in aux_outputs]
+        return list(zip(normed, cls_tokens)), aux_normed

comfy/ldm/boogu/model.py

@@ -0,0 +1,321 @@
+# Boogu-Image-0.1 transformer
+# Architecture is an OmniGen2 derivative (see comfy/ldm/omnigen/omnigen2.py) with an
+# added dual-stream ("double_stream") stage before the single-stream layers, conditioned
+# by a Qwen3-VL multimodal LLM. Reuses the OmniGen2/Lumina building blocks and the Flux
+# RoPE core, the only new component is the double-stream block + the hybrid forward order.
+
+from typing import Optional, Tuple
+
+import torch
+import torch.nn as nn
+from einops import rearrange
+
+import comfy.ldm.common_dit
+import comfy.ldm.omnigen.omnigen2
+from comfy.ldm.modules.attention import optimized_attention_masked
+from comfy.ldm.omnigen.omnigen2 import (
+    OmniGen2RotaryPosEmbed,
+    Lumina2CombinedTimestepCaptionEmbedding,
+    LuminaRMSNormZero,
+    LuminaLayerNormContinuous,
+    LuminaFeedForward,
+    Attention,
+    OmniGen2TransformerBlock,
+    apply_rotary_emb,
+)
+
+class BooguDoubleStreamProcessor(nn.Module):
+    # Joint attention over [instruct ; img] with separate per-stream q/k/v and output projections.
+    def __init__(self, dim, head_dim, heads, kv_heads, dtype=None, device=None, operations=None):
+        super().__init__()
+        query_dim = head_dim * heads
+        kv_dim = head_dim * kv_heads
+
+        self.img_to_q = operations.Linear(query_dim, query_dim, bias=False, dtype=dtype, device=device)
+        self.img_to_k = operations.Linear(query_dim, kv_dim, bias=False, dtype=dtype, device=device)
+        self.img_to_v = operations.Linear(query_dim, kv_dim, bias=False, dtype=dtype, device=device)
+
+        self.instruct_to_q = operations.Linear(query_dim, query_dim, bias=False, dtype=dtype, device=device)
+        self.instruct_to_k = operations.Linear(query_dim, kv_dim, bias=False, dtype=dtype, device=device)
+        self.instruct_to_v = operations.Linear(query_dim, kv_dim, bias=False, dtype=dtype, device=device)
+
+        self.instruct_out = operations.Linear(query_dim, query_dim, bias=False, dtype=dtype, device=device)
+        self.img_out = operations.Linear(query_dim, query_dim, bias=False, dtype=dtype, device=device)
+
+    def forward(self, attn, img_hidden_states, instruct_hidden_states, rotary_emb, attention_mask=None, transformer_options={}):
+        batch_size = img_hidden_states.shape[0]
+        L_instruct = instruct_hidden_states.shape[1]
+
+        img_q = self.img_to_q(img_hidden_states)
+        img_k = self.img_to_k(img_hidden_states)
+        img_v = self.img_to_v(img_hidden_states)
+
+        instruct_q = self.instruct_to_q(instruct_hidden_states)
+        instruct_k = self.instruct_to_k(instruct_hidden_states)
+        instruct_v = self.instruct_to_v(instruct_hidden_states)
+
+        # Concatenate instruction first, then image (matches reference processor order).
+        query = torch.cat([instruct_q, img_q], dim=1)
+        key = torch.cat([instruct_k, img_k], dim=1)
+        value = torch.cat([instruct_v, img_v], dim=1)
+
+        query = query.view(batch_size, -1, attn.heads, attn.dim_head)
+        key = key.view(batch_size, -1, attn.kv_heads, attn.dim_head)
+        value = value.view(batch_size, -1, attn.kv_heads, attn.dim_head)
+
+        query = attn.norm_q(query)
+        key = attn.norm_k(key)
+
+        if rotary_emb is not None:
+            query = apply_rotary_emb(query, rotary_emb)
+            key = apply_rotary_emb(key, rotary_emb)
+
+        query = query.transpose(1, 2)
+        key = key.transpose(1, 2)
+        value = value.transpose(1, 2)
+
+        if attn.kv_heads < attn.heads:
+            key = key.repeat_interleave(attn.heads // attn.kv_heads, dim=1)
+            value = value.repeat_interleave(attn.heads // attn.kv_heads, dim=1)
+
+        hidden_states = optimized_attention_masked(query, key, value, attn.heads, attention_mask, skip_reshape=True, transformer_options=transformer_options)
+
+        # Split back to instruction/image, apply per-stream output projections, recombine.
+        instruct_hidden_states = self.instruct_out(hidden_states[:, :L_instruct])
+        img_hidden_states = self.img_out(hidden_states[:, L_instruct:])
+        hidden_states = torch.cat([instruct_hidden_states, img_hidden_states], dim=1)
+
+        hidden_states = attn.to_out[0](hidden_states)
+        return hidden_states
+
+
+class BooguJointAttention(nn.Module):
+    # Holds the shared q/k RMSNorm + final output projection
+    def __init__(self, dim, head_dim, heads, kv_heads, eps=1e-5, dtype=None, device=None, operations=None):
+        super().__init__()
+        self.heads = heads
+        self.kv_heads = kv_heads
+        self.dim_head = head_dim
+        self.scale = head_dim ** -0.5
+
+        self.norm_q = operations.RMSNorm(head_dim, eps=eps, dtype=dtype, device=device)
+        self.norm_k = operations.RMSNorm(head_dim, eps=eps, dtype=dtype, device=device)
+        self.to_out = nn.Sequential(
+            operations.Linear(heads * head_dim, dim, bias=False, dtype=dtype, device=device),
+            nn.Dropout(0.0),
+        )
+        self.processor = BooguDoubleStreamProcessor(dim, head_dim, heads, kv_heads, dtype=dtype, device=device, operations=operations)
+
+    def forward(self, img_hidden_states, instruct_hidden_states, rotary_emb, attention_mask=None, transformer_options={}):
+        return self.processor(self, img_hidden_states, instruct_hidden_states, rotary_emb, attention_mask, transformer_options=transformer_options)
+
+
+class BooguDoubleStreamBlock(nn.Module):
+    # Dual-stream block: joint attention over [instruct ; img] + image self-attention, each stream with its own modulation/MLP.
+    def __init__(self, dim, num_attention_heads, num_kv_heads, multiple_of, ffn_dim_multiplier, norm_eps, dtype=None, device=None, operations=None):
+        super().__init__()
+        head_dim = dim // num_attention_heads
+
+        self.img_instruct_attn = BooguJointAttention(dim, head_dim, num_attention_heads, num_kv_heads, eps=1e-5, dtype=dtype, device=device, operations=operations)
+        self.img_self_attn = Attention(
+            query_dim=dim, dim_head=head_dim, heads=num_attention_heads, kv_heads=num_kv_heads,
+            eps=1e-5, bias=False, dtype=dtype, device=device, operations=operations,
+        )
+
+        self.img_feed_forward = LuminaFeedForward(dim=dim, inner_dim=4 * dim, multiple_of=multiple_of, dtype=dtype, device=device, operations=operations)
+        self.instruct_feed_forward = LuminaFeedForward(dim=dim, inner_dim=4 * dim, multiple_of=multiple_of, dtype=dtype, device=device, operations=operations)
+
+        self.img_norm1 = LuminaRMSNormZero(embedding_dim=dim, norm_eps=norm_eps, dtype=dtype, device=device, operations=operations)
+        self.img_norm2 = LuminaRMSNormZero(embedding_dim=dim, norm_eps=norm_eps, dtype=dtype, device=device, operations=operations)
+        self.img_norm3 = LuminaRMSNormZero(embedding_dim=dim, norm_eps=norm_eps, dtype=dtype, device=device, operations=operations)
+        self.instruct_norm1 = LuminaRMSNormZero(embedding_dim=dim, norm_eps=norm_eps, dtype=dtype, device=device, operations=operations)
+        self.instruct_norm2 = LuminaRMSNormZero(embedding_dim=dim, norm_eps=norm_eps, dtype=dtype, device=device, operations=operations)
+
+        self.img_attn_norm = operations.RMSNorm(dim, eps=norm_eps, dtype=dtype, device=device)
+        self.img_self_attn_norm = operations.RMSNorm(dim, eps=norm_eps, dtype=dtype, device=device)
+        self.img_ffn_norm1 = operations.RMSNorm(dim, eps=norm_eps, dtype=dtype, device=device)
+        self.img_ffn_norm2 = operations.RMSNorm(dim, eps=norm_eps, dtype=dtype, device=device)
+
+        self.instruct_attn_norm = operations.RMSNorm(dim, eps=norm_eps, dtype=dtype, device=device)
+        self.instruct_ffn_norm1 = operations.RMSNorm(dim, eps=norm_eps, dtype=dtype, device=device)
+        self.instruct_ffn_norm2 = operations.RMSNorm(dim, eps=norm_eps, dtype=dtype, device=device)
+
+    def forward(self, img_hidden_states, instruct_hidden_states, joint_rotary_emb, img_rotary_emb, temb, joint_attention_mask=None, img_attention_mask=None, transformer_options={}):
+        L_instruct = instruct_hidden_states.shape[1]
+
+        img_norm1_out, img_gate_msa, img_scale_mlp, img_gate_mlp = self.img_norm1(img_hidden_states, temb)
+        img_norm2_out, img_shift_mlp, _, _ = self.img_norm2(img_hidden_states, temb)
+        img_norm3_out, img_gate_self, _, _ = self.img_norm3(img_hidden_states, temb)
+
+        instruct_norm1_out, instruct_gate_msa, instruct_scale_mlp, instruct_gate_mlp = self.instruct_norm1(instruct_hidden_states, temb)
+        instruct_norm2_out, instruct_shift_mlp, _, _ = self.instruct_norm2(instruct_hidden_states, temb)
+
+        joint_attn_out = self.img_instruct_attn(img_norm1_out, instruct_norm1_out, joint_rotary_emb, joint_attention_mask, transformer_options=transformer_options)
+        instruct_attn_out = joint_attn_out[:, :L_instruct]
+        img_attn_out = joint_attn_out[:, L_instruct:]
+
+        img_self_attn_out = self.img_self_attn(img_norm3_out, img_norm3_out, img_attention_mask, img_rotary_emb, transformer_options=transformer_options)
+
+        img_hidden_states = img_hidden_states + img_gate_msa.unsqueeze(1).tanh() * self.img_attn_norm(img_attn_out)
+        img_hidden_states = img_hidden_states + img_gate_self.unsqueeze(1).tanh() * self.img_self_attn_norm(img_self_attn_out)
+        img_mlp_input = (1 + img_scale_mlp.unsqueeze(1)) * img_norm2_out + img_shift_mlp.unsqueeze(1)
+        img_mlp_out = self.img_feed_forward(self.img_ffn_norm1(img_mlp_input))
+        img_hidden_states = img_hidden_states + img_gate_mlp.unsqueeze(1).tanh() * self.img_ffn_norm2(img_mlp_out)
+
+        instruct_hidden_states = instruct_hidden_states + instruct_gate_msa.unsqueeze(1).tanh() * self.instruct_attn_norm(instruct_attn_out)
+        instruct_mlp_input = (1 + instruct_scale_mlp.unsqueeze(1)) * instruct_norm2_out + instruct_shift_mlp.unsqueeze(1)
+        instruct_mlp_out = self.instruct_feed_forward(self.instruct_ffn_norm1(instruct_mlp_input))
+        instruct_hidden_states = instruct_hidden_states + instruct_gate_mlp.unsqueeze(1).tanh() * self.instruct_ffn_norm2(instruct_mlp_out)
+
+        return img_hidden_states, instruct_hidden_states
+
+
+class BooguTransformer2DModel(nn.Module):
+    def __init__(
+        self,
+        patch_size: int = 2,
+        in_channels: int = 16,
+        out_channels: Optional[int] = None,
+        hidden_size: int = 3360,
+        num_layers: int = 32,
+        num_double_stream_layers: int = 8,
+        num_refiner_layers: int = 2,
+        num_attention_heads: int = 28,
+        num_kv_heads: int = 7,
+        multiple_of: int = 256,
+        ffn_dim_multiplier: Optional[float] = None,
+        norm_eps: float = 1e-5,
+        axes_dim_rope: Tuple[int, int, int] = (40, 40, 40),
+        axes_lens: Tuple[int, int, int] = (2048, 1664, 1664),
+        instruction_feat_dim: int = 4096,
+        timestep_scale: float = 1000.0,
+        image_model=None,
+        device=None, dtype=None, operations=None,
+    ):
+        super().__init__()
+
+        self.patch_size = patch_size
+        self.out_channels = out_channels or in_channels
+        self.hidden_size = hidden_size
+        self.dtype = dtype
+
+        self.rope_embedder = OmniGen2RotaryPosEmbed(
+            theta=10000,
+            axes_dim=axes_dim_rope,
+            axes_lens=axes_lens,
+            patch_size=patch_size,
+        )
+
+        self.x_embedder = operations.Linear(patch_size * patch_size * in_channels, hidden_size, dtype=dtype, device=device)
+        self.ref_image_patch_embedder = operations.Linear(patch_size * patch_size * in_channels, hidden_size, dtype=dtype, device=device)
+
+        self.time_caption_embed = Lumina2CombinedTimestepCaptionEmbedding(
+            hidden_size=hidden_size,
+            text_feat_dim=instruction_feat_dim,
+            norm_eps=norm_eps,
+            timestep_scale=timestep_scale, dtype=dtype, device=device, operations=operations
+        )
+
+        self.noise_refiner = nn.ModuleList([
+            OmniGen2TransformerBlock(hidden_size, num_attention_heads, num_kv_heads, multiple_of, ffn_dim_multiplier, norm_eps, modulation=True, dtype=dtype, device=device, operations=operations)
+            for _ in range(num_refiner_layers)
+        ])
+
+        self.ref_image_refiner = nn.ModuleList([
+            OmniGen2TransformerBlock(hidden_size, num_attention_heads, num_kv_heads, multiple_of, ffn_dim_multiplier, norm_eps, modulation=True, dtype=dtype, device=device, operations=operations)
+            for _ in range(num_refiner_layers)
+        ])
+
+        self.context_refiner = nn.ModuleList([
+            OmniGen2TransformerBlock(hidden_size, num_attention_heads, num_kv_heads, multiple_of, ffn_dim_multiplier, norm_eps, modulation=False, dtype=dtype, device=device, operations=operations)
+            for _ in range(num_refiner_layers)
+        ])
+
+        self.double_stream_layers = nn.ModuleList([
+            BooguDoubleStreamBlock(hidden_size, num_attention_heads, num_kv_heads, multiple_of, ffn_dim_multiplier, norm_eps, dtype=dtype, device=device, operations=operations)
+            for _ in range(num_double_stream_layers)
+        ])
+
+        self.single_stream_layers = nn.ModuleList([
+            OmniGen2TransformerBlock(hidden_size, num_attention_heads, num_kv_heads, multiple_of, ffn_dim_multiplier, norm_eps, modulation=True, dtype=dtype, device=device, operations=operations)
+            for _ in range(num_layers)
+        ])
+
+        self.norm_out = LuminaLayerNormContinuous(
+            embedding_dim=hidden_size,
+            conditioning_embedding_dim=min(hidden_size, 1024),
+            elementwise_affine=False,
+            eps=1e-6,
+            out_dim=patch_size * patch_size * self.out_channels, dtype=dtype, device=device, operations=operations
+        )
+
+        self.image_index_embedding = nn.Parameter(torch.empty(5, hidden_size, device=device, dtype=dtype))
+
+    # Patchify/refine helpers are identical to OmniGen2; reuse via bound methods.
+    flat_and_pad_to_seq = comfy.ldm.omnigen.omnigen2.OmniGen2Transformer2DModel.flat_and_pad_to_seq
+    img_patch_embed_and_refine = comfy.ldm.omnigen.omnigen2.OmniGen2Transformer2DModel.img_patch_embed_and_refine
+
+    def forward(self, x, timesteps, context, num_tokens, ref_latents=None, attention_mask=None, transformer_options={}, **kwargs):
+        B, C, H, W = x.shape
+        hidden_states = comfy.ldm.common_dit.pad_to_patch_size(x, (self.patch_size, self.patch_size))
+        _, _, H_padded, W_padded = hidden_states.shape
+        timestep = 1.0 - timesteps
+        text_hidden_states = context
+        text_attention_mask = attention_mask
+        ref_image_hidden_states = ref_latents
+        device = hidden_states.device
+
+        temb, text_hidden_states = self.time_caption_embed(timestep, text_hidden_states, hidden_states[0].dtype)
+
+        (
+            hidden_states, ref_image_hidden_states,
+            img_mask, ref_img_mask,
+            l_effective_ref_img_len, l_effective_img_len,
+            ref_img_sizes, img_sizes,
+        ) = self.flat_and_pad_to_seq(hidden_states, ref_image_hidden_states)
+
+        (
+            context_rotary_emb, ref_img_rotary_emb, noise_rotary_emb,
+            rotary_emb, encoder_seq_lengths, seq_lengths,
+        ) = self.rope_embedder(
+            hidden_states.shape[0], text_hidden_states.shape[1], [num_tokens] * text_hidden_states.shape[0],
+            l_effective_ref_img_len, l_effective_img_len,
+            ref_img_sizes, img_sizes, device,
+        )
+
+        for layer in self.context_refiner:
+            text_hidden_states = layer(text_hidden_states, text_attention_mask, context_rotary_emb, transformer_options=transformer_options)
+
+        img_len = hidden_states.shape[1]
+        combined_img_hidden_states = self.img_patch_embed_and_refine(
+            hidden_states, ref_image_hidden_states,
+            img_mask, ref_img_mask,
+            noise_rotary_emb, ref_img_rotary_emb,
+            l_effective_ref_img_len, l_effective_img_len,
+            temb,
+            transformer_options=transformer_options,
+        )
+
+        # Double-stream stage: the image self-attention only sees the [ref ; noise] tokens,
+        # which sit after the instruction tokens in the joint rope.
+        L_instruct = text_hidden_states.shape[1]
+        combined_img_rotary_emb = rotary_emb[:, L_instruct:]
+        for layer in self.double_stream_layers:
+            combined_img_hidden_states, text_hidden_states = layer(
+                combined_img_hidden_states, text_hidden_states,
+                rotary_emb, combined_img_rotary_emb, temb,
+                joint_attention_mask=None, img_attention_mask=None,
+                transformer_options=transformer_options,
+            )
+
+        hidden_states = torch.cat([text_hidden_states, combined_img_hidden_states], dim=1)
+
+        for layer in self.single_stream_layers:
+            hidden_states = layer(hidden_states, None, rotary_emb, temb, transformer_options=transformer_options)
+
+        hidden_states = self.norm_out(hidden_states, temb)
+
+        p = self.patch_size
+        output = rearrange(hidden_states[:, -img_len:], 'b (h w) (p1 p2 c) -> b c (h p1) (w p2)', h=H_padded // p, w=W_padded // p, p1=p, p2=p)[:, :, :H, :W]
+
+        return -output

comfy/ldm/chroma_radiance/model.py

@@ -38,6 +38,8 @@ class ChromaRadianceParams(ChromaParams):
     # None means use the same dtype as the model.
     nerf_embedder_dtype: Optional[torch.dtype]
     use_x0: bool
+    # Use sequential txt_ids instead of zeros
+    use_sequential_txt_ids: bool
 
 class ChromaRadiance(Chroma):
     """
@@ -162,6 +164,9 @@ class ChromaRadiance(Chroma):
         if params.use_x0:
             self.register_buffer("__x0__", torch.tensor([]))
 
+        if params.use_sequential_txt_ids:
+            self.register_buffer("__sequential__", torch.tensor([]))
+
     @property
     def _nerf_final_layer(self) -> nn.Module:
         if self.params.nerf_final_head_type == "linear":
@@ -313,6 +318,9 @@ class ChromaRadiance(Chroma):
         img_ids[:, :, 2] = img_ids[:, :, 2] + torch.linspace(0, w_len - 1, steps=w_len, device=x.device, dtype=x.dtype).unsqueeze(0)
         img_ids = repeat(img_ids, "h w c -> b (h w) c", b=bs)
         txt_ids = torch.zeros((bs, context.shape[1], 3), device=x.device, dtype=x.dtype)
+        # Radiance after 2026-05-22 uses sequential txt_ids instead of zeros
+        if params.use_sequential_txt_ids:
+            txt_ids[:, :, 0] = torch.arange(context.shape[1], device=x.device, dtype=x.dtype).unsqueeze(0).expand(bs, -1)
 
         img_out = self.forward_orig(
             img,

comfy/ldm/colormap.py

@@ -0,0 +1,25 @@
+"""Colormap utilities for depth and geometry visualisation."""
+
+from __future__ import annotations
+
+import torch
+
+
+def turbo(x: torch.Tensor) -> torch.Tensor:
+    """Anton Mikhailov polynomial approximation of the Turbo colormap.
+
+    Args:
+        x: Float tensor with values in [0, 1].
+
+    Returns:
+        RGB tensor of the same shape as ``x`` with a trailing size-3 dimension.
+    """
+    x = x.clamp(0.0, 1.0)
+    x2 = x * x
+    x3 = x2 * x
+    x4 = x2 * x2
+    x5 = x4 * x
+    r = 0.13572138 + 4.61539260*x - 42.66032258*x2 + 132.13108234*x3 - 152.94239396*x4 + 59.28637943*x5
+    g = 0.09140261 + 2.19418839*x + 4.84296658*x2 - 14.18503333*x3 +   4.27729857*x4 +  2.82956604*x5
+    b = 0.10667330 + 12.64194608*x - 60.58204836*x2 + 110.36276771*x3 - 89.90310912*x4 + 27.34824973*x5
+    return torch.stack([r, g, b], dim=-1).clamp(0.0, 1.0)

comfy/ldm/cosmos/predict2.py

@@ -515,7 +515,7 @@ class Block(nn.Module):
             h=H,
             w=W,
         )
-        x_B_T_H_W_D = x_B_T_H_W_D + gate_self_attn_B_T_1_1_D.to(residual_dtype) * result_B_T_H_W_D.to(residual_dtype)
+        x_B_T_H_W_D = torch.addcmul(x_B_T_H_W_D, gate_self_attn_B_T_1_1_D.to(residual_dtype), result_B_T_H_W_D.to(residual_dtype))
 
         def _x_fn(
             _x_B_T_H_W_D: torch.Tensor,
@@ -548,7 +548,7 @@ class Block(nn.Module):
             shift_cross_attn_B_T_1_1_D,
             transformer_options=transformer_options,
         )
-        x_B_T_H_W_D = result_B_T_H_W_D.to(residual_dtype) * gate_cross_attn_B_T_1_1_D.to(residual_dtype) + x_B_T_H_W_D
+        x_B_T_H_W_D = torch.addcmul(x_B_T_H_W_D, gate_cross_attn_B_T_1_1_D.to(residual_dtype), result_B_T_H_W_D.to(residual_dtype))
 
         normalized_x_B_T_H_W_D = _fn(
             x_B_T_H_W_D,
@@ -557,7 +557,7 @@ class Block(nn.Module):
             shift_mlp_B_T_1_1_D,
         )
         result_B_T_H_W_D = self.mlp(normalized_x_B_T_H_W_D.to(compute_dtype))
-        x_B_T_H_W_D = x_B_T_H_W_D + gate_mlp_B_T_1_1_D.to(residual_dtype) * result_B_T_H_W_D.to(residual_dtype)
+        x_B_T_H_W_D = torch.addcmul(x_B_T_H_W_D, gate_mlp_B_T_1_1_D.to(residual_dtype), result_B_T_H_W_D.to(residual_dtype))
         return x_B_T_H_W_D
 
 

comfy/ldm/depth_anything_3/camera.py

@@ -0,0 +1,177 @@
+"""Camera-token encoder and decoder for Depth Anything 3."""
+
+from __future__ import annotations
+
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+
+from comfy.ldm.modules.attention import optimized_attention_for_device
+from .transform import affine_inverse, extri_intri_to_pose_encoding
+
+
+# -----------------------------------------------------------------------
+# Building blocks (mirror depth_anything_3.model.utils.{attention,block})
+# -----------------------------------------------------------------------
+
+
+class _Mlp(nn.Module):
+    """Standard 2-layer MLP with GELU. Matches upstream ``utils.attention.Mlp``."""
+
+    def __init__(self, in_features, hidden_features=None, out_features=None, *, device=None, dtype=None, operations=None):
+        super().__init__()
+        out_features = out_features or in_features
+        hidden_features = hidden_features or in_features
+        self.fc1 = operations.Linear(in_features, hidden_features, bias=True, device=device, dtype=dtype)
+        self.fc2 = operations.Linear(hidden_features, out_features, bias=True, device=device, dtype=dtype)
+
+    def forward(self, x):
+        return self.fc2(F.gelu(self.fc1(x)))
+
+
+class _LayerScale(nn.Module):
+    """Per-channel learnable scaling. Matches upstream LayerScale."""
+
+    def __init__(self, dim, *, device=None, dtype=None):
+        super().__init__()
+        self.gamma = nn.Parameter(torch.empty(dim, device=device, dtype=dtype))
+
+    def forward(self, x):
+        return x * self.gamma.to(dtype=x.dtype, device=x.device)
+
+
+class _Attention(nn.Module):
+    """ Self-attention with fused QKV projection. Mirrors upstream utils.attention.Attention;
+    Layout matches the HF safetensors (attn.qkv.{weight,bias} and attn.proj.{weight,bias})."""
+
+    def __init__(self, dim, num_heads, *, device=None, dtype=None, operations=None):
+        super().__init__()
+        assert dim % num_heads == 0
+        self.num_heads = num_heads
+        self.head_dim = dim // num_heads
+        self.qkv = operations.Linear(dim, dim * 3, bias=True, device=device, dtype=dtype)
+        self.proj = operations.Linear(dim, dim, bias=True, device=device, dtype=dtype)
+
+    def forward(self, x):
+        B, N, C = x.shape
+        qkv = self.qkv(x).reshape(B, N, 3, C)
+        q, k, v = qkv.unbind(2)                      # each (B, N, C)
+        attn_fn = optimized_attention_for_device(x.device, small_input=True)
+        out = attn_fn(q, k, v, heads=self.num_heads)
+        return self.proj(out)
+
+
+class _Block(nn.Module):
+    """Pre-norm transformer block with LayerScale. Used by :class:CameraEnc. Layout follows upstream utils.block.Block."""
+
+    def __init__(self, dim, num_heads, mlp_ratio=4, init_values=0.01, *, device=None, dtype=None, operations=None):
+        super().__init__()
+        self.norm1 = operations.LayerNorm(dim, device=device, dtype=dtype)
+        self.attn = _Attention(dim, num_heads, device=device, dtype=dtype, operations=operations)
+        self.ls1 = _LayerScale(dim, device=device, dtype=dtype) if init_values else nn.Identity()
+        self.norm2 = operations.LayerNorm(dim, device=device, dtype=dtype)
+        self.mlp = _Mlp(in_features=dim, hidden_features=int(dim * mlp_ratio), device=device, dtype=dtype, operations=operations)
+        self.ls2 = _LayerScale(dim, device=device, dtype=dtype) if init_values else nn.Identity()
+
+    def forward(self, x):
+        x = x + self.ls1(self.attn(self.norm1(x)))
+        x = x + self.ls2(self.mlp(self.norm2(x)))
+        return x
+
+
+class CameraEnc(nn.Module):
+    """Encode per-view (extrinsics, intrinsics) into a camera token.
+
+    Maps a 9-D pose-encoding vector through a small MLP up to the backbone's
+    ``embed_dim``, then runs ``trunk_depth`` transformer blocks. The output
+    has shape ``(B, S, embed_dim)`` and is injected at block ``alt_start``
+    of the DINOv2 backbone in place of the cls token.
+
+    Parameters mirror the upstream ``cam_enc.py`` so HF weights load directly.
+    """
+
+    def __init__(
+        self,
+        dim_out: int = 1024,
+        dim_in: int = 9,
+        trunk_depth: int = 4,
+        target_dim: int = 9,
+        num_heads: int = 16,
+        mlp_ratio: int = 4,
+        init_values: float = 0.01,
+        *,
+        device=None, dtype=None, operations=None,
+        **_kwargs,
+    ):
+        super().__init__()
+        self.target_dim = target_dim
+        self.trunk_depth = trunk_depth
+        self.trunk = nn.Sequential(*[
+            _Block(dim_out, num_heads=num_heads, mlp_ratio=mlp_ratio,
+                   init_values=init_values,
+                   device=device, dtype=dtype, operations=operations)
+            for _ in range(trunk_depth)
+        ])
+        self.token_norm = operations.LayerNorm(dim_out, device=device, dtype=dtype)
+        self.trunk_norm = operations.LayerNorm(dim_out, device=device, dtype=dtype)
+        self.pose_branch = _Mlp(
+            in_features=dim_in,
+            hidden_features=dim_out // 2,
+            out_features=dim_out,
+            device=device, dtype=dtype, operations=operations,
+        )
+
+    def forward(self, extrinsics: torch.Tensor, intrinsics: torch.Tensor,
+                image_size_hw) -> torch.Tensor:
+        """Encode camera parameters into ``(B, S, dim_out)`` tokens."""
+        c2ws = affine_inverse(extrinsics)
+        pose_encoding = extri_intri_to_pose_encoding(c2ws, intrinsics, image_size_hw)
+        tokens = self.pose_branch(pose_encoding.to(self.pose_branch.fc1.weight.dtype))
+        tokens = self.token_norm(tokens)
+        tokens = self.trunk(tokens)
+        tokens = self.trunk_norm(tokens)
+        return tokens
+
+
+class CameraDec(nn.Module):
+    """Decode the final cam token into a 9-D pose encoding.
+
+    Output layout: ``[T(3), quat_xyzw(4), fov_h, fov_w]``. The translation is
+    always predicted by the network; the quaternion and FoV can either be
+    predicted or supplied via ``camera_encoding`` (used at training time
+    when GT cameras are available -- not exercised at inference here).
+
+    Parameters mirror the upstream ``cam_dec.py`` so HF weights load directly.
+    """
+
+    def __init__(self, dim_in: int = 1536,
+                 *, device=None, dtype=None, operations=None, **_kwargs):
+        super().__init__()
+        d = dim_in
+        self.backbone = nn.Sequential(
+            operations.Linear(d, d, device=device, dtype=dtype),
+            nn.ReLU(),
+            operations.Linear(d, d, device=device, dtype=dtype),
+            nn.ReLU(),
+        )
+        self.fc_t = operations.Linear(d, 3, device=device, dtype=dtype)
+        self.fc_qvec = operations.Linear(d, 4, device=device, dtype=dtype)
+        self.fc_fov = nn.Sequential(
+            operations.Linear(d, 2, device=device, dtype=dtype),
+            nn.ReLU(),
+        )
+
+    def forward(self, feat: torch.Tensor,
+                camera_encoding: "torch.Tensor | None" = None) -> torch.Tensor:
+        """Decode ``(B, N, dim_in)`` cam tokens into ``(B, N, 9)`` pose enc."""
+        B, N = feat.shape[:2]
+        feat = feat.reshape(B * N, -1)
+        feat = self.backbone(feat)
+        out_t = self.fc_t(feat.float()).reshape(B, N, 3)
+        if camera_encoding is None:
+            out_qvec = self.fc_qvec(feat.float()).reshape(B, N, 4)
+            out_fov = self.fc_fov(feat.float()).reshape(B, N, 2)
+        else:
+            out_qvec = camera_encoding[..., 3:7]
+            out_fov = camera_encoding[..., -2:]
+        return torch.cat([out_t, out_qvec, out_fov], dim=-1)

comfy/ldm/depth_anything_3/dpt.py

@@ -0,0 +1,489 @@
+"""DPT / DualDPT heads for Depth Anything 3."""
+
+from __future__ import annotations
+
+from typing import List, Optional, Sequence, Tuple
+
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+
+
+class Permute(nn.Module):
+    def __init__(self, dims: Tuple[int, ...]):
+        super().__init__()
+        self.dims = dims
+
+    def forward(self, x: torch.Tensor) -> torch.Tensor:
+        return x.permute(*self.dims)
+
+
+def _custom_interpolate(
+    x: torch.Tensor,
+    size: Optional[Tuple[int, int]] = None,
+    scale_factor: Optional[float] = None,
+    mode: str = "bilinear",
+    align_corners: bool = True,
+) -> torch.Tensor:
+    if size is None:
+        assert scale_factor is not None
+        size = (int(x.shape[-2] * scale_factor), int(x.shape[-1] * scale_factor))
+    INT_MAX = 1610612736
+    total = size[0] * size[1] * x.shape[0] * x.shape[1]
+    if total > INT_MAX:
+        chunks = torch.chunk(x, chunks=(total // INT_MAX) + 1, dim=0)
+        outs = [F.interpolate(c, size=size, mode=mode, align_corners=align_corners) for c in chunks]
+        return torch.cat(outs, dim=0).contiguous()
+    return F.interpolate(x, size=size, mode=mode, align_corners=align_corners)
+
+
+def _create_uv_grid(width: int, height: int, aspect_ratio: float, dtype, device) -> torch.Tensor:
+    """Normalised UV grid spanning (-x_span, -y_span)..(x_span, y_span)."""
+    diag_factor = (aspect_ratio ** 2 + 1.0) ** 0.5
+    span_x = aspect_ratio / diag_factor
+    span_y = 1.0 / diag_factor
+    left_x = -span_x * (width - 1) / width
+    right_x = span_x * (width - 1) / width
+    top_y = -span_y * (height - 1) / height
+    bottom_y = span_y * (height - 1) / height
+    x_coords = torch.linspace(left_x, right_x, steps=width, dtype=dtype, device=device)
+    y_coords = torch.linspace(top_y, bottom_y, steps=height, dtype=dtype, device=device)
+    uu, vv = torch.meshgrid(x_coords, y_coords, indexing="xy")
+    return torch.stack((uu, vv), dim=-1)  # (H, W, 2)
+
+
+def _make_sincos_pos_embed(embed_dim: int, pos: torch.Tensor, omega_0: float = 100.0) -> torch.Tensor:
+    omega = torch.arange(embed_dim // 2, dtype=torch.float32, device=pos.device)
+    omega = 1.0 / omega_0 ** (omega / (embed_dim / 2.0))
+    pos = pos.reshape(-1)
+    out = torch.einsum("m,d->md", pos, omega)
+    return torch.cat([out.sin(), out.cos()], dim=1).float()
+
+
+def _position_grid_to_embed(pos_grid: torch.Tensor, embed_dim: int, omega_0: float = 100.0) -> torch.Tensor:
+    H, W, _ = pos_grid.shape
+    pos_flat = pos_grid.reshape(-1, 2)
+    emb_x = _make_sincos_pos_embed(embed_dim // 2, pos_flat[:, 0], omega_0=omega_0)
+    emb_y = _make_sincos_pos_embed(embed_dim // 2, pos_flat[:, 1], omega_0=omega_0)
+    emb = torch.cat([emb_x, emb_y], dim=-1)
+    return emb.view(H, W, embed_dim)
+
+
+def _add_pos_embed(x: torch.Tensor, W: int, H: int, ratio: float = 0.1) -> torch.Tensor:
+    """Stateless UV positional embedding added to a feature map (B, C, h, w)."""
+    pw, ph = x.shape[-1], x.shape[-2]
+    pe = _create_uv_grid(pw, ph, aspect_ratio=W / H, dtype=x.dtype, device=x.device)
+    pe = _position_grid_to_embed(pe, x.shape[1]) * ratio
+    pe = pe.permute(2, 0, 1)[None].expand(x.shape[0], -1, -1, -1).to(dtype=x.dtype)
+    return x + pe
+
+
+def _apply_activation(x: torch.Tensor, activation: str) -> torch.Tensor:
+    act = (activation or "linear").lower()
+    if act == "exp":
+        return torch.exp(x)
+    if act == "expp1":
+        return torch.exp(x) + 1
+    if act == "expm1":
+        return torch.expm1(x)
+    if act == "relu":
+        return torch.relu(x)
+    if act == "sigmoid":
+        return torch.sigmoid(x)
+    if act == "softplus":
+        return F.softplus(x)
+    if act == "tanh":
+        return torch.tanh(x)
+    return x
+
+
+# -----------------------------------------------------------------------------
+# Fusion building blocks
+# -----------------------------------------------------------------------------
+
+
+class ResidualConvUnit(nn.Module):
+    def __init__(self, features: int, device=None, dtype=None, operations=None):
+        super().__init__()
+        self.conv1 = operations.Conv2d(features, features, 3, 1, 1, bias=True, device=device, dtype=dtype)
+        self.conv2 = operations.Conv2d(features, features, 3, 1, 1, bias=True, device=device, dtype=dtype)
+        self.activation = nn.ReLU(inplace=False)
+
+    def forward(self, x: torch.Tensor) -> torch.Tensor:
+        out = self.activation(x)
+        out = self.conv1(out)
+        out = self.activation(out)
+        out = self.conv2(out)
+        return out + x
+
+
+class FeatureFusionBlock(nn.Module):
+    def __init__(self, features: int, has_residual: bool = True, align_corners: bool = True, device=None, dtype=None, operations=None):
+        super().__init__()
+        self.align_corners = align_corners
+        self.has_residual = has_residual
+        if has_residual:
+            self.resConfUnit1 = ResidualConvUnit(features, device=device, dtype=dtype, operations=operations)
+        else:
+            self.resConfUnit1 = None
+        self.resConfUnit2 = ResidualConvUnit(features, device=device, dtype=dtype, operations=operations)
+        self.out_conv = operations.Conv2d(features, features, 1, 1, 0, bias=True, device=device, dtype=dtype)
+
+    def forward(self, *xs: torch.Tensor, size: Optional[Tuple[int, int]] = None) -> torch.Tensor:
+        y = xs[0]
+        if self.has_residual and len(xs) > 1 and self.resConfUnit1 is not None:
+            y = y + self.resConfUnit1(xs[1])
+        y = self.resConfUnit2(y)
+        if size is None:
+            up_kwargs = {"scale_factor": 2.0}
+        else:
+            up_kwargs = {"size": size}
+        y = _custom_interpolate(y, **up_kwargs, mode="bilinear", align_corners=self.align_corners)
+        y = self.out_conv(y)
+        return y
+
+
+class _Scratch(nn.Module):
+    """Container that mirrors upstream ``scratch`` attribute layout."""
+
+
+def _make_scratch(in_shape: List[int], out_shape: int, device=None, dtype=None, operations=None) -> _Scratch:
+    scratch = _Scratch()
+    scratch.layer1_rn = operations.Conv2d(in_shape[0], out_shape, 3, 1, 1, bias=False, device=device, dtype=dtype)
+    scratch.layer2_rn = operations.Conv2d(in_shape[1], out_shape, 3, 1, 1, bias=False, device=device, dtype=dtype)
+    scratch.layer3_rn = operations.Conv2d(in_shape[2], out_shape, 3, 1, 1, bias=False, device=device, dtype=dtype)
+    scratch.layer4_rn = operations.Conv2d(in_shape[3], out_shape, 3, 1, 1, bias=False, device=device, dtype=dtype)
+    return scratch
+
+
+def _make_fusion_block(features: int, has_residual: bool = True, device=None, dtype=None, operations=None) -> FeatureFusionBlock:
+    return FeatureFusionBlock(features, has_residual=has_residual, align_corners=True, device=device, dtype=dtype, operations=operations)
+
+
+# -----------------------------------------------------------------------------
+# DPT (single head + optional sky head) -- used by DA3Mono/Metric
+# -----------------------------------------------------------------------------
+
+
+class DPT(nn.Module):
+    """Single-head DPT used by DA3Mono-Large and DA3Metric-Large."""
+
+    def __init__(
+        self,
+        dim_in: int,
+        patch_size: int = 14,
+        output_dim: int = 1,
+        activation: str = "exp",
+        conf_activation: str = "expp1",
+        features: int = 256,
+        out_channels: Sequence[int] = (256, 512, 1024, 1024),
+        pos_embed: bool = False,
+        down_ratio: int = 1,
+        head_name: str = "depth",
+        use_sky_head: bool = True,
+        sky_name: str = "sky",
+        sky_activation: str = "relu",
+        norm_type: str = "idt",
+        device=None, dtype=None, operations=None,
+    ):
+        super().__init__()
+        self.patch_size = patch_size
+        self.activation = activation
+        self.conf_activation = conf_activation
+        self.pos_embed = pos_embed
+        self.down_ratio = down_ratio
+        self.head_main = head_name
+        self.sky_name = sky_name
+        self.out_dim = output_dim
+        self.has_conf = output_dim > 1
+        self.use_sky_head = use_sky_head
+        self.sky_activation = sky_activation
+        self.intermediate_layer_idx: Tuple[int, int, int, int] = (0, 1, 2, 3)
+
+        if norm_type == "layer":
+            self.norm = operations.LayerNorm(dim_in, device=device, dtype=dtype)
+        else:
+            self.norm = nn.Identity()
+
+        out_channels = list(out_channels)
+        self.projects = nn.ModuleList([
+            operations.Conv2d(dim_in, oc, kernel_size=1, stride=1, padding=0, device=device, dtype=dtype)
+            for oc in out_channels
+        ])
+        self.resize_layers = nn.ModuleList([
+            operations.ConvTranspose2d(out_channels[0], out_channels[0], kernel_size=4, stride=4, padding=0, device=device, dtype=dtype),
+            operations.ConvTranspose2d(out_channels[1], out_channels[1], kernel_size=2, stride=2, padding=0, device=device, dtype=dtype),
+            nn.Identity(),
+            operations.Conv2d(out_channels[3], out_channels[3], kernel_size=3, stride=2, padding=1, device=device, dtype=dtype),
+        ])
+
+        self.scratch = _make_scratch(out_channels, features, device=device, dtype=dtype, operations=operations)
+        self.scratch.refinenet1 = _make_fusion_block(features, device=device, dtype=dtype, operations=operations)
+        self.scratch.refinenet2 = _make_fusion_block(features, device=device, dtype=dtype, operations=operations)
+        self.scratch.refinenet3 = _make_fusion_block(features, device=device, dtype=dtype, operations=operations)
+        self.scratch.refinenet4 = _make_fusion_block(features, has_residual=False, device=device, dtype=dtype, operations=operations)
+
+        head_features_1 = features
+        head_features_2 = 32
+        self.scratch.output_conv1 = operations.Conv2d(
+            head_features_1, head_features_1 // 2, kernel_size=3, stride=1, padding=1,
+            device=device, dtype=dtype,
+        )
+        self.scratch.output_conv2 = nn.Sequential(
+            operations.Conv2d(head_features_1 // 2, head_features_2, kernel_size=3, stride=1, padding=1, device=device, dtype=dtype),
+            nn.ReLU(inplace=False),
+            operations.Conv2d(head_features_2, output_dim, kernel_size=1, stride=1, padding=0, device=device, dtype=dtype),
+        )
+
+        if self.use_sky_head:
+            self.scratch.sky_output_conv2 = nn.Sequential(
+                operations.Conv2d(head_features_1 // 2, head_features_2, kernel_size=3, stride=1, padding=1, device=device, dtype=dtype),
+                nn.ReLU(inplace=False),
+                operations.Conv2d(head_features_2, 1, kernel_size=1, stride=1, padding=0, device=device, dtype=dtype),
+            )
+
+    def forward(self, feats: List[torch.Tensor], H: int, W: int, patch_start_idx: int = 0, **_kwargs) -> dict:
+        # feats[i][0] is the patch-token tensor with shape (B, S, N_patch, C)
+        B, S, N, C = feats[0][0].shape
+        feats_flat = [feat[0].reshape(B * S, N, C) for feat in feats]
+
+        ph, pw = H // self.patch_size, W // self.patch_size
+        resized = []
+        for stage_idx, take_idx in enumerate(self.intermediate_layer_idx):
+            x = feats_flat[take_idx][:, patch_start_idx:]
+            x = self.norm(x)
+            x = x.permute(0, 2, 1).contiguous().reshape(B * S, C, ph, pw)
+            x = self.projects[stage_idx](x)
+            if self.pos_embed:
+                x = _add_pos_embed(x, W, H)
+            x = self.resize_layers[stage_idx](x)
+            resized.append(x)
+
+        l1_rn = self.scratch.layer1_rn(resized[0])
+        l2_rn = self.scratch.layer2_rn(resized[1])
+        l3_rn = self.scratch.layer3_rn(resized[2])
+        l4_rn = self.scratch.layer4_rn(resized[3])
+
+        out = self.scratch.refinenet4(l4_rn, size=l3_rn.shape[2:])
+        out = self.scratch.refinenet3(out, l3_rn, size=l2_rn.shape[2:])
+        out = self.scratch.refinenet2(out, l2_rn, size=l1_rn.shape[2:])
+        out = self.scratch.refinenet1(out, l1_rn)
+
+        h_out = int(ph * self.patch_size / self.down_ratio)
+        w_out = int(pw * self.patch_size / self.down_ratio)
+
+        fused = self.scratch.output_conv1(out)
+        fused = _custom_interpolate(fused, (h_out, w_out), mode="bilinear", align_corners=True)
+        if self.pos_embed:
+            fused = _add_pos_embed(fused, W, H)
+        feat = fused
+
+        main_logits = self.scratch.output_conv2(feat)
+        outs = {}
+        if self.has_conf:
+            fmap = main_logits.permute(0, 2, 3, 1)
+            pred = _apply_activation(fmap[..., :-1], self.activation)
+            conf = _apply_activation(fmap[..., -1], self.conf_activation)
+            outs[self.head_main] = pred.squeeze(-1).view(B, S, *pred.shape[1:-1])
+            outs[f"{self.head_main}_conf"] = conf.view(B, S, *conf.shape[1:])
+        else:
+            pred = _apply_activation(main_logits, self.activation)
+            outs[self.head_main] = pred.squeeze(1).view(B, S, *pred.shape[2:])
+
+        if self.use_sky_head:
+            sky_logits = self.scratch.sky_output_conv2(feat)
+            if self.sky_activation.lower() == "sigmoid":
+                sky = torch.sigmoid(sky_logits)
+            elif self.sky_activation.lower() == "relu":
+                sky = F.relu(sky_logits)
+            else:
+                sky = sky_logits
+            outs[self.sky_name] = sky.squeeze(1).view(B, S, *sky.shape[2:])
+
+        return outs
+
+
+# -----------------------------------------------------------------------------
+# DualDPT (depth + auxiliary "ray" head) -- used by DA3-Small / DA3-Base
+# -----------------------------------------------------------------------------
+
+
+class DualDPT(nn.Module):
+    """Two-head DPT used by DA3-Small / DA3-Base."""
+
+    def __init__(
+        self,
+        dim_in: int,
+        patch_size: int = 14,
+        output_dim: int = 2,
+        activation: str = "exp",
+        conf_activation: str = "expp1",
+        features: int = 256,
+        out_channels: Sequence[int] = (256, 512, 1024, 1024),
+        pos_embed: bool = True,
+        down_ratio: int = 1,
+        aux_pyramid_levels: int = 4,
+        aux_out1_conv_num: int = 5,
+        head_names: Tuple[str, str] = ("depth", "ray"),
+        device=None, dtype=None, operations=None,
+    ):
+        super().__init__()
+        self.patch_size = patch_size
+        self.activation = activation
+        self.conf_activation = conf_activation
+        self.pos_embed = pos_embed
+        self.down_ratio = down_ratio
+        self.aux_levels = aux_pyramid_levels
+        self.aux_out1_conv_num = aux_out1_conv_num
+        self.head_main, self.head_aux = head_names
+        self.intermediate_layer_idx: Tuple[int, int, int, int] = (0, 1, 2, 3)
+        # Toggle the auxiliary ray branch at runtime. Default off (mono path).
+        # DepthAnything3Net flips this on when running multi-view + ray-pose.
+        self.enable_aux: bool = False
+
+        self.norm = operations.LayerNorm(dim_in, device=device, dtype=dtype)
+        out_channels = list(out_channels)
+        self.projects = nn.ModuleList([
+            operations.Conv2d(dim_in, oc, kernel_size=1, stride=1, padding=0, device=device, dtype=dtype)
+            for oc in out_channels
+        ])
+        self.resize_layers = nn.ModuleList([
+            operations.ConvTranspose2d(out_channels[0], out_channels[0], kernel_size=4, stride=4, padding=0, device=device, dtype=dtype),
+            operations.ConvTranspose2d(out_channels[1], out_channels[1], kernel_size=2, stride=2, padding=0, device=device, dtype=dtype),
+            nn.Identity(),
+            operations.Conv2d(out_channels[3], out_channels[3], kernel_size=3, stride=2, padding=1, device=device, dtype=dtype),
+        ])
+
+        self.scratch = _make_scratch(out_channels, features, device=device, dtype=dtype, operations=operations)
+        # Main fusion chain
+        self.scratch.refinenet1 = _make_fusion_block(features, device=device, dtype=dtype, operations=operations)
+        self.scratch.refinenet2 = _make_fusion_block(features, device=device, dtype=dtype, operations=operations)
+        self.scratch.refinenet3 = _make_fusion_block(features, device=device, dtype=dtype, operations=operations)
+        self.scratch.refinenet4 = _make_fusion_block(features, has_residual=False, device=device, dtype=dtype, operations=operations)
+        # Auxiliary fusion chain (separate copies)
+        self.scratch.refinenet1_aux = _make_fusion_block(features, device=device, dtype=dtype, operations=operations)
+        self.scratch.refinenet2_aux = _make_fusion_block(features, device=device, dtype=dtype, operations=operations)
+        self.scratch.refinenet3_aux = _make_fusion_block(features, device=device, dtype=dtype, operations=operations)
+        self.scratch.refinenet4_aux = _make_fusion_block(features, has_residual=False, device=device, dtype=dtype, operations=operations)
+
+        head_features_1 = features
+        head_features_2 = 32
+
+        # Main head neck + final projection
+        self.scratch.output_conv1 = operations.Conv2d(
+            head_features_1, head_features_1 // 2, kernel_size=3, stride=1, padding=1,
+            device=device, dtype=dtype,
+        )
+        self.scratch.output_conv2 = nn.Sequential(
+            operations.Conv2d(head_features_1 // 2, head_features_2, kernel_size=3, stride=1, padding=1, device=device, dtype=dtype),
+            nn.ReLU(inplace=False),
+            operations.Conv2d(head_features_2, output_dim, kernel_size=1, stride=1, padding=0, device=device, dtype=dtype),
+        )
+
+        # Aux pre-head per level (multi-level pyramid)
+        self.scratch.output_conv1_aux = nn.ModuleList([
+            self._make_aux_out1_block(head_features_1, device=device, dtype=dtype, operations=operations)
+            for _ in range(self.aux_levels)
+        ])
+
+        # Aux final projection per level (includes LayerNorm permute path).
+        ln_seq = [Permute((0, 2, 3, 1)),
+                  operations.LayerNorm(head_features_2, device=device, dtype=dtype),
+                  Permute((0, 3, 1, 2))]
+        self.scratch.output_conv2_aux = nn.ModuleList([
+            nn.Sequential(
+                operations.Conv2d(head_features_1 // 2, head_features_2, kernel_size=3, stride=1, padding=1, device=device, dtype=dtype),
+                *ln_seq,
+                nn.ReLU(inplace=False),
+                operations.Conv2d(head_features_2, 7, kernel_size=1, stride=1, padding=0, device=device, dtype=dtype),
+            )
+            for _ in range(self.aux_levels)
+        ])
+
+    @staticmethod
+    def _make_aux_out1_block(in_ch: int, *, device=None, dtype=None, operations=None) -> nn.Sequential:
+        # aux_out1_conv_num=5 in all Apache-2.0 variants.
+        return nn.Sequential(
+            operations.Conv2d(in_ch, in_ch // 2, 3, 1, 1, device=device, dtype=dtype),
+            operations.Conv2d(in_ch // 2, in_ch, 3, 1, 1, device=device, dtype=dtype),
+            operations.Conv2d(in_ch, in_ch // 2, 3, 1, 1, device=device, dtype=dtype),
+            operations.Conv2d(in_ch // 2, in_ch, 3, 1, 1, device=device, dtype=dtype),
+            operations.Conv2d(in_ch, in_ch // 2, 3, 1, 1, device=device, dtype=dtype),
+        )
+
+    def forward(self, feats: List[torch.Tensor], H: int, W: int, patch_start_idx: int = 0, **_kwargs) -> dict:
+        B, S, N, C = feats[0][0].shape
+        feats_flat = [feat[0].reshape(B * S, N, C) for feat in feats]
+
+        ph, pw = H // self.patch_size, W // self.patch_size
+        resized = []
+        for stage_idx, take_idx in enumerate(self.intermediate_layer_idx):
+            x = feats_flat[take_idx][:, patch_start_idx:]
+            x = self.norm(x)
+            x = x.permute(0, 2, 1).contiguous().reshape(B * S, C, ph, pw)
+            x = self.projects[stage_idx](x)
+            if self.pos_embed:
+                x = _add_pos_embed(x, W, H)
+            x = self.resize_layers[stage_idx](x)
+            resized.append(x)
+
+        l1_rn = self.scratch.layer1_rn(resized[0])
+        l2_rn = self.scratch.layer2_rn(resized[1])
+        l3_rn = self.scratch.layer3_rn(resized[2])
+        l4_rn = self.scratch.layer4_rn(resized[3])
+
+        # Main pyramid (output_conv1 is applied inside the upstream `_fuse`,
+        # before interpolation -- replicate that order here).
+        m = self.scratch.refinenet4(l4_rn, size=l3_rn.shape[2:])
+        if self.enable_aux:
+            a4 = self.scratch.refinenet4_aux(l4_rn, size=l3_rn.shape[2:])
+            aux_pyr = [a4]
+        m = self.scratch.refinenet3(m, l3_rn, size=l2_rn.shape[2:])
+        if self.enable_aux:
+            aux_pyr.append(self.scratch.refinenet3_aux(aux_pyr[-1], l3_rn, size=l2_rn.shape[2:]))
+        m = self.scratch.refinenet2(m, l2_rn, size=l1_rn.shape[2:])
+        if self.enable_aux:
+            aux_pyr.append(self.scratch.refinenet2_aux(aux_pyr[-1], l2_rn, size=l1_rn.shape[2:]))
+        m = self.scratch.refinenet1(m, l1_rn)
+        if self.enable_aux:
+            aux_pyr.append(self.scratch.refinenet1_aux(aux_pyr[-1], l1_rn))
+        m = self.scratch.output_conv1(m)
+
+        h_out = int(ph * self.patch_size / self.down_ratio)
+        w_out = int(pw * self.patch_size / self.down_ratio)
+
+        m = _custom_interpolate(m, (h_out, w_out), mode="bilinear", align_corners=True)
+        if self.pos_embed:
+            m = _add_pos_embed(m, W, H)
+        main_logits = self.scratch.output_conv2(m)
+        fmap = main_logits.permute(0, 2, 3, 1)
+        depth_pred = _apply_activation(fmap[..., :-1], self.activation)
+        depth_conf = _apply_activation(fmap[..., -1], self.conf_activation)
+
+        outs = {
+            self.head_main: depth_pred.squeeze(-1).view(B, S, *depth_pred.shape[1:-1]),
+            f"{self.head_main}_conf": depth_conf.view(B, S, *depth_conf.shape[1:]),
+        }
+
+        if self.enable_aux:
+            # Auxiliary "ray" head (multi-level inside) -- only the last level
+            # is returned. Mirrors upstream ``DualDPT._fuse`` + ``_forward_impl``:
+            # each aux pyramid level goes through ``output_conv1_aux[i]``
+            # (5-layer conv stack that ends at ``features // 2`` channels),
+            # then the last level optionally gets a pos-embed and finally
+            # ``output_conv2_aux[-1]``.
+            aux_processed = [
+                self.scratch.output_conv1_aux[i](a) for i, a in enumerate(aux_pyr)
+            ]
+            last_aux = aux_processed[-1]
+            if self.pos_embed:
+                last_aux = _add_pos_embed(last_aux, W, H)
+            last_aux_logits = self.scratch.output_conv2_aux[-1](last_aux)
+            fmap_last = last_aux_logits.permute(0, 2, 3, 1)
+            # Channels: [ray(6), ray_conf(1)]; ray uses 'linear' activation.
+            aux_pred = fmap_last[..., :-1]
+            aux_conf = _apply_activation(fmap_last[..., -1], self.conf_activation)
+            outs[self.head_aux] = aux_pred.view(B, S, *aux_pred.shape[1:])
+            outs[f"{self.head_aux}_conf"] = aux_conf.view(B, S, *aux_conf.shape[1:])
+
+        return outs

comfy/ldm/depth_anything_3/model.py

@@ -0,0 +1,236 @@
+from __future__ import annotations
+
+from typing import Dict, Optional, Sequence
+
+import torch
+import torch.nn as nn
+
+from comfy.image_encoders.dino2 import Dinov2Model
+
+from .camera import CameraDec, CameraEnc
+from .dpt import DPT, DualDPT
+from .ray_pose import get_extrinsic_from_camray
+from .transform import affine_inverse, pose_encoding_to_extri_intri
+
+
+_HEAD_REGISTRY = {
+    "dpt": DPT,
+    "dualdpt": DualDPT,
+}
+
+
+# Backbone presets (mirror the upstream DINOv2 ViT variants).
+_BACKBONE_PRESETS = {
+    "vits": dict(hidden_size=384,  num_hidden_layers=12, num_attention_heads=6,  use_swiglu_ffn=False),
+    "vitb": dict(hidden_size=768,  num_hidden_layers=12, num_attention_heads=12, use_swiglu_ffn=False),
+    "vitl": dict(hidden_size=1024, num_hidden_layers=24, num_attention_heads=16, use_swiglu_ffn=False),
+    "vitg": dict(hidden_size=1536, num_hidden_layers=40, num_attention_heads=24, use_swiglu_ffn=True),
+}
+
+
+def _build_backbone_config(
+    backbone_name: str,
+    *,
+    alt_start: int,
+    qknorm_start: int,
+    rope_start: int,
+    cat_token: bool,
+) -> dict:
+    if backbone_name not in _BACKBONE_PRESETS:
+        raise ValueError(f"Unknown DINOv2 backbone variant: {backbone_name!r}")
+    cfg = dict(_BACKBONE_PRESETS[backbone_name])
+    cfg.update(dict(
+        layer_norm_eps=1e-6,
+        patch_size=14,
+        image_size=518,
+        # No mask_token in DA3 weights; omit param to avoid load warnings.
+        use_mask_token=False,
+        alt_start=alt_start,
+        qknorm_start=qknorm_start,
+        rope_start=rope_start,
+        cat_token=cat_token,
+        rope_freq=100.0,
+    ))
+    return cfg
+
+
+class DepthAnything3Net(nn.Module):
+
+    PATCH_SIZE = 14
+
+    def __init__(
+        self,
+        # --- Backbone ---
+        backbone_name: str = "vitl",
+        out_layers: Sequence[int] = (4, 11, 17, 23),
+        alt_start: int = -1,
+        qknorm_start: int = -1,
+        rope_start: int = -1,
+        cat_token: bool = False,
+        # --- Head ---
+        head_type: str = "dpt",  # dpt or dualdpt
+        head_dim_in: int = 1024,
+        head_output_dim: int = 1,  # 1 = depth only, 2 = depth+conf
+        head_features: int = 256,
+        head_out_channels: Sequence[int] = (256, 512, 1024, 1024),
+        head_use_sky_head: bool = True, # ignored by DualDPT
+        head_pos_embed: Optional[bool] = None,  # default: True for DualDPT, False for DPT
+        # --- Camera (multi-view) ---
+        has_cam_enc: bool = False,
+        has_cam_dec: bool = False,
+        cam_dim_out: Optional[int] = None,  # CameraEnc dim_out (defaults to embed_dim)
+        cam_dec_dim_in: Optional[int] = None,  # CameraDec dim_in  (defaults to 2*embed_dim with cat_token)
+        # ComfyUI plumbing
+        device=None, dtype=None, operations=None,
+        **_ignored,
+    ):
+        super().__init__()
+        head_cls = _HEAD_REGISTRY[head_type.lower()]
+        self.head_type = head_type.lower()
+        self.has_sky = (self.head_type == "dpt") and head_use_sky_head
+        self.has_conf = head_output_dim > 1
+        self.out_layers = list(out_layers)
+
+        backbone_cfg = _build_backbone_config(
+            backbone_name,
+            alt_start=alt_start,
+            qknorm_start=qknorm_start,
+            rope_start=rope_start,
+            cat_token=cat_token,
+        )
+        self.backbone = Dinov2Model(backbone_cfg, dtype, device, operations)
+
+        head_kwargs = dict(
+            dim_in=head_dim_in,
+            patch_size=self.PATCH_SIZE,
+            output_dim=head_output_dim,
+            features=head_features,
+            out_channels=tuple(head_out_channels),
+            device=device, dtype=dtype, operations=operations,
+        )
+        if self.head_type == "dpt":
+            head_kwargs.update(
+                use_sky_head=head_use_sky_head,
+                pos_embed=(False if head_pos_embed is None else head_pos_embed),
+            )
+        else:  # dualdpt
+            head_kwargs.update(
+                pos_embed=(True if head_pos_embed is None else head_pos_embed),
+            )
+        self.head = head_cls(**head_kwargs)
+
+        # Built only if checkpoint has weights; cam_enc output dim == embed_dim.
+        embed_dim = backbone_cfg["hidden_size"]
+        if has_cam_enc:
+            self.cam_enc = CameraEnc(
+                dim_out=cam_dim_out if cam_dim_out is not None else embed_dim,
+                num_heads=max(1, embed_dim // 64),
+                device=device, dtype=dtype, operations=operations,
+            )
+        else:
+            self.cam_enc = None
+        if has_cam_dec:
+            default_dim = embed_dim * (2 if cat_token else 1)
+            self.cam_dec = CameraDec(
+                dim_in=cam_dec_dim_in if cam_dec_dim_in is not None else default_dim,
+                device=device, dtype=dtype, operations=operations,
+            )
+        else:
+            self.cam_dec = None
+
+        self.dtype = dtype
+
+    def forward(
+        self,
+        image: torch.Tensor,
+        extrinsics: Optional[torch.Tensor] = None,
+        intrinsics: Optional[torch.Tensor] = None,
+        *,
+        use_ray_pose: bool = False,
+        ref_view_strategy: str = "saddle_balanced",
+        export_feat_layers: Optional[Sequence[int]] = None,
+        **_unused,
+    ) -> Dict[str, torch.Tensor]:
+        """Run depth and optionally pose prediction."""
+        if image.ndim == 4:
+            image = image.unsqueeze(1)  # (B, 1, 3, H, W)
+        assert image.ndim == 5 and image.shape[2] == 3, \
+            f"image must be (B,3,H,W) or (B,S,3,H,W); got {tuple(image.shape)}"
+
+        B, S, _, H, W = image.shape
+        assert H % self.PATCH_SIZE == 0 and W % self.PATCH_SIZE == 0, \
+            f"image H,W must be multiples of {self.PATCH_SIZE}; got {(H, W)}"
+
+        # Camera-token preparation (multi-view path).
+        cam_token = None
+        if extrinsics is not None and intrinsics is not None and self.cam_enc is not None:
+            cam_token = self.cam_enc(extrinsics, intrinsics, (H, W))
+
+        # Toggle aux ray output on/off depending on what the caller asked for.
+        if isinstance(self.head, DualDPT):
+            self.head.enable_aux = bool(use_ray_pose)
+
+        feats, aux_feats = self.backbone.get_intermediate_layers_da3(
+            image, self.out_layers, cam_token=cam_token,
+            ref_view_strategy=ref_view_strategy,
+            export_feat_layers=export_feat_layers,
+        )
+        head_out = self.head(feats, H=H, W=W, patch_start_idx=0)
+
+        # Pose prediction.
+        out: Dict[str, torch.Tensor] = {}
+        if use_ray_pose and "ray" in head_out and "ray_conf" in head_out:
+            ray = head_out["ray"]
+            ray_conf = head_out["ray_conf"]
+            extr_c2w, focal, pp = get_extrinsic_from_camray(
+                ray, ray_conf, ray.shape[-3], ray.shape[-2],
+            )
+            # Match the upstream output: w2c, drop the homogeneous row.
+            extr_w2c = affine_inverse(extr_c2w)[:, :, :3, :]
+            # Build pixel-space intrinsics from the normalised focal/pp output.
+            intr = torch.eye(3, device=ray.device, dtype=ray.dtype)
+            intr = intr[None, None].expand(extr_c2w.shape[0], extr_c2w.shape[1], 3, 3).clone()
+            intr[:, :, 0, 0] = focal[:, :, 0] / 2 * W
+            intr[:, :, 1, 1] = focal[:, :, 1] / 2 * H
+            intr[:, :, 0, 2] = pp[:, :, 0] * W * 0.5
+            intr[:, :, 1, 2] = pp[:, :, 1] * H * 0.5
+            out["extrinsics"] = extr_w2c
+            out["intrinsics"] = intr
+        elif self.cam_dec is not None and S > 1:
+            # Decode the cam-token of the final out_layer into a pose encoding.
+            cam_feat = feats[-1][1]  # (B, S, dim_in_to_cam_dec)
+            pose_enc = self.cam_dec(cam_feat)
+            c2w_3x4, intr = pose_encoding_to_extri_intri(pose_enc, (H, W))
+            # Match the upstream output convention: w2c (world->camera), 3x4.
+            c2w_4x4 = torch.cat([
+                c2w_3x4,
+                torch.tensor([0, 0, 0, 1], device=c2w_3x4.device, dtype=c2w_3x4.dtype)
+                    .view(1, 1, 1, 4).expand(B, S, 1, 4),
+            ], dim=-2)
+            out["extrinsics"] = affine_inverse(c2w_4x4)[:, :, :3, :]
+            out["intrinsics"] = intr
+
+        # Flatten the views axis for per-pixel outputs (depth/conf/sky) so the
+        # per-image consumer keeps its (B*S, H, W) interface.
+        for k, v in head_out.items():
+            if k in ("ray", "ray_conf"):
+                # Keep multi-view shape for downstream pose work.
+                out[k] = v
+            elif v.ndim >= 3 and v.shape[0] == B and v.shape[1] == S:
+                out[k] = v.reshape(B * S, *v.shape[2:])
+            else:
+                out[k] = v
+
+        if export_feat_layers:
+            out["aux_features"] = self._reshape_aux_features(aux_feats, H, W)
+        return out
+
+    def _reshape_aux_features(self, aux_feats, H: int, W: int):
+        """Reshape (B, S, N, C) aux features into (B, S, h_p, w_p, C)."""
+        ph, pw = H // self.PATCH_SIZE, W // self.PATCH_SIZE
+        out = []
+        for f in aux_feats:
+            B, S, N, C = f.shape
+            assert N == ph * pw, f"aux feature seq mismatch: {N} != {ph}*{pw}"
+            out.append(f.reshape(B, S, ph, pw, C))
+        return out

comfy/ldm/depth_anything_3/preprocess.py

@@ -0,0 +1,128 @@
+"""Input/output preprocessing helpers for Depth Anything 3."""
+
+from __future__ import annotations
+
+from typing import Tuple
+
+import torch
+
+import comfy.utils
+
+PATCH_SIZE = 14
+
+# ImageNet normalization constants used during DA3 training.
+_IMAGENET_MEAN = torch.tensor([0.485, 0.456, 0.406])
+_IMAGENET_STD = torch.tensor([0.229, 0.224, 0.225])
+
+
+def _round_to_patch(x: int, patch: int = PATCH_SIZE) -> int:
+    down = (x // patch) * patch
+    up = down + patch
+    return up if abs(up - x) <= abs(x - down) else down
+
+
+def compute_target_size(orig_h: int, orig_w: int, process_res: int, method: str = "upper_bound_resize") -> Tuple[int, int]:
+    """Compute (target_h, target_w) for a single image.
+    upper_bound_resize: scale longest side to process_res, then round each dim to nearest multiple of 14 (default upstream method).
+    lower_bound_resize: scale shortest side to process_res, then round."""
+
+    if method == "upper_bound_resize":
+        longest = max(orig_h, orig_w)
+        scale = process_res / float(longest)
+    elif method == "lower_bound_resize":
+        shortest = min(orig_h, orig_w)
+        scale = process_res / float(shortest)
+    else:
+        raise ValueError(f"Unsupported process_res_method: {method}")
+
+    new_w = max(1, _round_to_patch(int(round(orig_w * scale))))
+    new_h = max(1, _round_to_patch(int(round(orig_h * scale))))
+    return new_h, new_w
+
+
+def preprocess_image(image: torch.Tensor, process_res: int = 504, method: str = "upper_bound_resize") -> torch.Tensor:
+    assert image.ndim == 4 and image.shape[-1] == 3, f"expected (B,H,W,3) IMAGE; got {tuple(image.shape)}"
+    B, H, W, _ = image.shape
+    target_h, target_w = compute_target_size(H, W, process_res, method)
+
+    # (B, H, W, 3) -> (B, 3, H, W)
+    x = image.movedim(-1, 1).contiguous()
+    if (target_h, target_w) != (H, W):
+        # Upstream uses cv2 INTER_CUBIC (upscale) / INTER_AREA (downscale).
+        # Lanczos in ``common_upscale`` is anti-aliased and produces the
+        # closest pixel-wise match in a sweep across {bilinear, bicubic,
+        # area, lanczos, bislerp}. Used in both directions for simplicity.
+        x = comfy.utils.common_upscale(x.float(), target_w, target_h, "lanczos", "disabled",)
+    x = x.clamp(0.0, 1.0)
+
+    mean = _IMAGENET_MEAN.to(device=x.device, dtype=x.dtype).view(1, 3, 1, 1)
+    std = _IMAGENET_STD.to(device=x.device, dtype=x.dtype).view(1, 3, 1, 1)
+    x = (x - mean) / std
+    return x
+
+
+# -----------------------------------------------------------------------------
+# Output post-processing (sky-aware clipping for Mono/Metric variants)
+# -----------------------------------------------------------------------------
+
+
+def compute_non_sky_mask(sky_prediction: torch.Tensor, threshold: float = 0.3) -> torch.Tensor:
+    """Boolean mask: True for non-sky pixels (sky probability < threshold)."""
+    return sky_prediction < threshold
+
+
+def apply_sky_aware_clip(depth: torch.Tensor, sky: torch.Tensor, threshold: float = 0.3, quantile: float = 0.99) -> torch.Tensor:
+    """Clips sky regions to the 99th percentile of non-sky depth. Returns a new depth tensor."""
+    non_sky = compute_non_sky_mask(sky, threshold=threshold)
+    if non_sky.sum() <= 10 or (~non_sky).sum() <= 10:
+        return depth.clone()
+
+    non_sky_depth = depth[non_sky]
+    if non_sky_depth.numel() > 100_000:
+        idx = torch.randint(0, non_sky_depth.numel(), (100_000,), device=non_sky_depth.device)
+        sampled = non_sky_depth[idx]
+    else:
+        sampled = non_sky_depth
+
+    max_depth = torch.quantile(sampled, quantile)
+    out = depth.clone()
+    out[~non_sky] = max_depth
+    return out
+
+
+def normalize_depth_v2_style(depth: torch.Tensor, sky: torch.Tensor | None = None, low_quantile: float = 0.01, high_quantile: float = 0.99) -> torch.Tensor:
+    """V2-style normalization computes percentile bounds over non-sky pixels (when available), then maps depth into [0, 1] with near = white (1.0)."""
+    if sky is not None:
+        mask = compute_non_sky_mask(sky)
+        if mask.any():
+            valid = depth[mask]
+        else:
+            valid = depth.flatten()
+    else:
+        valid = depth.flatten()
+
+    if valid.numel() > 100_000:
+        idx = torch.randint(0, valid.numel(), (100_000,), device=valid.device)
+        sample = valid[idx]
+    else:
+        sample = valid
+
+    lo = torch.quantile(sample, low_quantile)
+    hi = torch.quantile(sample, high_quantile)
+    rng = (hi - lo).clamp(min=1e-6)
+    norm = ((depth - lo) / rng).clamp(0.0, 1.0)
+    # Nearer pixels are brighter (1.0)
+    norm = 1.0 - norm
+    if sky is not None:
+        # Sky pixels become black (far / unknown)
+        sky_mask = ~compute_non_sky_mask(sky)
+        norm = torch.where(sky_mask, torch.zeros_like(norm), norm)
+    return norm
+
+
+def normalize_depth_min_max(depth: torch.Tensor) -> torch.Tensor:
+    """Simple per-frame min/max normalization with near=1.0 convention."""
+    lo = depth.amin(dim=(-2, -1), keepdim=True)
+    hi = depth.amax(dim=(-2, -1), keepdim=True)
+    rng = (hi - lo).clamp(min=1e-6)
+    return 1.0 - ((depth - lo) / rng).clamp(0.0, 1.0)

comfy/ldm/depth_anything_3/ray_pose.py

@@ -0,0 +1,272 @@
+"""Ray-to-pose conversion for the multi-view path of Depth Anything 3."""
+
+from __future__ import annotations
+
+from typing import Optional, Tuple
+
+import torch
+
+
+# qr/svd use fp32: CUDA often has no fp16/bf16 kernels for these ops.
+
+
+def _ql_decomposition(A: torch.Tensor) -> Tuple[torch.Tensor, torch.Tensor]:
+    """Decompose A = Q @ L with Q orthogonal and L lower-triangular.
+    Implemented in terms of QR by reversing the columns/rows; the standard
+    trick from the upstream reference. Inputs A are (3, 3)."""
+    P = torch.tensor([[0, 0, 1], [0, 1, 0], [1, 0, 0]], device=A.device, dtype=A.dtype)
+    A_tilde = A @ P
+    # CUDA QR is not implemented for fp16/bf16; upcast just for this call.
+    Q_tilde, R_tilde = torch.linalg.qr(A_tilde.float())
+    Q_tilde = Q_tilde.to(A.dtype)
+    R_tilde = R_tilde.to(A.dtype)
+    Q = Q_tilde @ P
+    L = P @ R_tilde @ P
+    d = torch.diag(L)
+    sign = torch.sign(d)
+    Q = Q * sign[None, :]  # scale columns of Q
+    L = L * sign[:, None]  # scale rows of L
+    return Q, L
+
+
+def _homogenize_points(points: torch.Tensor) -> torch.Tensor:
+    return torch.cat([points, torch.ones_like(points[..., :1])], dim=-1)
+
+
+# -----------------------------------------------------------------------------
+# Weighted-LSQ + RANSAC homography (batched)
+# -----------------------------------------------------------------------------
+
+
+def _find_homography_weighted_lsq(src_pts: torch.Tensor, dst_pts: torch.Tensor, confident_weight: torch.Tensor,) -> torch.Tensor:
+    """Solve a single H with weighted least-squares (DLT)."""
+    N = src_pts.shape[0]
+    if N < 4:
+        raise ValueError("At least 4 points are required to compute a homography.")
+    w = confident_weight.sqrt().unsqueeze(1)  # (N, 1)
+    x = src_pts[:, 0:1]
+    y = src_pts[:, 1:2]
+    u = dst_pts[:, 0:1]
+    v = dst_pts[:, 1:2]
+    zeros = torch.zeros_like(x)
+    A1 = torch.cat([-x * w, -y * w, -w, zeros, zeros, zeros, x * u * w, y * u * w, u * w], dim=1)
+    A2 = torch.cat([zeros, zeros, zeros, -x * w, -y * w, -w, x * v * w, y * v * w, v * w], dim=1)
+    A = torch.cat([A1, A2], dim=0)        # (2N, 9)
+    # CUDA SVD is not implemented for fp16/bf16; upcast just for this call.
+    _, _, Vh = torch.linalg.svd(A.float())
+    Vh = Vh.to(A.dtype)
+    H = Vh[-1].reshape(3, 3)
+    return H / H[-1, -1]
+
+
+def _find_homography_weighted_lsq_batched(src_pts_batch: torch.Tensor, dst_pts_batch: torch.Tensor, confident_weight_batch: torch.Tensor) -> torch.Tensor:
+    """Batched DLT solver. Inputs (B, K, 2) / (B, K); output (B, 3, 3)."""
+    B, K, _ = src_pts_batch.shape
+    w = confident_weight_batch.sqrt().unsqueeze(2)
+    x = src_pts_batch[:, :, 0:1]
+    y = src_pts_batch[:, :, 1:2]
+    u = dst_pts_batch[:, :, 0:1]
+    v = dst_pts_batch[:, :, 1:2]
+    zeros = torch.zeros_like(x)
+    A1 = torch.cat([-x * w, -y * w, -w, zeros, zeros, zeros, x * u * w, y * u * w, u * w], dim=2)
+    A2 = torch.cat([zeros, zeros, zeros, -x * w, -y * w, -w, x * v * w, y * v * w, v * w], dim=2)
+    A = torch.cat([A1, A2], dim=1)        # (B, 2K, 9)
+    # CUDA SVD is not implemented for fp16/bf16; upcast just for this call.
+    _, _, Vh = torch.linalg.svd(A.float())
+    Vh = Vh.to(A.dtype)
+    H = Vh[:, -1].reshape(B, 3, 3)
+    return H / H[:, 2:3, 2:3]
+
+
+def _ransac_find_homography_weighted_batched(
+    src_pts: torch.Tensor,                # (B, N, 2)
+    dst_pts: torch.Tensor,                # (B, N, 2)
+    confident_weight: torch.Tensor,       # (B, N)
+    n_sample: int,
+    n_iter: int = 100,
+    reproj_threshold: float = 3.0,
+    num_sample_for_ransac: int = 8,
+    max_inlier_num: int = 10000,
+    rand_sample_iters_idx: Optional[torch.Tensor] = None,
+) -> torch.Tensor:
+    """Batched weighted-RANSAC homography estimator. Returns (B, 3, 3) homography matrices."""
+    B, N, _ = src_pts.shape
+    assert N >= 4
+    device = src_pts.device
+
+    sorted_idx = torch.argsort(confident_weight, descending=True, dim=1)
+    candidate_idx = sorted_idx[:, :n_sample]                  # (B, n_sample)
+
+    if rand_sample_iters_idx is None:
+        rand_sample_iters_idx = torch.stack(
+            [torch.randperm(n_sample, device=device)[:num_sample_for_ransac]
+             for _ in range(n_iter)],
+            dim=0,
+        )
+
+    rand_idx = candidate_idx[:, rand_sample_iters_idx]        # (B, n_iter, k)
+    b_idx = (
+        torch.arange(B, device=device)
+        .view(B, 1, 1)
+        .expand(B, n_iter, num_sample_for_ransac)
+    )
+    src_b = src_pts[b_idx, rand_idx]
+    dst_b = dst_pts[b_idx, rand_idx]
+    w_b = confident_weight[b_idx, rand_idx]
+
+    cB, cN = src_b.shape[:2]
+    H_batch = _find_homography_weighted_lsq_batched(
+        src_b.flatten(0, 1), dst_b.flatten(0, 1), w_b.flatten(0, 1),
+    ).unflatten(0, (cB, cN))                                  # (B, n_iter, 3, 3)
+
+    src_homo = torch.cat([src_pts, torch.ones(B, N, 1, device=device, dtype=src_pts.dtype)], dim=2)
+    proj = torch.bmm(
+        src_homo.unsqueeze(1).expand(B, n_iter, N, 3).reshape(-1, N, 3),
+        H_batch.reshape(-1, 3, 3).transpose(1, 2),
+    )                                                          # (B*n_iter, N, 3)
+    proj_xy = (proj[:, :, :2] / proj[:, :, 2:3]).reshape(B, n_iter, N, 2)
+    err = ((proj_xy - dst_pts.unsqueeze(1)) ** 2).sum(-1).sqrt()  # (B, n_iter, N)
+    inlier_mask = err < reproj_threshold
+    score = (inlier_mask * confident_weight.unsqueeze(1)).sum(dim=2)
+    best_idx = torch.argmax(score, dim=1)
+    best_inlier_mask = inlier_mask[torch.arange(B, device=device), best_idx]
+
+    # Refit with the inlier set (per-batch, since the inlier counts vary).
+    H_inlier_list = []
+    for b in range(B):
+        mask = best_inlier_mask[b]
+        in_src = src_pts[b][mask]
+        in_dst = dst_pts[b][mask]
+        in_w = confident_weight[b][mask]
+        if in_src.shape[0] < 4:
+            # Fall back to identity when RANSAC fails to find enough inliers.
+            H_inlier_list.append(torch.eye(3, device=device, dtype=src_pts.dtype))
+            continue
+        sorted_w = torch.argsort(in_w, descending=True)
+        if len(sorted_w) > max_inlier_num:
+            keep = max(int(len(sorted_w) * 0.95), max_inlier_num)
+            sorted_w = sorted_w[:keep][torch.randperm(keep, device=device)[:max_inlier_num]]
+        H_inlier_list.append(
+            _find_homography_weighted_lsq(in_src[sorted_w], in_dst[sorted_w], in_w[sorted_w])
+        )
+    return torch.stack(H_inlier_list, dim=0)
+
+
+# -----------------------------------------------------------------------------
+# Camera-ray utilities
+# -----------------------------------------------------------------------------
+
+
+def _unproject_identity(num_y: int, num_x: int, B: int, S: int, device, dtype) -> torch.Tensor:
+    """Camera-space unit rays for an identity intrinsic on a 2x2 image plane."""
+    dx = 1.0 / num_x
+    dy = 1.0 / num_y
+    # Centered camera-space coords directly (skip the K^-1 step since it's
+    # just a translation by -1 on x and y when K is identity-with-center=1).
+    y = torch.linspace(-(1 - dy), (1 - dy), num_y, device=device, dtype=dtype)
+    x = torch.linspace(-(1 - dx), (1 - dx), num_x, device=device, dtype=dtype)
+    yy, xx = torch.meshgrid(y, x, indexing="ij")
+    grid = torch.stack((xx, yy), dim=-1)            # (h, w, 2)
+    grid = grid.unsqueeze(0).unsqueeze(0).expand(B, S, num_y, num_x, 2)
+    return torch.cat([grid, torch.ones_like(grid[..., :1])], dim=-1)
+
+
+def _camray_to_caminfo(
+    camray: torch.Tensor,  # (B, S, h, w, 6)
+    confidence: Optional[torch.Tensor] = None,  # (B, S, h, w)
+    reproj_threshold: float = 0.2,
+) -> Tuple[torch.Tensor, torch.Tensor, torch.Tensor, torch.Tensor]:
+    """Convert per-pixel camera rays to per-view (R, T, focal, principal)."""
+    if confidence is None:
+        confidence = torch.ones_like(camray[..., 0])
+    B, S, h, w, _ = camray.shape
+    device = camray.device
+    dtype = camray.dtype
+
+    rays_target = camray[..., :3]                           # (B, S, h, w, 3)
+    rays_origin = _unproject_identity(h, w, B, S, device, dtype)
+
+    # Flatten (B*S, h*w, *) for the RANSAC routine.
+    rays_target = rays_target.flatten(0, 1).flatten(1, 2)
+    rays_origin = rays_origin.flatten(0, 1).flatten(1, 2)
+    weights = confidence.flatten(0, 1).flatten(1, 2).clone()
+
+    # Project to 2D in homogeneous form (the upstream calls this "perspective division").
+    z_thresh = 1e-4
+    mask = (rays_target[:, :, 2].abs() > z_thresh) & (rays_origin[:, :, 2].abs() > z_thresh)
+    weights = torch.where(mask, weights, torch.zeros_like(weights))
+    src = rays_origin.clone()
+    dst = rays_target.clone()
+    src[..., 0] = torch.where(mask, src[..., 0] / src[..., 2], src[..., 0])
+    src[..., 1] = torch.where(mask, src[..., 1] / src[..., 2], src[..., 1])
+    dst[..., 0] = torch.where(mask, dst[..., 0] / dst[..., 2], dst[..., 0])
+    dst[..., 1] = torch.where(mask, dst[..., 1] / dst[..., 2], dst[..., 1])
+    src = src[..., :2]
+    dst = dst[..., :2]
+
+    N = src.shape[1]
+    n_iter = 100
+    sample_ratio = 0.3
+    num_sample_for_ransac = 8
+    n_sample = max(num_sample_for_ransac, int(N * sample_ratio))
+    rand_idx = torch.stack(
+        [torch.randperm(n_sample, device=device)[:num_sample_for_ransac] for _ in range(n_iter)],
+        dim=0,
+    )
+
+    # Chunk along the view axis to keep peak memory predictable.
+    chunk = 2
+    A_list = []
+    for i in range(0, src.shape[0], chunk):
+        A = _ransac_find_homography_weighted_batched(
+            src[i:i + chunk], dst[i:i + chunk], weights[i:i + chunk],
+            n_sample=n_sample, n_iter=n_iter,
+            num_sample_for_ransac=num_sample_for_ransac,
+            reproj_threshold=reproj_threshold,
+            rand_sample_iters_idx=rand_idx,
+            max_inlier_num=8000,
+        )
+        # Flip sign on dets that come out < 0 (so that the QL produces a
+        # right-handed rotation). ``det`` lacks fp16/bf16 CUDA kernels, so
+        # do the comparison in fp32.
+        flip = torch.linalg.det(A.float()) < 0
+        A = torch.where(flip[:, None, None], -A, A)
+        A_list.append(A)
+    A = torch.cat(A_list, dim=0)                            # (B*S, 3, 3)
+
+    R_list, f_list, pp_list = [], [], []
+    for i in range(A.shape[0]):
+        R, L = _ql_decomposition(A[i])
+        L = L / L[2][2]
+        f_list.append(torch.stack((L[0][0], L[1][1])))
+        pp_list.append(torch.stack((L[2][0], L[2][1])))
+        R_list.append(R)
+    R = torch.stack(R_list).reshape(B, S, 3, 3)
+    focal = torch.stack(f_list).reshape(B, S, 2)
+    pp = torch.stack(pp_list).reshape(B, S, 2)
+
+    # Translation: confidence-weighted average of camray direction(s).
+    cf = confidence.flatten(0, 1).flatten(1, 2)
+    T = (camray.flatten(0, 1).flatten(1, 2)[..., 3:] * cf.unsqueeze(-1)).sum(dim=1)
+    T = T / cf.sum(dim=-1, keepdim=True)
+    T = T.reshape(B, S, 3)
+
+    # Match upstream output convention: focal -> 1/focal, pp + 1.
+    return R, T, 1.0 / focal, pp + 1.0
+
+
+def get_extrinsic_from_camray(
+    camray: torch.Tensor,  # (B, S, h, w, 6)
+    conf: torch.Tensor,  # (B, S, h, w, 1) or (B, S, h, w)
+    patch_size_y: int,
+    patch_size_x: int,
+) -> Tuple[torch.Tensor, torch.Tensor, torch.Tensor]:
+    """Wrap a 4x4 extrinsic + per-view focal + principal-point output."""
+    if conf.ndim == 5 and conf.shape[-1] == 1:
+        conf = conf.squeeze(-1)
+    R, T, focal, pp = _camray_to_caminfo(camray, confidence=conf)
+    extr = torch.cat([R, T.unsqueeze(-1)], dim=-1)           # (B, S, 3, 4)
+    homo_row = torch.tensor([0, 0, 0, 1], dtype=R.dtype, device=R.device)
+    homo_row = homo_row.view(1, 1, 1, 4).expand(R.shape[0], R.shape[1], 1, 4)
+    extr = torch.cat([extr, homo_row], dim=-2)               # (B, S, 4, 4)
+    return extr, focal, pp

comfy/ldm/depth_anything_3/reference_view_selector.py

@@ -0,0 +1,87 @@
+"""Reference-view selection for the multi-view path of Depth Anything 3."""
+
+from __future__ import annotations
+
+from typing import Literal
+
+import torch
+
+
+RefViewStrategy = Literal["first", "middle", "saddle_balanced", "saddle_sim_range"]
+
+
+# Per the upstream constants module: ``THRESH_FOR_REF_SELECTION = 3``.
+# Reference selection only runs when there are at least this many views.
+THRESH_FOR_REF_SELECTION: int = 3
+
+
+def select_reference_view(x: torch.Tensor, strategy: RefViewStrategy = "saddle_balanced") -> torch.Tensor:
+    """Pick a reference view index per batch element."""
+    B, S, _, _ = x.shape
+    if S <= 1:
+        return torch.zeros(B, dtype=torch.long, device=x.device)
+    if strategy == "first":
+        return torch.zeros(B, dtype=torch.long, device=x.device)
+    if strategy == "middle":
+        return torch.full((B,), S // 2, dtype=torch.long, device=x.device)
+
+    # Feature-based strategies: normalised cls/cam token per view.
+    img_class_feat = x[:, :, 0] / x[:, :, 0].norm(dim=-1, keepdim=True)  # (B,S,C)
+
+    if strategy == "saddle_balanced":
+        sim = torch.matmul(img_class_feat, img_class_feat.transpose(1, 2))  # (B,S,S)
+        sim_no_diag = sim - torch.eye(S, device=sim.device).unsqueeze(0)
+        sim_score = sim_no_diag.sum(dim=-1) / (S - 1)               # (B,S)
+        feat_norm = x[:, :, 0].norm(dim=-1)                          # (B,S)
+        feat_var = img_class_feat.var(dim=-1)                        # (B,S)
+
+        def _normalize(metric):
+            mn = metric.min(dim=1, keepdim=True).values
+            mx = metric.max(dim=1, keepdim=True).values
+            return (metric - mn) / (mx - mn + 1e-8)
+
+        sim_n, norm_n, var_n = _normalize(sim_score), _normalize(feat_norm), _normalize(feat_var)
+        balance = (sim_n - 0.5).abs() + (norm_n - 0.5).abs() + (var_n - 0.5).abs()
+        return balance.argmin(dim=1)
+
+    if strategy == "saddle_sim_range":
+        sim = torch.matmul(img_class_feat, img_class_feat.transpose(1, 2))
+        sim_no_diag = sim - torch.eye(S, device=sim.device).unsqueeze(0)
+        sim_max = sim_no_diag.max(dim=-1).values
+        sim_min = sim_no_diag.min(dim=-1).values
+        return (sim_max - sim_min).argmax(dim=1)
+
+    raise ValueError(
+        f"Unknown reference view selection strategy: {strategy!r}. "
+        f"Must be one of: 'first', 'middle', 'saddle_balanced', 'saddle_sim_range'"
+    )
+
+
+def reorder_by_reference(x: torch.Tensor, b_idx: torch.Tensor) -> torch.Tensor:
+    """Reorder x so the reference view is at position 0 in axis S."""
+    B, S = x.shape[0], x.shape[1]
+    if S <= 1:
+        return x
+    positions = torch.arange(S, device=x.device).unsqueeze(0).expand(B, -1)
+    b_idx_exp = b_idx.unsqueeze(1)
+    reorder = torch.where(
+        (positions > 0) & (positions <= b_idx_exp),
+        positions - 1,
+        positions,
+    )
+    reorder[:, 0] = b_idx
+    batch = torch.arange(B, device=x.device).unsqueeze(1)
+    return x[batch, reorder]
+
+
+def restore_original_order(x: torch.Tensor, b_idx: torch.Tensor) -> torch.Tensor:
+    """Inverse of reorder_by_reference."""
+    B, S = x.shape[0], x.shape[1]
+    if S <= 1:
+        return x
+    target_positions = torch.arange(S, device=x.device).unsqueeze(0).expand(B, -1)
+    b_idx_exp = b_idx.unsqueeze(1)
+    restore = torch.where(target_positions < b_idx_exp, target_positions + 1, target_positions)
+    restore = torch.scatter(restore, dim=1, index=b_idx_exp, src=torch.zeros_like(b_idx_exp))
+    batch = torch.arange(B, device=x.device).unsqueeze(1)
+    return x[batch, restore]

comfy/ldm/depth_anything_3/transform.py

@@ -0,0 +1,160 @@
+"""Geometry / camera transform helpers for Depth Anything 3."""
+
+from __future__ import annotations
+
+from typing import Tuple
+
+import torch
+import torch.nn.functional as F
+
+
+# -----------------------------------------------------------------------------
+# Affine 4x4 helpers
+# -----------------------------------------------------------------------------
+
+
+def as_homogeneous(ext: torch.Tensor) -> torch.Tensor:
+    """Promote (...,3,4) extrinsics to (...,4,4) homogeneous form. No-op when the input is already ``(...,4,4)``."""
+    if ext.shape[-2:] == (4, 4):
+        return ext
+    if ext.shape[-2:] == (3, 4):
+        ones = torch.zeros_like(ext[..., :1, :4])
+        ones[..., 0, 3] = 1.0
+        return torch.cat([ext, ones], dim=-2)
+    raise ValueError(f"Invalid affine shape: {ext.shape}")
+
+
+def affine_inverse(A: torch.Tensor) -> torch.Tensor:
+    """Inverse of an affine matrix ``[R|T; 0 0 0 1]``."""
+    R = A[..., :3, :3]
+    T = A[..., :3, 3:]
+    P = A[..., 3:, :]
+    return torch.cat([torch.cat([R.mT, -R.mT @ T], dim=-1), P], dim=-2)
+
+
+# -----------------------------------------------------------------------------
+# Quaternion <-> rotation matrix (xyzw / scalar-last)
+# -----------------------------------------------------------------------------
+
+
+def _sqrt_positive_part(x: torch.Tensor) -> torch.Tensor:
+    """sqrt(max(0, x)) with a zero subgradient where x == 0."""
+    ret = torch.zeros_like(x)
+    positive_mask = x > 0
+    if torch.is_grad_enabled():
+        ret[positive_mask] = torch.sqrt(x[positive_mask])
+    else:
+        ret = torch.where(positive_mask, torch.sqrt(x), ret)
+    return ret
+
+
+def standardize_quaternion(quaternions: torch.Tensor) -> torch.Tensor:
+    """Force the real part of a unit quaternion (xyzw) to be non-negative."""
+    return torch.where(quaternions[..., 3:4] < 0, -quaternions, quaternions)
+
+
+def quat_to_mat(quaternions: torch.Tensor) -> torch.Tensor:
+    """Convert quaternions (xyzw) to (...,3,3) rotation matrices."""
+    i, j, k, r = torch.unbind(quaternions, -1)
+    two_s = 2.0 / (quaternions * quaternions).sum(-1)
+    o = torch.stack(
+        (
+            1 - two_s * (j * j + k * k),
+            two_s * (i * j - k * r),
+            two_s * (i * k + j * r),
+            two_s * (i * j + k * r),
+            1 - two_s * (i * i + k * k),
+            two_s * (j * k - i * r),
+            two_s * (i * k - j * r),
+            two_s * (j * k + i * r),
+            1 - two_s * (i * i + j * j),
+        ),
+        -1,
+    )
+    return o.reshape(quaternions.shape[:-1] + (3, 3))
+
+
+def mat_to_quat(matrix: torch.Tensor) -> torch.Tensor:
+    """Convert (...,3,3) rotation matrices to quaternions (xyzw)."""
+    if matrix.size(-1) != 3 or matrix.size(-2) != 3:
+        raise ValueError(f"Invalid rotation matrix shape {matrix.shape}.")
+
+    batch_dim = matrix.shape[:-2]
+    m00, m01, m02, m10, m11, m12, m20, m21, m22 = torch.unbind(
+        matrix.reshape(batch_dim + (9,)), dim=-1
+    )
+
+    q_abs = _sqrt_positive_part(
+        torch.stack(
+            [
+                1.0 + m00 + m11 + m22,
+                1.0 + m00 - m11 - m22,
+                1.0 - m00 + m11 - m22,
+                1.0 - m00 - m11 + m22,
+            ],
+            dim=-1,
+        )
+    )
+
+    quat_by_rijk = torch.stack(
+        [
+            torch.stack([q_abs[..., 0] ** 2, m21 - m12, m02 - m20, m10 - m01], dim=-1),
+            torch.stack([m21 - m12, q_abs[..., 1] ** 2, m10 + m01, m02 + m20], dim=-1),
+            torch.stack([m02 - m20, m10 + m01, q_abs[..., 2] ** 2, m12 + m21], dim=-1),
+            torch.stack([m10 - m01, m20 + m02, m21 + m12, q_abs[..., 3] ** 2], dim=-1),
+        ],
+        dim=-2,
+    )
+
+    flr = torch.tensor(0.1).to(dtype=q_abs.dtype, device=q_abs.device)
+    quat_candidates = quat_by_rijk / (2.0 * q_abs[..., None].max(flr))
+
+    out = quat_candidates[F.one_hot(q_abs.argmax(dim=-1), num_classes=4) > 0.5, :].reshape(
+        batch_dim + (4,)
+    )
+    # Reorder rijk -> xyzw (i.e. ijkr).
+    out = out[..., [1, 2, 3, 0]]
+    return standardize_quaternion(out)
+
+
+# -----------------------------------------------------------------------------
+# Pose-encoding <-> extrinsics + intrinsics
+# -----------------------------------------------------------------------------
+
+
+def extri_intri_to_pose_encoding(extrinsics: torch.Tensor, intrinsics: torch.Tensor, image_size_hw: Tuple[int, int]) -> torch.Tensor:
+    """Pack (extr, intr, image_size) into the 9-D pose-encoding vector.
+    extrinsics: camera-to-world (c2w) (B,S,4,4) matrices,
+    intrinsics: pixel-space (B,S,3,3) matrices,
+    image_size_hw: is a (H, W) pair.
+    """
+    R = extrinsics[..., :3, :3]
+    T = extrinsics[..., :3, 3]
+    quat = mat_to_quat(R)
+    H, W = image_size_hw
+    fov_h = 2 * torch.atan((H / 2) / intrinsics[..., 1, 1])
+    fov_w = 2 * torch.atan((W / 2) / intrinsics[..., 0, 0])
+    return torch.cat([T, quat, fov_h[..., None], fov_w[..., None]], dim=-1).float()
+
+
+def pose_encoding_to_extri_intri(pose_encoding: torch.Tensor, image_size_hw: Tuple[int, int]) -> Tuple[torch.Tensor, torch.Tensor]:
+    """Inverse of extri_intri_to_pose_encoding."""
+    T = pose_encoding[..., :3]
+    quat = pose_encoding[..., 3:7]
+    fov_h = pose_encoding[..., 7]
+    fov_w = pose_encoding[..., 8]
+    # Normalize to unit quaternion. CameraDec outputs raw values; a near-zero
+    # quaternion causes two_s = 2/norm² → inf in quat_to_mat → NaN extrinsics.
+    quat = quat / quat.norm(dim=-1, keepdim=True).clamp(min=1e-6)
+    R = quat_to_mat(quat)
+    extrinsics = torch.cat([R, T[..., None]], dim=-1)
+    H, W = image_size_hw
+    fy = (H / 2.0) / torch.clamp(torch.tan(fov_h / 2.0), 1e-6)
+    fx = (W / 2.0) / torch.clamp(torch.tan(fov_w / 2.0), 1e-6)
+    intrinsics = torch.zeros(pose_encoding.shape[:2] + (3, 3), device=pose_encoding.device, dtype=pose_encoding.dtype)
+    intrinsics[..., 0, 0] = fx
+    intrinsics[..., 1, 1] = fy
+    intrinsics[..., 0, 2] = W / 2
+    intrinsics[..., 1, 2] = H / 2
+    intrinsics[..., 2, 2] = 1.0
+    return extrinsics, intrinsics

comfy/ldm/flux/math.py

@@ -4,7 +4,7 @@ from torch import Tensor
 
 from comfy.ldm.modules.attention import optimized_attention
 import comfy.model_management
-import logging
+import comfy.quant_ops
 
 
 def attention(q: Tensor, k: Tensor, v: Tensor, pe: Tensor, mask=None, transformer_options={}) -> Tensor:
@@ -44,21 +44,15 @@ def _apply_rope(xq: Tensor, xk: Tensor, freqs_cis: Tensor):
     return apply_rope1(xq, freqs_cis), apply_rope1(xk, freqs_cis)
 
 
-try:
-    import comfy.quant_ops
-    q_apply_rope = comfy.quant_ops.ck.apply_rope
-    q_apply_rope1 = comfy.quant_ops.ck.apply_rope1
-    def apply_rope(xq, xk, freqs_cis):
-        if comfy.model_management.in_training:
-            return _apply_rope(xq, xk, freqs_cis)
-        else:
-            return apply_rope1(xq, freqs_cis), apply_rope1(xk, freqs_cis)
-    def apply_rope1(x, freqs_cis):
-        if comfy.model_management.in_training:
-            return _apply_rope1(x, freqs_cis)
-        else:
-            return q_apply_rope1(x, freqs_cis)
-except:
-    logging.warning("No comfy kitchen, using old apply_rope functions.")
-    apply_rope = _apply_rope
-    apply_rope1 = _apply_rope1
+def apply_rope(xq, xk, freqs_cis):
+    if comfy.model_management.in_training:
+        return _apply_rope(xq, xk, freqs_cis)
+    else:
+        return comfy.quant_ops.ck.apply_rope(xq, xk, freqs_cis)
+
+
+def apply_rope1(x, freqs_cis):
+    if comfy.model_management.in_training:
+        return _apply_rope1(x, freqs_cis)
+    else:
+        return comfy.quant_ops.ck.apply_rope1(x, freqs_cis)

comfy/ldm/ideogram4/model.py

@@ -0,0 +1,297 @@
+"""
+The Ideogram 4 transformer is a NextDiT/Lumina2-family single-stream model
+consumes Qwen3-VL hidden-state features (concatenated from 13 layers -> 53248 dims)
+packs ``[text tokens, image tokens]`` into one sequence with block-diagonal segment attention and 3D interleaved MRoPE.
+"""
+
+from __future__ import annotations
+
+import math
+
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+
+import comfy.patcher_extension
+from comfy.ldm.lumina.model import FeedForward
+from comfy.ldm.modules.attention import optimized_attention_masked
+from comfy.text_encoders.llama import apply_rope, precompute_freqs_cis
+
+# Per-token role indicators
+SEQUENCE_PADDING_INDICATOR = -1
+OUTPUT_IMAGE_INDICATOR = 2
+LLM_TOKEN_INDICATOR = 3
+# Image grid coordinates are offset so they never collide with text positions
+IMAGE_POSITION_OFFSET = 65536
+
+
+class Ideogram4Attention(nn.Module):
+    def __init__(self, hidden_size, num_heads, eps=1e-5, dtype=None, device=None, operations=None):
+        super().__init__()
+        self.num_heads = num_heads
+        self.head_dim = hidden_size // num_heads
+        self.hidden_size = hidden_size
+
+        self.qkv = operations.Linear(hidden_size, hidden_size * 3, bias=False, dtype=dtype, device=device)
+        self.norm_q = operations.RMSNorm(self.head_dim, eps=eps, elementwise_affine=True, dtype=dtype, device=device)
+        self.norm_k = operations.RMSNorm(self.head_dim, eps=eps, elementwise_affine=True, dtype=dtype, device=device)
+        self.o = operations.Linear(hidden_size, hidden_size, bias=False, dtype=dtype, device=device)
+
+    def forward(self, x, attn_mask, freqs_cis, transformer_options={}):
+        batch_size, seq_len, _ = x.shape
+        qkv = self.qkv(x).view(batch_size, seq_len, 3, self.num_heads, self.head_dim)
+        q, k, v = qkv.unbind(dim=2)
+
+        q = self.norm_q(q)
+        k = self.norm_k(k)
+
+        # (B, heads, L, head_dim)
+        q = q.transpose(1, 2)
+        k = k.transpose(1, 2)
+        v = v.transpose(1, 2)
+
+        q, k = apply_rope(q, k, freqs_cis)
+
+        out = optimized_attention_masked(q, k, v, self.num_heads, attn_mask, skip_reshape=True, transformer_options=transformer_options)
+        return self.o(out)
+
+
+class Ideogram4TransformerBlock(nn.Module):
+    def __init__(self, hidden_size, intermediate_size, num_heads, norm_eps, adaln_dim, dtype=None, device=None, operations=None):
+        super().__init__()
+        self.attention = Ideogram4Attention(hidden_size, num_heads, eps=1e-5, dtype=dtype, device=device, operations=operations)
+        self.feed_forward = FeedForward(
+            dim=hidden_size, hidden_dim=intermediate_size, multiple_of=1, ffn_dim_multiplier=None,
+            operation_settings={"operations": operations, "dtype": dtype, "device": device},
+        )
+
+        self.attention_norm1 = operations.RMSNorm(hidden_size, eps=norm_eps, elementwise_affine=True, dtype=dtype, device=device)
+        self.ffn_norm1 = operations.RMSNorm(hidden_size, eps=norm_eps, elementwise_affine=True, dtype=dtype, device=device)
+        self.attention_norm2 = operations.RMSNorm(hidden_size, eps=norm_eps, elementwise_affine=True, dtype=dtype, device=device)
+        self.ffn_norm2 = operations.RMSNorm(hidden_size, eps=norm_eps, elementwise_affine=True, dtype=dtype, device=device)
+
+        self.adaln_modulation = operations.Linear(adaln_dim, 4 * hidden_size, bias=True, dtype=dtype, device=device)
+
+    def forward(self, x, attn_mask, freqs_cis, adaln_input, transformer_options={}):
+        mod = self.adaln_modulation(adaln_input)
+        scale_msa, gate_msa, scale_mlp, gate_mlp = mod.chunk(4, dim=-1)
+        gate_msa = torch.tanh(gate_msa)
+        gate_mlp = torch.tanh(gate_mlp)
+        scale_msa = 1.0 + scale_msa
+        scale_mlp = 1.0 + scale_mlp
+
+        attn_out = self.attention(self.attention_norm1(x) * scale_msa, attn_mask, freqs_cis, transformer_options=transformer_options)
+        x = x + gate_msa * self.attention_norm2(attn_out)
+        x = x + gate_mlp * self.ffn_norm2(self.feed_forward(self.ffn_norm1(x) * scale_mlp))
+        return x
+
+
+def _sinusoidal_embedding(t, dim, scale=1e4):
+    t = t.to(torch.float32)
+    half = dim // 2
+    freq = math.log(scale) / (half - 1)
+    freq = torch.exp(torch.arange(half, dtype=torch.float32, device=t.device) * -freq)
+    emb = t.unsqueeze(-1) * freq
+    emb = torch.cat([torch.sin(emb), torch.cos(emb)], dim=-1)
+    if dim % 2 == 1:
+        emb = F.pad(emb, (0, 1))
+    return emb
+
+
+class Ideogram4EmbedScalar(nn.Module):
+    def __init__(self, dim, input_range=(0.0, 1.0), dtype=None, device=None, operations=None):
+        super().__init__()
+        self.dim = dim
+        self.range_min, self.range_max = input_range
+        self.mlp_in = operations.Linear(dim, dim, bias=True, dtype=dtype, device=device)
+        self.mlp_out = operations.Linear(dim, dim, bias=True, dtype=dtype, device=device)
+
+    def forward(self, x, dtype):
+        x = x.to(torch.float32)
+        scaled = 1e4 * (x - self.range_min) / (self.range_max - self.range_min)
+        emb = _sinusoidal_embedding(scaled, self.dim)
+        emb = emb.to(dtype)
+        emb = F.silu(self.mlp_in(emb))
+        return self.mlp_out(emb)
+
+
+class Ideogram4FinalLayer(nn.Module):
+    def __init__(self, hidden_size, out_channels, adaln_dim, dtype=None, device=None, operations=None):
+        super().__init__()
+        self.norm_final = operations.LayerNorm(hidden_size, eps=1e-6, elementwise_affine=False, dtype=dtype, device=device)
+        self.linear = operations.Linear(hidden_size, out_channels, bias=True, dtype=dtype, device=device)
+        self.adaln_modulation = operations.Linear(adaln_dim, hidden_size, bias=True, dtype=dtype, device=device)
+
+    def forward(self, x, c):
+        scale = 1.0 + self.adaln_modulation(F.silu(c))
+        return self.linear(self.norm_final(x) * scale)
+
+
+class Ideogram4Transformer(nn.Module):
+    """A single Ideogram 4 backbone operating on a packed token sequence."""
+
+    def __init__(self, emb_dim, num_layers, num_heads, intermediate_size, adaln_dim,
+                 in_channels, llm_features_dim, rope_theta, mrope_section, norm_eps,
+                 dtype=None, device=None, operations=None):
+        super().__init__()
+        self.head_dim = emb_dim // num_heads
+        self.rope_theta = rope_theta
+        self.mrope_section = tuple(mrope_section)
+
+        self.input_proj = operations.Linear(in_channels, emb_dim, bias=True, dtype=dtype, device=device)
+        self.llm_cond_norm = operations.RMSNorm(llm_features_dim, eps=1e-6, elementwise_affine=True, dtype=dtype, device=device)
+        self.llm_cond_proj = operations.Linear(llm_features_dim, emb_dim, bias=True, dtype=dtype, device=device)
+        self.t_embedding = Ideogram4EmbedScalar(emb_dim, input_range=(0.0, 1.0), dtype=dtype, device=device, operations=operations)
+        self.adaln_proj = operations.Linear(emb_dim, adaln_dim, bias=True, dtype=dtype, device=device)
+
+        self.embed_image_indicator = operations.Embedding(2, emb_dim, dtype=dtype, device=device)
+
+        self.layers = nn.ModuleList([
+            Ideogram4TransformerBlock(emb_dim, intermediate_size, num_heads, norm_eps, adaln_dim,
+                                      dtype=dtype, device=device, operations=operations)
+            for _ in range(num_layers)
+        ])
+
+        self.final_layer = Ideogram4FinalLayer(emb_dim, in_channels, adaln_dim, dtype=dtype, device=device, operations=operations)
+
+    def _backbone(self, llm_features, x, t, position_ids, attn_mask, indicator, transformer_options={}):
+        indicator = indicator.to(torch.long)
+        output_image_mask = (indicator == OUTPUT_IMAGE_INDICATOR).to(x.dtype).unsqueeze(-1)
+
+        x = x * output_image_mask
+        h = self.input_proj(x) * output_image_mask
+
+        t_cond = self.t_embedding(t, dtype=x.dtype)
+        if t.dim() == 1:
+            t_cond = t_cond.unsqueeze(1)
+        adaln_input = F.silu(self.adaln_proj(t_cond))
+
+        # h is zero on the text rows (content lives only on image rows), add writes the text features in place
+        if llm_features is not None:
+            L_text = llm_features.shape[1]
+            text_mask = (indicator[:, :L_text] == LLM_TOKEN_INDICATOR).to(x.dtype).unsqueeze(-1)
+            llm = self.llm_cond_norm(llm_features * text_mask)
+            llm = self.llm_cond_proj(llm) * text_mask
+            h[:, :L_text] = h[:, :L_text] + llm
+
+        h = h + self.embed_image_indicator((indicator == OUTPUT_IMAGE_INDICATOR).to(torch.long), out_dtype=h.dtype)
+
+        # Qwen3-VL interleaved MRoPE; position_ids (B, L, 3) -> (3, L) (same across batch).
+        freqs_cis = precompute_freqs_cis(
+            self.head_dim, position_ids[0].transpose(0, 1), self.rope_theta,
+            rope_dims=self.mrope_section, interleaved_mrope=True, device=position_ids.device,
+        )
+
+        if attn_mask is not None and attn_mask.dtype == torch.bool:
+            attn_mask = torch.zeros_like(attn_mask, dtype=h.dtype).masked_fill_(~attn_mask, -torch.finfo(h.dtype).max)
+
+        for layer in self.layers:
+            h = layer(h, attn_mask, freqs_cis, adaln_input, transformer_options=transformer_options)
+
+        return self.final_layer(h, adaln_input)
+
+
+class Ideogram4Transformer2DModel(Ideogram4Transformer):
+    """Ideogram 4 single-stream DiT.
+
+    Runs a packed ``[text, image]`` sequence when text context is supplied, or an image-only sequence when ``context is None``.
+    """
+
+    def __init__(self, image_model=None, in_channels=128, num_layers=34, num_attention_heads=18, attention_head_dim=256, intermediate_size=12288,
+                 adaln_dim=512, llm_features_dim=53248, rope_theta=5000000, mrope_section=(24, 20, 20), norm_eps=1e-5,
+                 dtype=None, device=None, operations=None, **kwargs):
+        emb_dim = num_attention_heads * attention_head_dim
+        super().__init__(
+            emb_dim=emb_dim, num_layers=num_layers, num_heads=num_attention_heads,
+            intermediate_size=intermediate_size, adaln_dim=adaln_dim, in_channels=in_channels,
+            llm_features_dim=llm_features_dim, rope_theta=rope_theta, mrope_section=mrope_section,
+            norm_eps=norm_eps, dtype=dtype, device=device, operations=operations)
+        self.dtype = dtype
+        self.in_channels = in_channels
+        self.out_channels = in_channels
+        # 128-dim token = patch (2x2) * ae_channels (32).
+        self.patch_size = 2
+        self.ae_channels = in_channels // (self.patch_size * self.patch_size)
+
+    def _img_to_tokens(self, x):
+        B, C, gh, gw = x.shape
+        x = x.view(B, self.ae_channels, self.patch_size, self.patch_size, gh, gw)
+        x = x.permute(0, 4, 5, 2, 3, 1)  # (B, gh, gw, pi, pj, c)
+        return x.reshape(B, gh * gw, C)
+
+    def _tokens_to_img(self, tokens, gh, gw):
+        B = tokens.shape[0]
+        C = tokens.shape[-1]
+        x = tokens.reshape(B, gh, gw, self.patch_size, self.patch_size, self.ae_channels)
+        x = x.permute(0, 5, 3, 4, 1, 2)  # (B, c, pi, pj, gh, gw)
+        return x.reshape(B, C, gh, gw)
+
+    def _image_position_ids(self, gh, gw, device):
+        h_idx = torch.arange(gh, device=device).view(-1, 1).expand(gh, gw).reshape(-1)
+        w_idx = torch.arange(gw, device=device).view(1, -1).expand(gh, gw).reshape(-1)
+        t_idx = torch.zeros_like(h_idx)
+        return torch.stack([t_idx, h_idx, w_idx], dim=1) + IMAGE_POSITION_OFFSET  # (L_img, 3)
+
+    def _run_conditional(self, x_chunk, context_chunk, attn_mask_chunk, t_chunk, gh, gw, transformer_options):
+        B = x_chunk.shape[0]
+        device = x_chunk.device
+        img_tokens = self._img_to_tokens(x_chunk)
+        L_img = img_tokens.shape[1]
+        L_text = context_chunk.shape[1]
+        L = L_text + L_img
+        latent_dim = img_tokens.shape[-1]
+
+        x_full = torch.zeros(B, L, latent_dim, dtype=img_tokens.dtype, device=device)
+        x_full[:, L_text:] = img_tokens
+
+        text_pos = torch.arange(L_text, device=device).view(-1, 1).expand(L_text, 3)
+        img_pos = self._image_position_ids(gh, gw, device)
+        position_ids = torch.cat([text_pos, img_pos], dim=0).unsqueeze(0).expand(B, L, 3)
+
+        indicator = torch.empty(B, L, dtype=torch.long, device=device)
+        indicator[:, :L_text] = LLM_TOKEN_INDICATOR
+        indicator[:, L_text:] = OUTPUT_IMAGE_INDICATOR
+
+        attn_mask = None
+        if attn_mask_chunk is not None:
+            segment_ids = torch.ones(B, L, dtype=torch.long, device=device)
+            pad = (attn_mask_chunk == 0)
+            segment_ids[:, :L_text][pad] = SEQUENCE_PADDING_INDICATOR
+            indicator[:, :L_text][pad] = 0
+            # Block-diagonal mask from segment ids: (B, 1, L, L), True = attend.
+            attn_mask = (segment_ids.unsqueeze(2) == segment_ids.unsqueeze(1)).unsqueeze(1)
+
+        out = self._backbone(context_chunk, x_full, t_chunk, position_ids, attn_mask, indicator,
+                             transformer_options=transformer_options)
+        return self._tokens_to_img(out[:, L_text:], gh, gw)
+
+    def _run_image_only(self, x_chunk, t_chunk, gh, gw, transformer_options):
+        B = x_chunk.shape[0]
+        device = x_chunk.device
+        img_tokens = self._img_to_tokens(x_chunk)
+        L_img = img_tokens.shape[1]
+
+        position_ids = self._image_position_ids(gh, gw, device).unsqueeze(0).expand(B, L_img, 3)
+        indicator = torch.full((B, L_img), OUTPUT_IMAGE_INDICATOR, dtype=torch.long, device=device)
+
+        # Image-only sequence is a single segment -> no mask, full attention, no LLM context.
+        out = self._backbone(None, img_tokens, t_chunk, position_ids, None, indicator, transformer_options=transformer_options)
+        return self._tokens_to_img(out, gh, gw)
+
+    def forward(self, x, timesteps, context=None, attention_mask=None, transformer_options={}, **kwargs):
+        return comfy.patcher_extension.WrapperExecutor.new_class_executor(
+            self._forward,
+            self,
+            comfy.patcher_extension.get_all_wrappers(comfy.patcher_extension.WrappersMP.DIFFUSION_MODEL, transformer_options),
+        ).execute(x, timesteps, context, attention_mask, transformer_options, **kwargs)
+
+    def _forward(self, x, timesteps, context=None, attention_mask=None, transformer_options={}, **kwargs):
+        bs, c, gh, gw = x.shape
+
+        timesteps = 1.0 - timesteps
+
+        # unconditional pass
+        if context is None:
+            return -self._run_image_only(x, timesteps, gh, gw, transformer_options)
+
+        return -self._run_conditional(x, context, attention_mask, timesteps, gh, gw, transformer_options)

comfy/ldm/krea2/model.py

@@ -0,0 +1,290 @@
+"""Krea 2 (K2) — single-stream MMDiT.
+
+Text tokens produced by a Qwen3-VL-4B 12-layer ``txtfusion`` adapter and patchified image tokens are
+concatenated into one sequence and run through ``layers`` shared transformer blocks with
+AdaLN-single modulation, GQA + per-head QK-norm + sigmoid-gated attention, SwiGLU MLP, and 3-axis RoPE.
+"""
+
+from typing import Optional
+
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+from einops import rearrange
+
+import comfy.model_management
+import comfy.patcher_extension
+import comfy.ldm.common_dit
+from comfy.ldm.flux.layers import EmbedND, timestep_embedding
+from comfy.ldm.flux.math import apply_rope
+from comfy.ldm.modules.attention import optimized_attention_masked
+
+
+class RMSNorm(nn.Module):
+    """RMSNorm with the reference ``(1 + scale)`` weight convention (scale stored zero-centered)."""
+
+    def __init__(self, features: int, eps: float = 1e-5, device=None, dtype=None, operations=None):
+        super().__init__()
+        self.eps = eps
+        self.scale = nn.Parameter(torch.empty(features, device=device, dtype=dtype))
+
+    def forward(self, x: torch.Tensor) -> torch.Tensor:
+        dtype = x.dtype
+        weight = comfy.model_management.cast_to(self.scale, dtype=torch.float32, device=x.device) + 1.0
+        return F.rms_norm(x.float(), (x.shape[-1],), weight=weight, eps=self.eps).to(dtype)
+
+
+class QKNorm(nn.Module):
+    def __init__(self, dim: int, device=None, dtype=None, operations=None):
+        super().__init__()
+        self.qnorm = RMSNorm(dim, device=device, dtype=dtype, operations=operations)
+        self.knorm = RMSNorm(dim, device=device, dtype=dtype, operations=operations)
+
+    def forward(self, q, k):
+        return self.qnorm(q), self.knorm(k)
+
+
+class SwiGLU(nn.Module):
+    def __init__(self, features: int, multiplier: int, bias: bool = False, multiple: int = 128,
+                 device=None, dtype=None, operations=None):
+        super().__init__()
+        mlpdim = int(2 * features / 3) * multiplier
+        mlpdim = multiple * ((mlpdim + multiple - 1) // multiple)
+        self.gate = operations.Linear(features, mlpdim, bias=bias, device=device, dtype=dtype)
+        self.up = operations.Linear(features, mlpdim, bias=bias, device=device, dtype=dtype)
+        self.down = operations.Linear(mlpdim, features, bias=bias, device=device, dtype=dtype)
+
+    def forward(self, x):
+        return self.down(F.silu(self.gate(x)).mul_(self.up(x)))
+
+
+class Attention(nn.Module):
+    def __init__(self, dim: int, heads: int, kvheads: Optional[int] = None, bias: bool = False,
+                 device=None, dtype=None, operations=None):
+        super().__init__()
+        self.heads = heads
+        self.kvheads = kvheads if kvheads is not None else heads
+        self.headdim = dim // self.heads
+        self.wq = operations.Linear(dim, self.headdim * self.heads, bias=bias, device=device, dtype=dtype)
+        self.wk = operations.Linear(dim, self.headdim * self.kvheads, bias=bias, device=device, dtype=dtype)
+        self.wv = operations.Linear(dim, self.headdim * self.kvheads, bias=bias, device=device, dtype=dtype)
+        self.gate = operations.Linear(dim, dim, bias=bias, device=device, dtype=dtype)
+        self.qknorm = QKNorm(self.headdim, device=device, dtype=dtype, operations=operations)
+        self.wo = operations.Linear(dim, dim, bias=bias, device=device, dtype=dtype)
+
+    def forward(self, x, freqs=None, mask=None, transformer_options={}):
+        q, k, v, gate = self.wq(x), self.wk(x), self.wv(x), self.gate(x)
+        q = rearrange(q, "B L (H D) -> B H L D", H=self.heads)
+        k = rearrange(k, "B L (H D) -> B H L D", H=self.kvheads)
+        v = rearrange(v, "B L (H D) -> B H L D", H=self.kvheads)
+        q, k = self.qknorm(q, k)
+        if freqs is not None:
+            q, k = apply_rope(q, k, freqs)
+        if self.kvheads != self.heads:
+            rep = self.heads // self.kvheads
+            k = k.repeat_interleave(rep, dim=1)
+            v = v.repeat_interleave(rep, dim=1)
+        out = optimized_attention_masked(q, k, v, self.heads, mask=mask, skip_reshape=True,
+                                         transformer_options=transformer_options)
+        return self.wo(out * F.sigmoid(gate))
+
+
+class SimpleModulation(nn.Module):
+    def __init__(self, dim: int, device=None, dtype=None, operations=None):
+        super().__init__()
+        self.lin = nn.Parameter(torch.empty(2, dim, device=device, dtype=dtype))
+
+    def forward(self, vec):
+        out = vec + comfy.model_management.cast_to(self.lin, dtype=vec.dtype, device=vec.device).unsqueeze(0)
+        scale, shift = out.chunk(2, dim=1)
+        return scale, shift
+
+
+class DoubleSharedModulation(nn.Module):
+    def __init__(self, dim: int, device=None, dtype=None, operations=None):
+        super().__init__()
+        self.lin = nn.Parameter(torch.empty(6 * dim, device=device, dtype=dtype))
+
+    def forward(self, vec):
+        out = vec + comfy.model_management.cast_to(self.lin, dtype=vec.dtype, device=vec.device)
+        return out.chunk(6, dim=-1)
+
+
+class TextFusionBlock(nn.Module):
+    def __init__(self, features, heads, multiplier, bias=False, kvheads=None, device=None, dtype=None, operations=None):
+        super().__init__()
+        self.prenorm = RMSNorm(features, device=device, dtype=dtype, operations=operations)
+        self.postnorm = RMSNorm(features, device=device, dtype=dtype, operations=operations)
+        self.attn = Attention(features, heads, kvheads=kvheads, bias=bias, device=device, dtype=dtype, operations=operations)
+        self.mlp = SwiGLU(features, multiplier, bias, device=device, dtype=dtype, operations=operations)
+
+    def forward(self, x, mask=None, transformer_options={}):
+        x = x + self.attn(self.prenorm(x), mask=mask, transformer_options=transformer_options)
+        x = x + self.mlp(self.postnorm(x))
+        return x
+
+
+class TextFusionTransformer(nn.Module):
+    def __init__(self, num_txt_layers, txt_dim, heads, multiplier, bias=False, kvheads=None, device=None, dtype=None, operations=None):
+        super().__init__()
+        self.layerwise_blocks = nn.ModuleList([
+            TextFusionBlock(txt_dim, heads, multiplier, bias, kvheads, device=device, dtype=dtype, operations=operations)
+            for _ in range(2)
+        ])
+        self.projector = operations.Linear(num_txt_layers, 1, bias=False, device=device, dtype=dtype)
+        self.refiner_blocks = nn.ModuleList([
+            TextFusionBlock(txt_dim, heads, multiplier, bias, kvheads, device=device, dtype=dtype, operations=operations)
+            for _ in range(2)
+        ])
+
+    def forward(self, x, mask=None, transformer_options={}):
+        b, l, n, d = x.shape
+        x = x.reshape(b * l, n, d)
+        for block in self.layerwise_blocks:
+            x = block(x.contiguous(), mask=None, transformer_options=transformer_options)
+        x = rearrange(x, "(b l) n d -> b l d n", b=b, l=l)
+        x = self.projector(x).squeeze(-1)
+        for block in self.refiner_blocks:
+            x = block(x, mask=mask, transformer_options=transformer_options)
+        return x
+
+
+class SingleStreamBlock(nn.Module):
+    def __init__(self, features, heads, multiplier, bias=False, kvheads=None, device=None, dtype=None, operations=None):
+        super().__init__()
+        self.mod = DoubleSharedModulation(features, device=device, dtype=dtype, operations=operations)
+        self.prenorm = RMSNorm(features, device=device, dtype=dtype, operations=operations)
+        self.postnorm = RMSNorm(features, device=device, dtype=dtype, operations=operations)
+        self.attn = Attention(features, heads, kvheads=kvheads, bias=bias, device=device, dtype=dtype, operations=operations)
+        self.mlp = SwiGLU(features, multiplier, bias, device=device, dtype=dtype, operations=operations)
+
+    def forward(self, x, vec, freqs, mask=None, transformer_options={}):
+        prescale, preshift, pregate, postscale, postshift, postgate = self.mod(vec)
+        x = x + pregate * self.attn((1 + prescale) * self.prenorm(x) + preshift, freqs, mask, transformer_options=transformer_options)
+        x = x + postgate * self.mlp((1 + postscale) * self.postnorm(x) + postshift)
+        return x
+
+
+class LastLayer(nn.Module):
+    def __init__(self, features, patch, channels, device=None, dtype=None, operations=None):
+        super().__init__()
+        self.norm = RMSNorm(features, device=device, dtype=dtype, operations=operations)
+        self.linear = operations.Linear(features, patch * patch * channels, bias=True, device=device, dtype=dtype)
+        self.modulation = SimpleModulation(features, device=device, dtype=dtype, operations=operations)
+
+    def forward(self, x, tvec):
+        scale, shift = self.modulation(tvec)
+        x = (1 + scale) * self.norm(x) + shift
+        return self.linear(x)
+
+
+class SingleStreamDiT(nn.Module):
+    def __init__(self, features=6144, tdim=256, txtdim=2560, heads=48, kvheads=12, multiplier=4,
+                 layers=28, patch=2, channels=16, bias=False, theta=1e3, txtlayers=12,
+                 txtheads=20, txtkvheads=20, image_model=None,
+                 device=None, dtype=None, operations=None, **kwargs):
+        super().__init__()
+        self.dtype = dtype
+        self.patch = patch
+        self.channels = channels
+        self.tdim = tdim
+        self.heads = heads
+        self.txtdim = txtdim
+        self.txtlayers = txtlayers
+
+        headdim = features // heads
+        axes = [headdim - 12 * (headdim // 16), 6 * (headdim // 16), 6 * (headdim // 16)]
+        assert sum(axes) == headdim, f"axes {axes} sum != headdim {headdim}"
+        self.pe_embedder = EmbedND(dim=headdim, theta=int(theta), axes_dim=axes)
+
+        self.first = operations.Linear(channels * patch ** 2, features, bias=True, device=device, dtype=dtype)
+        self.blocks = nn.ModuleList([
+            SingleStreamBlock(features, heads, multiplier, bias, kvheads, device=device, dtype=dtype, operations=operations)
+            for _ in range(layers)
+        ])
+        self.tmlp = nn.Sequential(
+            operations.Linear(tdim, features, device=device, dtype=dtype),
+            nn.GELU(approximate="tanh"),
+            operations.Linear(features, features, device=device, dtype=dtype),
+        )
+        self.txtfusion = TextFusionTransformer(txtlayers, txtdim, txtheads, multiplier, bias, txtkvheads,
+                                               device=device, dtype=dtype, operations=operations)
+        self.txtmlp = nn.Sequential(
+            RMSNorm(txtdim, device=device, dtype=dtype, operations=operations),
+            operations.Linear(txtdim, features, device=device, dtype=dtype),
+            nn.GELU(approximate="tanh"),
+            operations.Linear(features, features, device=device, dtype=dtype),
+        )
+        self.last = LastLayer(features, patch, channels, device=device, dtype=dtype, operations=operations)
+        self.tproj = nn.Sequential(
+            nn.GELU(approximate="tanh"),
+            operations.Linear(features, features * 6, device=device, dtype=dtype),
+        )
+
+    def forward(self, x, timesteps, context, attention_mask=None, transformer_options={}, **kwargs):
+        return comfy.patcher_extension.WrapperExecutor.new_class_executor(
+            self._forward,
+            self,
+            comfy.patcher_extension.get_all_wrappers(comfy.patcher_extension.WrappersMP.DIFFUSION_MODEL, transformer_options),
+        ).execute(x, timesteps, context, attention_mask, transformer_options, **kwargs)
+
+    def _forward(self, x, timesteps, context, attention_mask=None, transformer_options={}, **kwargs):
+        temporal = x.ndim == 5
+        if temporal:
+            b5, c5, t5, h5, w5 = x.shape
+            x = x.reshape(b5 * t5, c5, h5, w5)
+        bs, c, H_orig, W_orig = x.shape
+        patch = self.patch
+        # Pad the latent up to a multiple of patch (as Flux/Lumina/QwenImage do); crop back at the end.
+        x = comfy.ldm.common_dit.pad_to_patch_size(x, (patch, patch))
+        H, W = x.shape[-2], x.shape[-1]
+        h_, w_ = H // patch, W // patch
+
+        # context arrives as (B, seq, txtlayers*txtdim); reshape to (B, txtlayers, seq, txtdim).
+        context = self._unpack_context(context)
+
+        img = rearrange(x, "b c (h ph) (w pw) -> b (h w) (c ph pw)", ph=patch, pw=patch)
+        img = self.first(img)
+
+        t = self.tmlp(timestep_embedding(timesteps, self.tdim).unsqueeze(1).to(img.dtype))
+        tvec = self.tproj(t)
+
+        context = self.txtfusion(context, mask=None, transformer_options=transformer_options)
+        context = self.txtmlp(context)
+
+        txtlen, imglen = context.shape[1], img.shape[1]
+        combined = torch.cat((context, img), dim=1)
+
+        # Position ids: text at 0, image at (0, h_idx, w_idx).
+        device = combined.device
+        txtpos = torch.zeros(bs, txtlen, 3, device=device, dtype=torch.float32)
+        imgids = torch.zeros(h_, w_, 3, device=device, dtype=torch.float32)
+        imgids[..., 1] = torch.arange(h_, device=device, dtype=torch.float32)[:, None]
+        imgids[..., 2] = torch.arange(w_, device=device, dtype=torch.float32)[None, :]
+        imgpos = imgids.reshape(1, h_ * w_, 3).repeat(bs, 1, 1)
+        pos = torch.cat((txtpos, imgpos), dim=1)
+
+        freqs = self.pe_embedder(pos)
+
+        for block in self.blocks:
+            combined = block(combined, tvec, freqs, None, transformer_options=transformer_options)
+
+        final = self.last(combined, t)
+        out = final[:, txtlen:txtlen + imglen, :]
+        out = rearrange(out, "b (h w) (c ph pw) -> b c (h ph) (w pw)",
+                        h=h_, w=w_, ph=patch, pw=patch, c=self.channels)
+        out = out[:, :, :H_orig, :W_orig]  # crop padding back off
+        if temporal:
+            out = out.reshape(b5, t5, self.channels, H_orig, W_orig).movedim(1, 2)
+        return out
+
+    def _unpack_context(self, context):
+        # context: (B, seq, txtlayers*txtdim) -> (B, seq, txtlayers, txtdim).
+        b, seq, fused = context.shape
+        if fused != self.txtlayers * self.txtdim:
+            raise ValueError(
+                f"Krea2 expects conditioning with {self.txtlayers}x{self.txtdim}={self.txtlayers * self.txtdim} "
+                f"features (a {self.txtlayers}-layer Qwen3-VL stack) but got {fused}. "
+                f"Load the text encoder with CLIPLoader type 'krea2'."
+            )
+        return context.reshape(b, seq, self.txtlayers, self.txtdim)

comfy/ldm/lightricks/model.py

@@ -1085,7 +1085,7 @@ class LTXVModel(LTXBaseModel):
         )
 
         grid_mask = None
-        if keyframe_idxs is not None:
+        if keyframe_idxs is not None and keyframe_idxs.shape[2] > 0:
             additional_args.update({ "orig_patchified_shape": list(x.shape)})
             denoise_mask = self.patchifier.patchify(denoise_mask)[0]
             grid_mask = ~torch.any(denoise_mask < 0, dim=-1)[0]
@@ -1330,7 +1330,7 @@ class LTXVModel(LTXBaseModel):
         x = x * (1 + scale) + shift
         x = self.proj_out(x)
 
-        if keyframe_idxs is not None:
+        if keyframe_idxs is not None and keyframe_idxs.shape[2] > 0:
             grid_mask = kwargs["grid_mask"]
             orig_patchified_shape = kwargs["orig_patchified_shape"]
             full_x = torch.zeros(orig_patchified_shape, dtype=x.dtype, device=x.device)

comfy/ldm/omnigen/omnigen2.py

@@ -8,6 +8,7 @@ import torch.nn.functional as F
 from einops import rearrange, repeat
 from comfy.ldm.lightricks.model import Timesteps
 from comfy.ldm.flux.layers import EmbedND
+from comfy.ldm.flux.math import apply_rope1
 from comfy.ldm.modules.attention import optimized_attention_masked
 import comfy.model_management
 import comfy.ldm.common_dit
@@ -17,13 +18,11 @@ def apply_rotary_emb(x, freqs_cis):
     if x.shape[1] == 0:
         return x
 
-    t_ = x.reshape(*x.shape[:-1], -1, 1, 2)
-    t_out = freqs_cis[..., 0] * t_[..., 0] + freqs_cis[..., 1] * t_[..., 1]
-    return t_out.reshape(*x.shape).to(dtype=x.dtype)
+    return apply_rope1(x, freqs_cis)
 
 
 def swiglu(x: torch.Tensor, y: torch.Tensor) -> torch.Tensor:
-    return F.silu(x) * y
+    return F.silu(x, inplace=True).mul_(y)
 
 
 class TimestepEmbedding(nn.Module):

comfy/ldm/qwen_image/model.py

@@ -51,6 +51,18 @@ class FeedForward(nn.Module):
         return hidden_states
 
 
+# Addin this back because Nunchaku custom nodes rely on it, see comment here:
+# https://github.com/Comfy-Org/ComfyUI/pull/14178#issuecomment-4640475161
+# TODO: Eventually remove this once we natively support SVDQuants
+def apply_rotary_emb(x, freqs_cis):
+    if x.shape[1] == 0:
+        return x
+
+    t_ = x.reshape(*x.shape[:-1], -1, 1, 2)
+    t_out = freqs_cis[..., 0] * t_[..., 0] + freqs_cis[..., 1] * t_[..., 1]
+    return t_out.reshape(*x.shape)
+
+
 class QwenTimestepProjEmbeddings(nn.Module):
     def __init__(self, embedding_dim, pooled_projection_dim, use_additional_t_cond=False, dtype=None, device=None, operations=None):
         super().__init__()

comfy/ldm/wan/model.py

@@ -8,7 +8,7 @@ from einops import rearrange
 
 from comfy.ldm.modules.attention import optimized_attention
 from comfy.ldm.flux.layers import EmbedND
-from comfy.ldm.flux.math import apply_rope1
+from comfy.ldm.flux.math import apply_rope1, rope
 import comfy.ldm.common_dit
 import comfy.model_management
 import comfy.patcher_extension
@@ -570,6 +570,14 @@ class WanModel(torch.nn.Module):
                 full_ref = self.ref_conv(full_ref).flatten(2).transpose(1, 2)
                 x = torch.concat((full_ref, x), dim=1)
 
+        # In-context reference (Bernini)
+        context_latents = kwargs.get("context_latents", None)
+        main_len = x.shape[1]
+        if context_latents is not None:
+            for lat in context_latents:
+                cl = self.patch_embedding(lat.float().to(x.device)).to(x.dtype).flatten(2).transpose(1, 2)
+                x = torch.cat([x, cl], dim=1)
+
         # context
         context = self.text_embedding(context)
 
@@ -599,6 +607,9 @@ class WanModel(torch.nn.Module):
         # head
         x = self.head(x, e)
 
+        if context_latents is not None:
+            x = x[:, :main_len]
+
         if full_ref is not None:
             x = x[:, full_ref.shape[1]:]
 
@@ -606,7 +617,7 @@ class WanModel(torch.nn.Module):
         x = self.unpatchify(x, grid_sizes)
         return x
 
-    def rope_encode(self, t, h, w, t_start=0, steps_t=None, steps_h=None, steps_w=None, device=None, dtype=None, transformer_options={}):
+    def rope_encode(self, t, h, w, t_start=0, steps_t=None, steps_h=None, steps_w=None, device=None, dtype=None, transformer_options={}, source_id=0):
         patch_size = self.patch_size
         t_len = ((t + (patch_size[0] // 2)) // patch_size[0])
         h_len = ((h + (patch_size[1] // 2)) // patch_size[1])
@@ -638,6 +649,13 @@ class WanModel(torch.nn.Module):
         img_ids = img_ids.reshape(1, -1, img_ids.shape[-1])
 
         freqs = self.rope_embedder(img_ids).movedim(1, 2)
+
+        # In-context reference: a non-zero source_id composes an extra rotation into the spatial rope
+        if source_id:
+            d = self.dim // self.num_heads
+            pos = torch.tensor([[float(source_id)]], device=freqs.device, dtype=torch.float32)
+            id_rot = rope(pos, d, self.rope_embedder.theta).reshape(1, 1, 1, d // 2, 2, 2).to(freqs.dtype)
+            freqs = torch.einsum('...ij,...jk->...ik', freqs, id_rot)
         return freqs
 
     def forward(self, x, timestep, context, clip_fea=None, time_dim_concat=None, transformer_options={}, **kwargs):
@@ -661,6 +679,15 @@ class WanModel(torch.nn.Module):
             t_len += 1
 
         freqs = self.rope_encode(t_len, h, w, device=x.device, dtype=x.dtype, transformer_options=transformer_options)
+
+        # In-context reference: one rope block per stream, each with it's own source_id (1, 2, ...) to distinguish from the target (id 0).
+        context_latents = kwargs.get("context_latents", None)
+        if context_latents is not None:
+            context_latents = [comfy.ldm.common_dit.pad_to_patch_size(lat, self.patch_size) for lat in context_latents]
+            for i, lat in enumerate(context_latents):
+                freqs = torch.cat([freqs, self.rope_encode(lat.shape[-3], lat.shape[-2], lat.shape[-1], device=x.device, dtype=x.dtype, transformer_options=transformer_options, source_id=i + 1)], dim=1)
+            kwargs = {**kwargs, "context_latents": context_latents}
+
         return self.forward_orig(x, timestep, context, clip_fea=clip_fea, freqs=freqs, transformer_options=transformer_options, **kwargs)[:, :, :t, :h, :w]
 
     def unpatchify(self, x, grid_sizes):
@@ -1631,13 +1658,15 @@ class SCAILWanModel(WanModel):
 
         self.patch_embedding_pose = operations.Conv3d(in_dim, dim, kernel_size=patch_size, stride=patch_size, device=device, dtype=torch.float32)
 
-    def forward_orig(self, x, t, context, clip_fea=None, freqs=None, transformer_options={}, pose_latents=None, reference_latent=None, **kwargs):
+    def forward_orig(self, x, t, context, clip_fea=None, freqs=None, transformer_options={}, pose_latents=None, reference_latent=None, ref_mask_latents=None, sam_latents=None, **kwargs):
 
         if reference_latent is not None:
             x = torch.cat((reference_latent, x), dim=2)
 
         # embeddings
         x = self.patch_embedding(x.float()).to(x.dtype)
+        if ref_mask_latents is not None:  # SCAIL-2 additive mask stream (one identity mask frame per reference, then video)
+            x = x + self.patch_embedding_mask(ref_mask_latents.float()).to(x.dtype)
         grid_sizes = x.shape[2:]
         transformer_options["grid_sizes"] = grid_sizes
         x = x.flatten(2).transpose(1, 2)
@@ -1645,6 +1674,8 @@ class SCAILWanModel(WanModel):
         scail_pose_seq_len = 0
         if pose_latents is not None:
             scail_x = self.patch_embedding_pose(pose_latents.float()).to(x.dtype)
+            if sam_latents is not None:  # SCAIL-2 additive mask stream
+                scail_x = scail_x + self.patch_embedding_mask(sam_latents.float()).to(x.dtype)
             scail_x = scail_x.flatten(2).transpose(1, 2)
             scail_pose_seq_len = scail_x.shape[1]
             x = torch.cat([x, scail_x], dim=1)
@@ -1695,16 +1726,44 @@ class SCAILWanModel(WanModel):
 
         return x
 
-    def rope_encode(self, t, h, w, t_start=0, steps_t=None, steps_h=None, steps_w=None, device=None, dtype=None, pose_latents=None, reference_latent=None, transformer_options={}):
+    # ref_mask_flag is a scalar bool (CONDConstant, SCAIL-2 only). False => replacement mode,
+    # which places ref/pose via H/W rope shifts instead of the animation-mode temporal offset.
+    # reference_latent may stack several frames: the last is the primary reference adjacent to the video, the earlier frames are additional references.
+    def rope_encode(self, t, h, w, t_start=0, steps_t=None, steps_h=None, steps_w=None, device=None, dtype=None, pose_latents=None, reference_latent=None, ref_mask_flag=None, transformer_options={}):
+        ref_t_patches = 0
+        if reference_latent is not None:
+            ref_t_patches = (reference_latent.shape[2] + (self.patch_size[0] // 2)) // self.patch_size[0]
+
+        if ref_mask_flag is not None and not bool(ref_mask_flag):
+            REF_ROPE_H = 120.0
+            POSE_ROPE_W = 120.0
+
+            main_t_patches = t - ref_t_patches
+            video_t_start = max(ref_t_patches - 1, 0)
+
+            parts = []
+            if ref_t_patches > 0:
+                ref_tf = {"rope_options": {"shift_y": REF_ROPE_H, "shift_x": 0.0, "scale_y": 1.0, "scale_x": 1.0}}
+                parts.append(super().rope_encode(ref_t_patches, h, w, t_start=0, device=device, dtype=dtype, transformer_options=ref_tf))
+            if main_t_patches > 0:
+                parts.append(super().rope_encode(main_t_patches, h, w, t_start=video_t_start, device=device, dtype=dtype, transformer_options=transformer_options))
+
+            if pose_latents is not None:
+                F_pose, H_pose, W_pose = pose_latents.shape[-3], pose_latents.shape[-2], pose_latents.shape[-1]
+                h_scale = h / H_pose
+                w_scale = w / W_pose
+                h_shift = (h_scale - 1) / 2
+                w_shift = (w_scale - 1) / 2
+                pose_tf = {"rope_options": {"shift_y": h_shift, "shift_x": POSE_ROPE_W + w_shift, "scale_y": h_scale, "scale_x": w_scale}}
+                parts.append(super().rope_encode(F_pose, H_pose, W_pose, t_start=video_t_start, device=device, dtype=dtype, transformer_options=pose_tf))
+
+            return torch.cat(parts, dim=1)
+
         main_freqs = super().rope_encode(t, h, w, t_start=t_start, steps_t=steps_t, steps_h=steps_h, steps_w=steps_w, device=device, dtype=dtype, transformer_options=transformer_options)
 
         if pose_latents is None:
             return main_freqs
 
-        ref_t_patches = 0
-        if reference_latent is not None:
-            ref_t_patches = (reference_latent.shape[2] + (self.patch_size[0] // 2)) // self.patch_size[0]
-
         F_pose, H_pose, W_pose = pose_latents.shape[-3], pose_latents.shape[-2], pose_latents.shape[-1]
 
         # if pose is at half resolution, scale_y/scale_x=2 stretches the position range to cover the same RoPE extent as the main frames
@@ -1719,12 +1778,16 @@ class SCAILWanModel(WanModel):
 
         return torch.cat([main_freqs, pose_freqs], dim=1)
 
-    def _forward(self, x, timestep, context, clip_fea=None, time_dim_concat=None, transformer_options={}, pose_latents=None, **kwargs):
+    def _forward(self, x, timestep, context, clip_fea=None, time_dim_concat=None, transformer_options={}, pose_latents=None, ref_mask_latents=None, sam_latents=None, **kwargs):
         bs, c, t, h, w = x.shape
         x = comfy.ldm.common_dit.pad_to_patch_size(x, self.patch_size)
 
         if pose_latents is not None:
             pose_latents = comfy.ldm.common_dit.pad_to_patch_size(pose_latents, self.patch_size)
+        if ref_mask_latents is not None:  # SCAIL-2
+            ref_mask_latents = comfy.ldm.common_dit.pad_to_patch_size(ref_mask_latents, self.patch_size)
+        if sam_latents is not None:  # SCAIL-2
+            sam_latents = comfy.ldm.common_dit.pad_to_patch_size(sam_latents, self.patch_size)
 
         t_len = t
         if time_dim_concat is not None:
@@ -1737,5 +1800,15 @@ class SCAILWanModel(WanModel):
             reference_latent = comfy.ldm.common_dit.pad_to_patch_size(kwargs.pop("reference_latent"), self.patch_size)
             t_len += reference_latent.shape[2]
 
-        freqs = self.rope_encode(t_len, h, w, device=x.device, dtype=x.dtype, transformer_options=transformer_options, pose_latents=pose_latents, reference_latent=reference_latent)
-        return self.forward_orig(x, timestep, context, clip_fea=clip_fea, freqs=freqs, transformer_options=transformer_options, pose_latents=pose_latents, reference_latent=reference_latent, **kwargs)[:, :, :t, :h, :w]
+        ref_mask_flag = kwargs.pop("ref_mask_flag", None)  # SCAIL-2
+
+        freqs = self.rope_encode(t_len, h, w, device=x.device, dtype=x.dtype, transformer_options=transformer_options, pose_latents=pose_latents, reference_latent=reference_latent, ref_mask_flag=ref_mask_flag)
+        return self.forward_orig(x, timestep, context, clip_fea=clip_fea, freqs=freqs, transformer_options=transformer_options, pose_latents=pose_latents, reference_latent=reference_latent, ref_mask_latents=ref_mask_latents, sam_latents=sam_latents, **kwargs)[:, :, :t, :h, :w]
+
+
+class SCAIL2WanModel(SCAILWanModel):
+    """SCAIL-2: SCAIL-Preview + an additive binary multi-identity mask stream."""
+
+    def __init__(self, model_type="scail2", patch_size=(1, 2, 2), in_dim=20, mask_in_dim=28, dim=5120, operations=None, device=None, dtype=None, **kwargs):
+        super().__init__(model_type=model_type, patch_size=patch_size, in_dim=in_dim, dim=dim, operations=operations, device=device, dtype=dtype, **kwargs)
+        self.patch_embedding_mask = operations.Conv3d(mask_in_dim, dim, kernel_size=patch_size, stride=patch_size, device=device, dtype=torch.float32)

comfy/lora.py

@@ -326,6 +326,17 @@ def model_lora_keys_unet(model, key_map={}):
                 key_map["transformer.{}".format(key_lora)] = k
                 key_map["lycoris_{}".format(key_lora.replace(".", "_"))] = k #SimpleTuner lycoris format
 
+    if isinstance(model, comfy.model_base.Krea2):
+        diffusers_keys = comfy.utils.krea2_to_diffusers(model.model_config.unet_config, output_prefix="diffusion_model.")
+        for k in diffusers_keys:
+            if k.endswith(".weight"):
+                to = diffusers_keys[k]
+                key_lora = k[:-len(".weight")]
+                key_map["diffusion_model.{}".format(key_lora)] = to
+                key_map["transformer.{}".format(key_lora)] = to
+                key_map["lycoris_{}".format(key_lora.replace(".", "_"))] = to
+                key_map[key_lora] = to
+
     if isinstance(model, comfy.model_base.Lumina2):
         diffusers_keys = comfy.utils.z_image_to_diffusers(model.model_config.unet_config, output_prefix="diffusion_model.")
         for k in diffusers_keys:
@@ -357,6 +368,12 @@ def model_lora_keys_unet(model, key_map={}):
                 key_lora = k[len("diffusion_model."):-len(".weight")]
                 key_map["transformer.{}".format(key_lora)] = k
 
+    if isinstance(model, (comfy.model_base.LTXV, comfy.model_base.LTXAV)):
+        for k in sdk:
+            if k.startswith("diffusion_model.") and k.endswith(".weight"):
+                key_lora = k[len("diffusion_model."):-len(".weight")]
+                key_map["{}".format(key_lora)] = k
+
     return key_map
 
 

comfy/model_base.py

@@ -21,6 +21,7 @@ import comfy.ldm.hunyuan3dv2_1.hunyuandit
 import torch
 import logging
 import comfy.ldm.lightricks.av_model
+import comfy.ldm.lightricks.symmetric_patchifier
 import comfy.context_windows
 from comfy.ldm.modules.diffusionmodules.openaimodel import UNetModel, Timestep
 from comfy.ldm.cascade.stage_c import StageC
@@ -54,7 +55,10 @@ import comfy.ldm.pixeldit.model
 import comfy.ldm.pixeldit.pid
 import comfy.ldm.ace.model
 import comfy.ldm.omnigen.omnigen2
+import comfy.ldm.boogu.model
 import comfy.ldm.qwen_image.model
+import comfy.ldm.ideogram4.model
+import comfy.ldm.krea2.model
 import comfy.ldm.kandinsky5.model
 import comfy.ldm.anima.model
 import comfy.ldm.ace.ace_step15
@@ -64,6 +68,7 @@ import comfy.ldm.ernie.model
 import comfy.ldm.sam3.detector
 import comfy.ldm.hidream_o1.model
 from comfy.ldm.hidream_o1.conditioning import build_extra_conds
+import comfy.ldm.depth_anything_3.model
 
 import comfy.model_management
 import comfy.patcher_extension
@@ -1201,6 +1206,127 @@ class LTXAV(BaseModel):
     def scale_latent_inpaint(self, sigma, noise, latent_image, **kwargs):
         return latent_image
 
+    def map_context_window_to_modalities(self, primary_indices, latent_shapes, dim):
+        result = [primary_indices]
+        if len(latent_shapes) < 2:
+            return result
+
+        video_total = latent_shapes[0][dim]
+
+        for i in range(1, len(latent_shapes)):
+            mod_total = latent_shapes[i][dim]
+            # Map each primary index to its proportional range of modality indices and
+            # concatenate in order. Preserves wrapped/strided geometry so the modality
+            # attends to the same temporal regions as the primary window.
+            mod_indices = []
+            seen = set()
+            for v_idx in primary_indices:
+                a_start = min(int(round(v_idx * mod_total / video_total)), mod_total - 1)
+                a_end = min(int(round((v_idx + 1) * mod_total / video_total)), mod_total)
+                if a_end <= a_start:
+                    a_end = a_start + 1
+                for a in range(a_start, a_end):
+                    if a not in seen:
+                        seen.add(a)
+                        mod_indices.append(a)
+            result.append(mod_indices)
+
+        return result
+
+    @staticmethod
+    def _get_guide_entries(conds):
+        for cond_list in conds:
+            if cond_list is None:
+                continue
+            for cond_dict in cond_list:
+                model_conds = cond_dict.get('model_conds', {})
+                entries = model_conds.get('guide_attention_entries')
+                if entries is not None and hasattr(entries, 'cond') and entries.cond:
+                    return entries.cond
+        return None
+
+    def resize_cond_for_context_window(self, cond_key, cond_value, window, x_in, device, retain_index_list=[]):
+        # Audio denoise mask — slice using audio modality window
+        if cond_key == "audio_denoise_mask" and hasattr(window, 'modality_windows') and window.modality_windows:
+            audio_window = window.modality_windows.get(1)
+            if audio_window is not None and hasattr(cond_value, "cond") and isinstance(cond_value.cond, torch.Tensor):
+                sliced = audio_window.get_tensor(cond_value.cond, device, dim=2)
+                return cond_value._copy_with(sliced)
+
+        # Video denoise mask — split into video + guide portions, slice each
+        if cond_key == "denoise_mask" and hasattr(cond_value, "cond") and isinstance(cond_value.cond, torch.Tensor):
+            cond_tensor = cond_value.cond
+            guide_count = cond_tensor.size(window.dim) - x_in.size(window.dim)
+            if guide_count > 0:
+                T_video = x_in.size(window.dim)
+                video_mask = cond_tensor.narrow(window.dim, 0, T_video)
+                guide_mask = cond_tensor.narrow(window.dim, T_video, guide_count)
+                sliced_video = window.get_tensor(video_mask, device, retain_index_list=retain_index_list)
+                suffix_indices = window.guide_frames_indices
+                if suffix_indices:
+                    idx = tuple([slice(None)] * window.dim + [suffix_indices])
+                    sliced_guide = guide_mask[idx].to(device)
+                    return cond_value._copy_with(torch.cat([sliced_video, sliced_guide], dim=window.dim))
+                else:
+                    return cond_value._copy_with(sliced_video)
+
+        # Keyframe indices — regenerate pixel coords for window, select guide positions
+        if cond_key == "keyframe_idxs":
+            kf_local_pos = window.guide_kf_local_positions
+            if not kf_local_pos:
+                return cond_value._copy_with(cond_value.cond[:, :, :0, :])  # empty
+            H, W = x_in.shape[3], x_in.shape[4]
+            window_len = len(window.index_list)
+            # account for causal_window_fix anchor in coord space size
+            anchor_idx = getattr(window, 'causal_anchor_index', None)
+            if anchor_idx is not None and anchor_idx >= 0:
+                window_len += 1
+            patchifier = self.diffusion_model.patchifier
+            latent_coords = patchifier.get_latent_coords(window_len, H, W, 1, cond_value.cond.device)
+            scale_factors = self.diffusion_model.vae_scale_factors
+            pixel_coords = comfy.ldm.lightricks.symmetric_patchifier.latent_to_pixel_coords(
+                latent_coords,
+                scale_factors,
+                causal_fix=self.diffusion_model.causal_temporal_positioning)
+            tokens = []
+            for pos in kf_local_pos:
+                tokens.extend(range(pos * H * W, (pos + 1) * H * W))
+            pixel_coords = pixel_coords[:, :, tokens, :]
+
+            # Adjust spatial end positions for dilated (downscaled) guides.
+            # Each guide entry may have a different downscale factor; expand the
+            # per-entry factor to cover all tokens belonging to that entry.
+            downscale_factors = window.guide_downscale_factors
+            overlap_info = window.guide_overlap_info
+            if downscale_factors:
+                per_token_factor = []
+                for (entry_idx, overlap_count), dsf in zip(overlap_info, downscale_factors):
+                    per_token_factor.extend([dsf] * (overlap_count * H * W))
+                factor_tensor = torch.tensor(per_token_factor, device=pixel_coords.device, dtype=pixel_coords.dtype)
+                spatial_end_offset = (factor_tensor.unsqueeze(0).unsqueeze(0).unsqueeze(-1) - 1) * torch.tensor(
+                    scale_factors[1:], device=pixel_coords.device, dtype=pixel_coords.dtype,
+                ).view(1, -1, 1, 1)
+                pixel_coords[:, 1:, :, 1:] += spatial_end_offset
+
+            B = cond_value.cond.shape[0]
+            if B > 1:
+                pixel_coords = pixel_coords.expand(B, -1, -1, -1)
+            return cond_value._copy_with(pixel_coords)
+
+        # Guide attention entries — adjust per-guide counts based on window overlap
+        if cond_key == "guide_attention_entries":
+            overlap_info = window.guide_overlap_info
+            H, W = x_in.shape[3], x_in.shape[4]
+            new_entries = []
+            for entry_idx, overlap_count in overlap_info:
+                e = cond_value.cond[entry_idx]
+                new_entries.append({**e,
+                    "pre_filter_count": overlap_count * H * W,
+                    "latent_shape": [overlap_count, H, W]})
+            return cond_value._copy_with(new_entries)
+
+        return None
+
 class HunyuanVideo(BaseModel):
     def __init__(self, model_config, model_type=ModelType.FLOW, device=None):
         super().__init__(model_config, model_type, device=device, unet_model=comfy.ldm.hunyuan_video.model.HunyuanVideo)
@@ -1517,8 +1643,26 @@ class WAN21(BaseModel):
         if reference_latents is not None:
             out['reference_latent'] = comfy.conds.CONDRegular(self.process_latent_in(reference_latents[-1])[:, :, 0])
 
+        # In-context reference conditioning (Bernini)
+        context_latents = kwargs.get("context_latents", None)
+        if context_latents is not None:
+            out['context_latents'] = comfy.conds.CONDList([self.process_latent_in(l) for l in context_latents])
+
         return out
 
+    def resize_cond_for_context_window(self, cond_key, cond_value, window, x_in, device, retain_index_list=[]):
+        # In-context cond slicing (Bernini)
+        if cond_key == "context_latents" and isinstance(getattr(cond_value, "cond", None), list):
+            dim = window.dim
+            out = []
+            for lat in cond_value.cond:
+                if lat.ndim > dim and lat.shape[dim] > 1 and lat.shape[dim] == x_in.shape[dim]:
+                    out.append(window.get_tensor(lat, device, dim=dim, retain_index_list=retain_index_list))
+                else:
+                    out.append(lat.to(device))
+            return cond_value._copy_with(out)
+        return super().resize_cond_for_context_window(cond_key, cond_value, window, x_in, device, retain_index_list=retain_index_list)
+
 
 class WAN21_CausalAR(WAN21):
     def __init__(self, model_config, model_type=ModelType.FLOW, device=None):
@@ -1727,10 +1871,14 @@ class WAN21_SCAIL(WAN21):
 
         reference_latents = kwargs.get("reference_latents", None)
         if reference_latents is not None:
-            ref_latent = self.process_latent_in(reference_latents[-1])
-            ref_mask = torch.ones_like(ref_latent[:, :4])
-            ref_latent = torch.cat([ref_latent, ref_mask], dim=1)
-            out['reference_latent'] = comfy.conds.CONDRegular(ref_latent)
+            # SCAIL-2 multi-reference: reference_latents[0] is the primary ref, [1:] are additional
+            # references. Stack as [additional..., primary] so the primary stays adjacent to the video.
+            ordered = list(reference_latents[1:]) + list(reference_latents[:1])
+            stacked = []
+            for lat in ordered:
+                lat = self.process_latent_in(lat)
+                stacked.append(torch.cat([lat, torch.ones_like(lat[:, :4])], dim=1))
+            out['reference_latent'] = comfy.conds.CONDRegular(torch.cat(stacked, dim=2))
 
         pose_latents = kwargs.get("pose_video_latent", None)
         if pose_latents is not None:
@@ -1753,6 +1901,99 @@ class WAN21_SCAIL(WAN21):
 
         return out
 
+class WAN21_SCAIL2(WAN21_SCAIL):
+    """SCAIL-2: SCAIL-Preview + an additive binary multi-identity mask stream."""
+
+    def __init__(self, model_config, model_type=ModelType.FLOW, image_to_video=False, device=None):
+        super(WAN21, self).__init__(model_config, model_type, device=device, unet_model=comfy.ldm.wan.model.SCAIL2WanModel)
+        self.memory_usage_factor_conds = ("reference_latent", "pose_latents", "ref_mask_latents", "sam_latents")
+        self.memory_usage_shape_process = {
+            "pose_latents": lambda shape: [shape[0], shape[1], 1.5, shape[-2], shape[-1]],
+            "sam_latents":  lambda shape: [shape[0], shape[1], 1.5, shape[-2], shape[-1]],
+        }
+        self.image_to_video = image_to_video
+
+    def extra_conds(self, **kwargs):
+        out = super().extra_conds(**kwargs)
+
+        driving_mask_28ch = kwargs.get("driving_mask_28ch", None)
+        if driving_mask_28ch is not None:
+            out['sam_latents'] = comfy.conds.CONDRegular(driving_mask_28ch.movedim(1, 2).contiguous())
+
+        # ref_mask_28ch holds one identity mask per stacked reference frame (additional refs first, then the primary ref), followed by zeros over the video frames.
+        ref_mask_28ch = kwargs.get("ref_mask_28ch", None)
+        if ref_mask_28ch is not None:
+            out['ref_mask_latents'] = comfy.conds.CONDRegular(ref_mask_28ch.movedim(1, 2).contiguous())
+
+        ref_mask_flag = kwargs.get("ref_mask_flag", None)
+        if ref_mask_flag is not None:
+            out['ref_mask_flag'] = comfy.conds.CONDConstant(ref_mask_flag)
+
+        return out
+
+    def extra_conds_shapes(self, **kwargs):
+        out = super().extra_conds_shapes(**kwargs)
+        driving_mask_28ch = kwargs.get("driving_mask_28ch", None)
+        if driving_mask_28ch is not None:
+            s = driving_mask_28ch.shape
+            out['sam_latents'] = [s[0], 28, s[1], s[3], s[4]]
+        ref_mask_28ch = kwargs.get("ref_mask_28ch", None)
+        if ref_mask_28ch is not None:
+            s = ref_mask_28ch.shape
+            out['ref_mask_latents'] = [s[0], 28, s[1], s[3], s[4]]
+        return out
+
+    def resize_cond_for_context_window(self, cond_key, cond_value, window, x_in, device, retain_index_list=[]):
+        if cond_key in ("sam_latents", "pose_latents"):
+            # Return sliced view omitting retain_index_list
+            return comfy.context_windows.slice_cond(cond_value, window, x_in, device, temporal_dim=2, temporal_offset=0)
+        if cond_key == "ref_mask_latents" and hasattr(cond_value, "cond") and isinstance(cond_value.cond, torch.Tensor):
+            # The ref mask is N leading ref frames padded with frames of zeros, so just grab the first frames for all windows
+            full_ref_mask = cond_value.cond
+            video_frame_count = x_in.shape[2]
+            ref_frame_count = full_ref_mask.shape[2] - video_frame_count
+            if ref_frame_count < 1:
+                return None
+            window_length = len(window.index_list)
+
+            # Account for the causal anchor frame if it exists
+            anchor_index = getattr(window, "causal_anchor_index", None)
+            if anchor_index is not None and anchor_index >= 0:
+                window_length += 1
+
+            window_ref_mask = full_ref_mask[:, :, :window_length + ref_frame_count].to(device)
+            return cond_value._copy_with(window_ref_mask)
+
+        return super().resize_cond_for_context_window(cond_key, cond_value, window, x_in, device, retain_index_list=retain_index_list)
+
+    def concat_cond(self, **kwargs):
+        # The 4 extra channels are the history_mask (1 at clean-anchor frames).
+        noise = kwargs.get("noise", None)
+        extra_channels = self.diffusion_model.patch_embedding.weight.shape[1] - noise.shape[1]
+        if extra_channels != 4:
+            return super().concat_cond(**kwargs)
+
+        mask = kwargs.get("concat_mask", kwargs.get("denoise_mask", None))
+        if mask is None:
+            return torch.zeros_like(noise)[:, :4]
+
+        device = kwargs["device"]
+        if mask.shape[1] != 4:
+            mask = torch.mean(mask, dim=1, keepdim=True)
+        mask = 1.0 - mask
+        mask = utils.common_upscale(mask.to(device), noise.shape[-1], noise.shape[-2], "bilinear", "center")
+        if mask.shape[-3] < noise.shape[-3]:
+            mask = torch.nn.functional.pad(mask, (0, 0, 0, 0, 0, noise.shape[-3] - mask.shape[-3]), mode='constant', value=0)
+        if mask.shape[1] == 1:
+            mask = mask.repeat(1, 4, 1, 1, 1)
+        mask = utils.resize_to_batch_size(mask, noise.shape[0])
+        return mask
+
+    def scale_latent_inpaint(self, sigma, noise, latent_image, **kwargs):
+        # Hold anchor constant across all sigmas instead of base sigma*noise + (1-sigma)*latent_image.
+        return latent_image
+
+
 class WAN22_WanDancer(WAN21):
     def __init__(self, model_config, model_type=ModelType.FLOW, image_to_video=True, device=None):
         super(WAN21, self).__init__(model_config, model_type, device=device, unet_model=comfy.ldm.wan.model_wandancer.WanDancerModel)
@@ -1986,6 +2227,11 @@ class Omnigen2(BaseModel):
             out['ref_latents'] = list([1, 16, sum(map(lambda a: math.prod(a.size()), ref_latents)) // 16])
         return out
 
+class Boogu(Omnigen2):
+    def __init__(self, model_config, model_type=ModelType.FLOW, device=None):
+        super(Omnigen2, self).__init__(model_config, model_type, device=device, unet_model=comfy.ldm.boogu.model.BooguTransformer2DModel)
+        self.memory_usage_factor_conds = ("ref_latents",)
+
 class QwenImage(BaseModel):
     def __init__(self, model_config, model_type=ModelType.FLUX, device=None):
         super().__init__(model_config, model_type, device=device, unet_model=comfy.ldm.qwen_image.model.QwenImageTransformer2DModel)
@@ -2018,6 +2264,32 @@ class QwenImage(BaseModel):
             out['ref_latents'] = list([1, 16, sum(map(lambda a: math.prod(a.size()), ref_latents)) // 16])
         return out
 
+class Ideogram4(BaseModel):
+    def __init__(self, model_config, model_type=ModelType.FLOW, device=None):
+        super().__init__(model_config, model_type, device=device, unet_model=comfy.ldm.ideogram4.model.Ideogram4Transformer2DModel)
+
+    def extra_conds(self, **kwargs):
+        out = super().extra_conds(**kwargs)
+        attention_mask = kwargs.get("attention_mask", None)
+        if attention_mask is not None:
+            if torch.numel(attention_mask) != attention_mask.sum():
+                out['attention_mask'] = comfy.conds.CONDRegular(attention_mask)
+        cross_attn = kwargs.get("cross_attn", None)
+        if cross_attn is not None:
+            out['c_crossattn'] = comfy.conds.CONDRegular(cross_attn)
+        return out
+
+class Krea2(BaseModel):
+    def __init__(self, model_config, model_type=ModelType.FLUX, device=None):
+        super().__init__(model_config, model_type, device=device, unet_model=comfy.ldm.krea2.model.SingleStreamDiT)
+
+    def extra_conds(self, **kwargs):
+        out = super().extra_conds(**kwargs)
+        cross_attn = kwargs.get("cross_attn", None)
+        if cross_attn is not None:
+            out['c_crossattn'] = comfy.conds.CONDRegular(cross_attn)
+        return out
+
 class HunyuanImage21(BaseModel):
     def __init__(self, model_config, model_type=ModelType.FLOW, device=None):
         super().__init__(model_config, model_type, device=device, unet_model=comfy.ldm.hunyuan_video.model.HunyuanVideo)
@@ -2211,6 +2483,12 @@ class RT_DETR_v4(BaseModel):
     def __init__(self, model_config, model_type=ModelType.FLOW, device=None):
         super().__init__(model_config, model_type, device=device, unet_model=comfy.ldm.rt_detr.rtdetr_v4.RTv4)
 
+
+class DepthAnything3(BaseModel):
+    def __init__(self, model_config, model_type=ModelType.FLOW, device=None):
+        super().__init__(model_config, model_type, device=device,
+                         unet_model=comfy.ldm.depth_anything_3.model.DepthAnything3Net)
+
 class ErnieImage(BaseModel):
     def __init__(self, model_config, model_type=ModelType.FLOW, device=None):
         super().__init__(model_config, model_type, device=device, unet_model=comfy.ldm.ernie.model.ErnieImageModel)

comfy/model_detection.py

@@ -313,6 +313,10 @@ def detect_unet_config(state_dict, key_prefix, metadata=None):
                     dit_config["use_x0"] = True
                 else:
                     dit_config["use_x0"] = False
+                if "{}__sequential__".format(key_prefix) in state_dict_keys: # sequential txt_ids
+                    dit_config["use_sequential_txt_ids"] = True
+                else:
+                    dit_config["use_sequential_txt_ids"] = False
         else:
             dit_config["guidance_embed"] = "{}guidance_in.in_layer.weight".format(key_prefix) in state_dict_keys
             dit_config["yak_mlp"] = '{}double_blocks.0.img_mlp.gate_proj.weight'.format(key_prefix) in state_dict_keys
@@ -626,6 +630,8 @@ def detect_unet_config(state_dict, key_prefix, metadata=None):
             dit_config["model_type"] = "humo"
         elif '{}face_adapter.fuser_blocks.0.k_norm.weight'.format(key_prefix) in state_dict_keys:
             dit_config["model_type"] = "animate"
+        elif '{}patch_embedding_mask.weight'.format(key_prefix) in state_dict_keys:
+            dit_config["model_type"] = "scail2"
         elif '{}patch_embedding_pose.weight'.format(key_prefix) in state_dict_keys:
             dit_config["model_type"] = "scail"
         elif '{}patch_embedding_global.weight'.format(key_prefix) in state_dict_keys:
@@ -755,6 +761,16 @@ def detect_unet_config(state_dict, key_prefix, metadata=None):
 
         return dit_config
 
+    if '{}double_stream_layers.0.img_instruct_attn.processor.img_to_q.weight'.format(key_prefix) in state_dict_keys:  # Boogu-Image (OmniGen2 derivative + dual-stream stage)
+        dit_config = {}
+        dit_config["image_model"] = "boogu"
+        dit_config["hidden_size"] = state_dict['{}x_embedder.weight'.format(key_prefix)].shape[0]
+        dit_config["num_layers"] = count_blocks(state_dict_keys, '{}single_stream_layers.'.format(key_prefix) + '{}.')
+        dit_config["num_double_stream_layers"] = count_blocks(state_dict_keys, '{}double_stream_layers.'.format(key_prefix) + '{}.')
+        dit_config["num_refiner_layers"] = count_blocks(state_dict_keys, '{}noise_refiner.'.format(key_prefix) + '{}.')
+        dit_config["instruction_feat_dim"] = state_dict['{}time_caption_embed.caption_embedder.0.weight'.format(key_prefix)].shape[0]
+        return dit_config
+
     if '{}time_caption_embed.timestep_embedder.linear_1.bias'.format(key_prefix) in state_dict_keys:  # Omnigen2
         dit_config = {}
         dit_config["image_model"] = "omnigen2"
@@ -811,6 +827,28 @@ def detect_unet_config(state_dict, key_prefix, metadata=None):
             dit_config["default_ref_method"] = "negative_index"
         return dit_config
 
+    if '{}embed_image_indicator.weight'.format(key_prefix) in state_dict_keys:  # Ideogram 4
+        dit_config = {}
+        dit_config["image_model"] = "ideogram4"
+        dit_config["in_channels"] = state_dict['{}input_proj.weight'.format(key_prefix)].shape[1]
+        dit_config["num_layers"] = count_blocks(state_dict_keys, '{}layers.'.format(key_prefix) + '{}.')
+        return dit_config
+
+    if '{}txtfusion.projector.weight'.format(key_prefix) in state_dict_keys:  # Krea 2 (K2)
+        dit_config = {}
+        dit_config["image_model"] = "krea2"
+        head_dim = 128
+        first_w = state_dict['{}first.weight'.format(key_prefix)]  # (features, channels*patch^2)
+        dit_config["features"] = first_w.shape[0]
+        dit_config["channels"] = first_w.shape[1] // (2 * 2)  # patch=2
+        dit_config["patch"] = 2
+        dit_config["layers"] = count_blocks(state_dict_keys, '{}blocks.'.format(key_prefix) + '{}.')
+        dit_config["heads"] = state_dict['{}blocks.0.attn.wq.weight'.format(key_prefix)].shape[0] // head_dim
+        dit_config["kvheads"] = state_dict['{}blocks.0.attn.wk.weight'.format(key_prefix)].shape[0] // head_dim
+        dit_config["txtlayers"] = state_dict['{}txtfusion.projector.weight'.format(key_prefix)].shape[1]
+        dit_config["txtdim"] = state_dict['{}txtfusion.layerwise_blocks.0.prenorm.scale'.format(key_prefix)].shape[0]
+        return dit_config
+
     if '{}visual_transformer_blocks.0.cross_attention.key_norm.weight'.format(key_prefix) in state_dict_keys: # Kandinsky 5
         dit_config = {}
         model_dim = state_dict['{}visual_embeddings.in_layer.bias'.format(key_prefix)].shape[0]
@@ -849,6 +887,95 @@ def detect_unet_config(state_dict, key_prefix, metadata=None):
         dit_config["enc_h"] = state_dict['{}encoder.pan_blocks.1.cv4.conv.weight'.format(key_prefix)].shape[0]
         return dit_config
 
+    # Depth Anything 3 (repackaged to ComfyUI's native Dinov2Model layout via scripts/convert_da3.py)
+    if '{}backbone.embeddings.patch_embeddings.projection.weight'.format(key_prefix) in state_dict_keys:
+        dit_config = {}
+        dit_config["image_model"] = "DepthAnything3"
+
+        patch_w = state_dict['{}backbone.embeddings.patch_embeddings.projection.weight'.format(key_prefix)]
+        embed_dim = patch_w.shape[0]
+        depth = count_blocks(state_dict_keys, '{}backbone.encoder.layer.'.format(key_prefix) + '{}.')
+
+        # Backbone preset is determined by embed_dim (matches vits/vitb/vitl/vitg).
+        backbone_name = {384: "vits", 768: "vitb", 1024: "vitl", 1536: "vitg"}.get(embed_dim)
+        if backbone_name is None:
+            return None
+        dit_config["backbone_name"] = backbone_name
+
+        # Detect DA3 extensions on top of vanilla DINOv2.
+        has_camera_token = '{}backbone.embeddings.camera_token'.format(key_prefix) in state_dict_keys
+        # qk-norm shows up as `attention.q_norm.weight` on enabled blocks.
+        qknorm_indices = [
+            i for i in range(depth)
+            if '{}backbone.encoder.layer.{}.attention.q_norm.weight'.format(key_prefix, i) in state_dict_keys
+        ]
+        qknorm_start = qknorm_indices[0] if qknorm_indices else -1
+
+        # The DA3 main-series configs always set alt_start == qknorm_start == rope_start.
+        # cat_token=True is implied by the presence of camera_token.
+        if has_camera_token:
+            dit_config["alt_start"] = qknorm_start
+            dit_config["rope_start"] = qknorm_start
+            dit_config["qknorm_start"] = qknorm_start
+            dit_config["cat_token"] = True
+        else:
+            dit_config["alt_start"] = -1
+            dit_config["rope_start"] = -1
+            dit_config["qknorm_start"] = -1
+            dit_config["cat_token"] = False
+
+        # Detect head type and config.
+        has_aux = '{}head.scratch.refinenet1_aux.out_conv.weight'.format(key_prefix) in state_dict_keys
+        dit_config["head_dim_in"] = state_dict['{}head.projects.0.weight'.format(key_prefix)].shape[1]
+        dit_config["head_features"] = state_dict['{}head.scratch.refinenet1.out_conv.weight'.format(key_prefix)].shape[0]
+        dit_config["head_out_channels"] = [
+            state_dict['{}head.projects.{}.weight'.format(key_prefix, i)].shape[0]
+            for i in range(4)
+        ]
+        if has_aux:
+            # DualDPT: dim_in = 2 * embed_dim (because cat_token doubles token width).
+            dit_config["head_type"] = "dualdpt"
+            dit_config["head_output_dim"] = 2
+            dit_config["head_use_sky_head"] = False
+        else:
+            dit_config["head_type"] = "dpt"
+            dit_config["head_output_dim"] = state_dict[
+                '{}head.scratch.output_conv2.2.weight'.format(key_prefix)
+            ].shape[0]
+            dit_config["head_use_sky_head"] = (
+                '{}head.scratch.sky_output_conv2.0.weight'.format(key_prefix) in state_dict_keys
+            )
+
+        # out_layers: hard-coded per upstream YAML config (depth-aware default).
+        if depth >= 24:
+            # vitl: depths used vary between DA3-Large (DualDPT) and Mono/Metric (DPT).
+            if has_aux:
+                dit_config["out_layers"] = [11, 15, 19, 23]
+            else:
+                dit_config["out_layers"] = [4, 11, 17, 23]
+        else:
+            # vits/vitb: 12 blocks
+            dit_config["out_layers"] = [5, 7, 9, 11]
+
+        # Camera encoder/decoder presence (multi-view + pose path).
+        has_cam_enc = '{}cam_enc.token_norm.weight'.format(key_prefix) in state_dict_keys
+        has_cam_dec = '{}cam_dec.fc_t.weight'.format(key_prefix) in state_dict_keys
+        dit_config["has_cam_enc"] = has_cam_enc
+        dit_config["has_cam_dec"] = has_cam_dec
+        if has_cam_enc:
+            cam_enc_w = state_dict.get(
+                '{}cam_enc.pose_branch.fc2.weight'.format(key_prefix)
+            )
+            if cam_enc_w is not None:
+                dit_config["cam_dim_out"] = cam_enc_w.shape[0]
+        if has_cam_dec:
+            cam_dec_w = state_dict.get(
+                '{}cam_dec.fc_t.weight'.format(key_prefix)
+            )
+            if cam_dec_w is not None:
+                dit_config["cam_dec_dim_in"] = cam_dec_w.shape[1]
+        return dit_config
+
     if '{}layers.0.mlp.linear_fc2.weight'.format(key_prefix) in state_dict_keys: # Ernie Image
         dit_config = {}
         dit_config["image_model"] = "ernie"

comfy/model_management.py

@@ -534,8 +534,10 @@ try:
 except:
     pass
 
-if torch.cuda.is_available() and torch.backends.cudnn.is_available() and PerformanceFeature.AutoTune in args.fast:
-    torch.backends.cudnn.benchmark = True
+
+def set_cudnn_benchmark():
+    if torch.cuda.is_available() and torch.backends.cudnn.is_available():
+        torch.backends.cudnn.benchmark = PerformanceFeature.AutoTune in args.fast
 
 try:
     if torch_version_numeric >= (2, 5):
@@ -641,6 +643,8 @@ def free_pins(size, evict_active=False):
     return freed_total
 
 def ensure_pin_budget(size, evict_active=False):
+    if args.high_ram:
+        return True
     if args.fast_disk:
         shortfall = TOTAL_PINNED_MEMORY + size - MAX_PINNED_MEMORY
     else:
@@ -651,8 +655,7 @@ def ensure_pin_budget(size, evict_active=False):
     to_free = shortfall + PIN_PRESSURE_HYSTERESIS
     return free_pins(to_free, evict_active=evict_active) >= shortfall
 
-def ensure_pin_registerable(size, evict_active=True):
-    shortfall = TOTAL_PINNED_MEMORY + size - MAX_PINNED_MEMORY
+def free_registrations(shortfall, evict_active=True):
     if MAX_PINNED_MEMORY <= 0:
         return False
     if shortfall <= 0:
@@ -674,6 +677,9 @@ def ensure_pin_registerable(size, evict_active=True):
                     return True
     return shortfall <= REGISTERABLE_PIN_HYSTERESIS
 
+def ensure_pin_registerable(size, evict_active=True):
+    return free_registrations(TOTAL_PINNED_MEMORY + size - MAX_PINNED_MEMORY, evict_active=evict_active)
+
 class LoadedModel:
     def __init__(self, model: ModelPatcher):
         self._set_model(model)
@@ -956,8 +962,6 @@ def loaded_models(only_currently_used=False):
 def cleanup_models_gc():
     do_gc = False
 
-    reset_cast_buffers()
-
     for i in range(len(current_loaded_models)):
         cur = current_loaded_models[i]
         if cur.is_dead():
@@ -1494,6 +1498,8 @@ if not args.disable_pinned_memory:
 PINNING_ALLOWED_TYPES = set(["Tensor", "Parameter", "QuantizedTensor"])
 
 def pinned_hostbuf_size(size):
+    if args.high_ram:
+        return max(0, int(size * 2))
     return max(0, int(min(size, MAX_PINNED_MEMORY) * 2))
 
 def discard_cuda_async_error():

comfy/model_patcher.py

@@ -379,10 +379,11 @@ class ModelPatcher:
     def get_clone_model_override(self):
         return self.model, (self.backup, self.backup_buffers, self.object_patches_backup, self.pinned)
 
-    def clone(self, disable_dynamic=False, model_override=None):
+    def clone(self, disable_dynamic=False, model_override=None, force_deepcopy=False):
         class_ = self.__class__
-        if self.is_dynamic() and disable_dynamic:
-            class_ = ModelPatcher
+        if self.is_dynamic() and disable_dynamic or force_deepcopy:
+            if self.is_dynamic() and disable_dynamic:
+                class_ = ModelPatcher
             if model_override is None:
                 if self.cached_patcher_init is None:
                     raise RuntimeError("Cannot create non-dynamic delegate: cached_patcher_init is not initialized.")

comfy/multigpu.py

@@ -54,6 +54,8 @@ class MultiGPUThreadPool:
             try:
                 result = fn(*args, **kwargs)
                 result_q.put((result, None))
+            except comfy.model_management.InterruptProcessingException as e:
+                result_q.put((None, e))
             except Exception as e:
                 result_q.put((None, e))
 

comfy/ops.py

@@ -180,7 +180,7 @@ def cast_modules_with_vbar(comfy_modules, dtype, device, bias_dtype, non_blockin
             if pin is not None:
                 cast_maybe_lowvram_patch([pin], dest, offload_stream)
                 return
-            if signature is None:
+            if signature is None or args.high_ram:
                 comfy.pinned_memory.pin_memory(m, subset=subset, size=size)
                 pin = comfy.pinned_memory.get_pin(m, subset=subset)
             cast_maybe_lowvram_patch(source, pin, offload_stream, xfer_dest2=dest)
@@ -256,7 +256,7 @@ def resolve_cast_module_with_vbar(s, dtype, device, bias_dtype, compute_dtype, w
             if (want_requant and len(fns) == 0 or update_weight):
                 seed = comfy.utils.string_to_seed(s.seed_key)
                 if isinstance(orig, QuantizedTensor):
-                    y = QuantizedTensor.from_float(x, s.layout_type, scale="recalculate", stochastic_rounding=seed)
+                    y = orig.requantize_from_float(x, scale="recalculate", stochastic_rounding=seed)
                 else:
                     y = comfy.float.stochastic_rounding(x, orig.dtype, seed=seed)
             if want_requant and len(fns) == 0:
@@ -299,21 +299,21 @@ def cast_bias_weight(s, input=None, dtype=None, device=None, bias_dtype=None, of
 
     non_blocking = comfy.model_management.device_supports_non_blocking(device)
 
-    if hasattr(s, "_v"):
+    if hasattr(s, "_v") and comfy.model_management.is_device_cpu(device):
 
         #vbar doesn't support CPU weights, but some custom nodes have weird paths
         #that might switch the layer to the CPU and expect it to work. We have to take
         #a clone conservatively as we are mmapped and some SFT files are packed misaligned
         #If you are a custom node author reading this, please move your layer to the GPU
         #or declare your ModelPatcher as CPU in the first place.
-        if comfy.model_management.is_device_cpu(device):
-            materialize_meta_param(s, ["weight", "bias"])
-            weight = s.weight.to(dtype=dtype, copy=True)
-            if isinstance(weight, QuantizedTensor):
-                weight = weight.dequantize()
-            bias = s.bias.to(dtype=bias_dtype, copy=True) if s.bias is not None else None
-            return format_return((weight, bias, (None, None, None)), offloadable)
+        materialize_meta_param(s, ["weight", "bias"])
+        weight = s.weight.to(dtype=dtype, copy=True)
+        if isinstance(weight, QuantizedTensor):
+            weight = weight.dequantize()
+        bias = s.bias.to(dtype=bias_dtype, copy=True) if s.bias is not None else None
+        return format_return((weight, bias, (None, None, None)), offloadable)
 
+    elif hasattr(s, "_v") and s.weight.device != device:
         prefetched = hasattr(s, "_prefetch")
         offload_stream = None
         offload_device = None
@@ -1089,6 +1089,19 @@ def _load_quantized_module(module, super_load, state_dict, prefix, local_metadat
             if ts is None or bs is None:
                 raise ValueError(f"Missing NVFP4 scales for layer {layer_name}")
             scales = {"scale": ts, "block_scale": bs}
+        elif module.quant_format == "int8_tensorwise":
+            scale = pop_scale("weight_scale")
+            if scale is None:
+                raise ValueError(f"Missing INT8 weight scale for layer {layer_name}")
+            scales = {"scale": scale}
+            params_conf = layer_conf.get("params", {})
+            if not isinstance(params_conf, dict):
+                params_conf = {}
+            if layer_conf.get("convrot", params_conf.get("convrot", False)):
+                scales["convrot"] = True
+                scales["convrot_groupsize"] = int(
+                    layer_conf.get("convrot_groupsize", params_conf.get("convrot_groupsize", 256))
+                )
         else:
             raise ValueError(f"Unsupported quantization format: {module.quant_format}")
 
@@ -1131,6 +1144,10 @@ def _quantized_weight_state_dict(module, sd, prefix, extra_quant_conf=None, extr
         quant_conf = {"format": module.quant_format}
         if getattr(module, '_full_precision_mm_config', False):
             quant_conf["full_precision_matrix_mult"] = True
+        params = getattr(module.weight, "_params", None)
+        if module.quant_format == "int8_tensorwise" and getattr(params, "convrot", False):
+            quant_conf["convrot"] = True
+            quant_conf["convrot_groupsize"] = getattr(params, "convrot_groupsize", 256)
         if extra_quant_conf:
             quant_conf.update(extra_quant_conf)
         sd[f"{prefix}comfy_quant"] = torch.tensor(list(json.dumps(quant_conf).encode("utf-8")), dtype=torch.uint8)
@@ -1183,8 +1200,33 @@ def mixed_precision_ops(quant_config={}, compute_dtype=torch.bfloat16, full_prec
             def _forward(self, input, weight, bias):
                 return torch.nn.functional.linear(input, weight, bias)
 
-            def forward_comfy_cast_weights(self, input, compute_dtype=None, want_requant=False):
-                weight, bias, offload_stream = cast_bias_weight(self, input, offloadable=True, compute_dtype=compute_dtype, want_requant=want_requant)
+            def forward_comfy_cast_weights(
+                self,
+                input,
+                compute_dtype=None,
+                want_requant=False,
+                weight_only_quant=False,
+            ):
+                if weight_only_quant:
+                    weight, bias, offload_stream = cast_bias_weight(
+                        self,
+                        input=None,
+                        dtype=self.weight.dtype,
+                        device=input.device,
+                        bias_dtype=input.dtype,
+                        offloadable=True,
+                        compute_dtype=compute_dtype,
+                        want_requant=True,
+                    )
+                    weight = weight.to(dtype=input.dtype)
+                else:
+                    weight, bias, offload_stream = cast_bias_weight(
+                        self,
+                        input,
+                        offloadable=True,
+                        compute_dtype=compute_dtype,
+                        want_requant=want_requant,
+                    )
                 x = self._forward(input, weight, bias)
                 uncast_bias_weight(self, weight, bias, offload_stream)
                 return x
@@ -1203,9 +1245,10 @@ def mixed_precision_ops(quant_config={}, compute_dtype=torch.bfloat16, full_prec
                     not getattr(self, 'comfy_force_cast_weights', False) and
                     len(self.weight_function) == 0 and len(self.bias_function) == 0
                 )
+                quantize_input = QUANT_ALGOS.get(getattr(self, 'quant_format', None), {}).get("quantize_input", True)
 
                 # Training path: quantized forward with compute_dtype backward via autograd function
-                if (input.requires_grad and _use_quantized):
+                if (input.requires_grad and _use_quantized and quantize_input):
 
                     weight, bias, offload_stream = cast_bias_weight(
                         self,
@@ -1227,7 +1270,7 @@ def mixed_precision_ops(quant_config={}, compute_dtype=torch.bfloat16, full_prec
                     return output
 
                 # Inference path (unchanged)
-                if _use_quantized:
+                if _use_quantized and quantize_input:
 
                     # Reshape 3D tensors to 2D for quantization (needed for NVFP4 and others)
                     input_reshaped = input.reshape(-1, input_shape[2]) if input.ndim == 3 else input
@@ -1241,7 +1284,13 @@ def mixed_precision_ops(quant_config={}, compute_dtype=torch.bfloat16, full_prec
                             scale = comfy.model_management.cast_to_device(scale, input.device, None)
                         input = QuantizedTensor.from_float(input_reshaped, self.layout_type, scale=scale)
 
-                output = self.forward_comfy_cast_weights(input, compute_dtype, want_requant=isinstance(input, QuantizedTensor))
+                weight_only_quant = _use_quantized and not quantize_input and isinstance(self.weight, QuantizedTensor)
+                output = self.forward_comfy_cast_weights(
+                    input,
+                    compute_dtype,
+                    want_requant=isinstance(input, QuantizedTensor),
+                    weight_only_quant=weight_only_quant,
+                )
 
                 # Reshape output back to 3D if input was 3D
                 if reshaped_3d:
@@ -1257,8 +1306,7 @@ def mixed_precision_ops(quant_config={}, compute_dtype=torch.bfloat16, full_prec
 
             def set_weight(self, weight, inplace_update=False, seed=None, return_weight=False, **kwargs):
                 if getattr(self, 'layout_type', None) is not None:
-                    # dtype is now implicit in the layout class
-                    weight = QuantizedTensor.from_float(weight, self.layout_type, scale="recalculate", stochastic_rounding=seed, inplace_ops=True).to(self.weight.dtype)
+                    weight = self.weight.requantize_from_float(weight, scale="recalculate", stochastic_rounding=seed, inplace_ops=True).to(self.weight.dtype)
                 else:
                     weight = weight.to(self.weight.dtype)
                 if return_weight:

comfy/pinned_memory.py

@@ -89,13 +89,26 @@ def pin_memory(module, subset="weights", size=None):
         not comfy.model_management.ensure_pin_registerable(registerable_size)):
         return _steal_pin(module, stack, buckets, size, priority)
 
+    extended = False
     try:
-        hostbuf.extend(size=size)
+        hostbuf.extend(size=size, register=False)
+        extended = True
+        pin = comfy_aimdo.torch.hostbuf_to_tensor(hostbuf)[offset:offset + size]
+        pin.untyped_storage()._comfy_hostbuf = hostbuf
+        if torch.cuda.cudart().cudaHostRegister(pin.data_ptr(), size, 1) != 0:
+            comfy.model_management.discard_cuda_async_error()
+            comfy.model_management.free_registrations(size)
+            if torch.cuda.cudart().cudaHostRegister(pin.data_ptr(), size, 1) != 0:
+                comfy.model_management.discard_cuda_async_error()
+                del pin
+                hostbuf.truncate(offset, do_unregister=False)
+                return _steal_pin(module, stack, buckets, size, priority)
     except RuntimeError:
+        if extended:
+            hostbuf.truncate(offset, do_unregister=False)
         return _steal_pin(module, stack, buckets, size, priority)
 
-    module._pin = comfy_aimdo.torch.hostbuf_to_tensor(hostbuf)[offset:offset + size]
-    module._pin.untyped_storage()._comfy_hostbuf = hostbuf
+    module._pin = pin
     stack.append((module, offset))
     module._pin_registered = True
     module._pin_stack_index = len(stack) - 1

comfy/quant_ops.py

@@ -10,6 +10,7 @@ try:
         QuantizedLayout,
         TensorCoreFP8Layout as _CKFp8Layout,
         TensorCoreNVFP4Layout as _CKNvfp4Layout,
+        TensorWiseINT8Layout as _CKTensorWiseINT8Layout,
         register_layout_op,
         register_layout_class,
         get_layout_class,
@@ -47,6 +48,9 @@ except ImportError as e:
     class _CKNvfp4Layout:
         pass
 
+    class _CKTensorWiseINT8Layout:
+        pass
+
     def register_layout_class(name, cls):
         pass
 
@@ -174,6 +178,7 @@ class TensorCoreFP8E5M2Layout(_TensorCoreFP8LayoutBase):
 
 # Backward compatibility alias - default to E4M3
 TensorCoreFP8Layout = TensorCoreFP8E4M3Layout
+TensorWiseINT8Layout = _CKTensorWiseINT8Layout
 
 
 # ==============================================================================
@@ -184,6 +189,7 @@ register_layout_class("TensorCoreFP8Layout", TensorCoreFP8Layout)
 register_layout_class("TensorCoreFP8E4M3Layout", TensorCoreFP8E4M3Layout)
 register_layout_class("TensorCoreFP8E5M2Layout", TensorCoreFP8E5M2Layout)
 register_layout_class("TensorCoreNVFP4Layout", TensorCoreNVFP4Layout)
+register_layout_class("TensorWiseINT8Layout", _CKTensorWiseINT8Layout)
 if _CK_MXFP8_AVAILABLE:
     register_layout_class("TensorCoreMXFP8Layout", TensorCoreMXFP8Layout)
 
@@ -214,6 +220,13 @@ if _CK_MXFP8_AVAILABLE:
         "group_size": 32,
     }
 
+QUANT_ALGOS["int8_tensorwise"] = {
+    "storage_t": torch.int8,
+    "parameters": {"weight_scale"},
+    "comfy_tensor_layout": "TensorWiseINT8Layout",
+    "quantize_input": False,
+}
+
 
 # ==============================================================================
 # Re-exports for backward compatibility
@@ -226,6 +239,7 @@ __all__ = [
     "TensorCoreFP8E4M3Layout",
     "TensorCoreFP8E5M2Layout",
     "TensorCoreNVFP4Layout",
+    "TensorWiseINT8Layout",
     "QUANT_ALGOS",
     "register_layout_op",
 ]

comfy/sd.py

@@ -58,6 +58,8 @@ import comfy.text_encoders.omnigen2
 import comfy.text_encoders.qwen_image
 import comfy.text_encoders.hunyuan_image
 import comfy.text_encoders.z_image
+import comfy.text_encoders.krea2
+import comfy.text_encoders.ideogram4
 import comfy.text_encoders.ovis
 import comfy.text_encoders.kandinsky5
 import comfy.text_encoders.jina_clip_2
@@ -66,6 +68,8 @@ import comfy.text_encoders.anima
 import comfy.text_encoders.ace15
 import comfy.text_encoders.longcat_image
 import comfy.text_encoders.qwen35
+import comfy.text_encoders.qwen3vl
+import comfy.text_encoders.boogu
 import comfy.text_encoders.ernie
 import comfy.text_encoders.gemma4
 import comfy.text_encoders.cogvideo
@@ -1298,6 +1302,9 @@ class CLIPType(Enum):
     COGVIDEOX = 27
     LENS = 28
     PIXELDIT = 29
+    IDEOGRAM4 = 30
+    BOOGU = 31
+    KREA2 = 32
 
 
 
@@ -1351,6 +1358,8 @@ class TEModel(Enum):
     GEMMA_4_31B = 31
     T5_GEMMA = 32
     GPT_OSS_20B = 33
+    QWEN3VL_4B = 34
+    QWEN3VL_8B = 35
 
 
 def detect_te_model(sd):
@@ -1412,6 +1421,8 @@ def detect_te_model(sd):
         if weight.shape[0] == 5120:
             return TEModel.QWEN35_27B
         return TEModel.QWEN35_2B
+    if "model.visual.deepstack_merger_list.0.norm.weight" in sd:  # DeepStack is unique to Qwen3-VL
+        return TEModel.QWEN3VL_4B if sd["model.visual.merger.linear_fc2.weight"].shape[0] == 2560 else TEModel.QWEN3VL_8B
     if "model.layers.0.post_attention_layernorm.weight" in sd:
         weight = sd['model.layers.0.post_attention_layernorm.weight']
         if 'model.layers.0.self_attn.q_norm.weight' in sd:
@@ -1596,8 +1607,12 @@ def load_text_encoder_state_dicts(state_dicts=[], embedding_directory=None, clip
             clip_target.clip = comfy.text_encoders.ovis.te(**llama_detect(clip_data))
             clip_target.tokenizer = comfy.text_encoders.ovis.OvisTokenizer
         elif te_model == TEModel.QWEN3_8B:
-            clip_target.clip = comfy.text_encoders.flux.klein_te(**llama_detect(clip_data), model_type="qwen3_8b")
-            clip_target.tokenizer = comfy.text_encoders.flux.KleinTokenizer8B
+            if clip_type == CLIPType.IDEOGRAM4:
+                clip_target.clip = comfy.text_encoders.ideogram4.te(**llama_detect(clip_data))
+                clip_target.tokenizer = comfy.text_encoders.ideogram4.Ideogram4Tokenizer
+            else:
+                clip_target.clip = comfy.text_encoders.flux.klein_te(**llama_detect(clip_data), model_type="qwen3_8b")
+                clip_target.tokenizer = comfy.text_encoders.flux.KleinTokenizer8B
         elif te_model == TEModel.JINA_CLIP_2:
             clip_target.clip = comfy.text_encoders.jina_clip_2.JinaClip2TextModelWrapper
             clip_target.tokenizer = comfy.text_encoders.jina_clip_2.JinaClip2TokenizerWrapper
@@ -1606,6 +1621,28 @@ def load_text_encoder_state_dicts(state_dicts=[], embedding_directory=None, clip
             qwen35_type = {TEModel.QWEN35_08B: "qwen35_08b", TEModel.QWEN35_2B: "qwen35_2b", TEModel.QWEN35_4B: "qwen35_4b", TEModel.QWEN35_9B: "qwen35_9b", TEModel.QWEN35_27B: "qwen35_27b"}[te_model]
             clip_target.clip = comfy.text_encoders.qwen35.te(**llama_detect(clip_data), model_type=qwen35_type)
             clip_target.tokenizer = comfy.text_encoders.qwen35.tokenizer(model_type=qwen35_type)
+        elif te_model in (TEModel.QWEN3VL_4B, TEModel.QWEN3VL_8B):
+            if clip_type == CLIPType.IDEOGRAM4 and te_model == TEModel.QWEN3VL_8B:  # Ideogram4 reuses the full Qwen3-VL-8B (13-layer tap for conditioning + multimodal generate).
+                clip_data[0] = comfy.utils.state_dict_prefix_replace(clip_data[0], {"model.language_model.": "model.", "model.visual.": "visual.", "lm_head.": "model.lm_head."})
+                clip_target.clip = comfy.text_encoders.ideogram4.te_qwen3vl(**llama_detect(clip_data))
+                clip_target.tokenizer = comfy.text_encoders.ideogram4.Ideogram4Qwen3VLTokenizer
+            elif clip_type == CLIPType.BOOGU and te_model == TEModel.QWEN3VL_8B:  # Boogu-Image: full Qwen3-VL-8B, last hidden state, no-think template.
+                clip_data[0] = comfy.utils.state_dict_prefix_replace(clip_data[0], {"model.language_model.": "model.", "model.visual.": "visual.", "lm_head.": "model.lm_head."})
+                clip_target.clip = comfy.text_encoders.boogu.te(**llama_detect(clip_data))
+                clip_target.tokenizer = comfy.text_encoders.boogu.BooguTokenizer
+            elif clip_type == CLIPType.KREA2 and te_model == TEModel.QWEN3VL_4B:  # Krea2: full Qwen3-VL-4B (12-layer tap for conditioning + multimodal generate).
+                clip_data[0] = comfy.utils.state_dict_prefix_replace(clip_data[0], {"model.language_model.": "model.", "model.visual.": "visual.", "lm_head.": "model.lm_head."})
+                clip_target.clip = comfy.text_encoders.krea2.te(**llama_detect(clip_data))
+                clip_target.tokenizer = comfy.text_encoders.krea2.Krea2Tokenizer
+            elif clip_type in (CLIPType.FLUX, CLIPType.FLUX2):  # Flux2 Klein reuses the Qwen3-VL LM (3-layer tap -> 12288); visual unused.
+                klein_model_type = "qwen3_8b" if te_model == TEModel.QWEN3VL_8B else "qwen3_4b"
+                clip_target.clip = comfy.text_encoders.flux.klein_te(**llama_detect(clip_data), model_type=klein_model_type)
+                clip_target.tokenizer = comfy.text_encoders.flux.KleinTokenizer8B if te_model == TEModel.QWEN3VL_8B else comfy.text_encoders.flux.KleinTokenizer
+            else:
+                clip_data[0] = comfy.utils.state_dict_prefix_replace(clip_data[0], {"model.language_model.": "model.", "model.visual.": "visual.", "lm_head.": "model.lm_head."})
+                qwen3vl_type = {TEModel.QWEN3VL_4B: "qwen3vl_4b", TEModel.QWEN3VL_8B: "qwen3vl_8b"}[te_model]
+                clip_target.clip = comfy.text_encoders.qwen3vl.te(**llama_detect(clip_data), model_type=qwen3vl_type)
+                clip_target.tokenizer = comfy.text_encoders.qwen3vl.tokenizer(model_type=qwen3vl_type)
         elif te_model == TEModel.QWEN3_06B:
             clip_target.clip = comfy.text_encoders.anima.te(**llama_detect(clip_data))
             clip_target.tokenizer = comfy.text_encoders.anima.AnimaTokenizer

comfy/sd1_clip.py

@@ -543,18 +543,24 @@ class SDTokenizer:
     def _try_get_embedding(self, embedding_name:str):
         '''
         Takes a potential embedding name and tries to retrieve it.
-        Returns a Tuple consisting of the embedding and any leftover string, embedding can be None.
+        Returns a Tuple consisting of the embedding, the cleaned embedding name, and any leftover string, embedding can be None.
         '''
         split_embed = embedding_name.split()
         embedding_name = split_embed[0]
         leftover = ' '.join(split_embed[1:])
+
+        match = re.search(r'[<\[]', embedding_name)
+        if match is not None:
+            leftover = embedding_name[match.start():] + (" " + leftover if leftover else "")
+            embedding_name = embedding_name[:match.start()]
+
         embed = load_embed(embedding_name, self.embedding_directory, self.embedding_size, self.embedding_key)
         if embed is None:
             stripped = embedding_name.strip(',')
             if len(stripped) < len(embedding_name):
                 embed = load_embed(stripped, self.embedding_directory, self.embedding_size, self.embedding_key)
-                return (embed, "{} {}".format(embedding_name[len(stripped):], leftover))
-        return (embed, leftover)
+                return (embed, embedding_name, "{} {}".format(embedding_name[len(stripped):], leftover))
+        return (embed, embedding_name, leftover)
 
     def pad_tokens(self, tokens, amount):
         if self.pad_left:
@@ -585,7 +591,7 @@ class SDTokenizer:
         tokens = []
         for weighted_segment, weight in parsed_weights:
             to_tokenize = unescape_important(weighted_segment)
-            split = re.split(' {0}|\n{0}'.format(self.embedding_identifier), to_tokenize)
+            split = re.split(r'(?<=\s){}'.format(re.escape(self.embedding_identifier)), to_tokenize)
             to_tokenize = [split[0]]
             for i in range(1, len(split)):
                 to_tokenize.append("{}{}".format(self.embedding_identifier, split[i]))
@@ -595,7 +601,7 @@ class SDTokenizer:
                 # if we find an embedding, deal with the embedding
                 if word.startswith(self.embedding_identifier) and self.embedding_directory is not None:
                     embedding_name = word[len(self.embedding_identifier):].strip('\n')
-                    embed, leftover = self._try_get_embedding(embedding_name)
+                    embed, embedding_name, leftover = self._try_get_embedding(embedding_name)
                     if embed is None:
                         logging.warning(f"warning, embedding:{embedding_name} does not exist, ignoring")
                     else:

comfy/supported_models.py

@@ -24,6 +24,9 @@ import comfy.text_encoders.qwen_image
 import comfy.text_encoders.hunyuan_image
 import comfy.text_encoders.kandinsky5
 import comfy.text_encoders.z_image
+import comfy.text_encoders.ideogram4
+import comfy.text_encoders.boogu
+import comfy.text_encoders.krea2
 import comfy.text_encoders.anima
 import comfy.text_encoders.ace15
 import comfy.text_encoders.longcat_image
@@ -1449,6 +1452,17 @@ class WAN21_SCAIL(WAN21_T2V):
         out = model_base.WAN21_SCAIL(self, image_to_video=False, device=device)
         return out
 
+
+class WAN21_SCAIL2(WAN21_T2V):
+    unet_config = {
+        "image_model": "wan2.1",
+        "model_type": "scail2",
+    }
+
+    def get_model(self, state_dict, prefix="", device=None):
+        out = model_base.WAN21_SCAIL2(self, image_to_video=False, device=device)
+        return out
+
 class WAN22_WanDancer(WAN21_T2V):
     unet_config = {
         "image_model": "wan2.1",
@@ -1746,6 +1760,94 @@ class Omnigen2(supported_models_base.BASE):
         hunyuan_detect = comfy.text_encoders.hunyuan_video.llama_detect(state_dict, "{}qwen25_3b.transformer.".format(pref))
         return supported_models_base.ClipTarget(comfy.text_encoders.omnigen2.Omnigen2Tokenizer, comfy.text_encoders.omnigen2.te(**hunyuan_detect))
 
+class Boogu(Omnigen2):
+    unet_config = {
+        "image_model": "boogu",
+    }
+
+    sampling_settings = {
+        "multiplier": 1.0,
+        "shift": 3.16,
+    }
+
+    memory_usage_factor = 2.15
+
+    def get_model(self, state_dict, prefix="", device=None):
+        out = model_base.Boogu(self, device=device)
+        return out
+
+    def clip_target(self, state_dict={}):
+        pref = self.text_encoder_key_prefix[0]
+        hunyuan_detect = comfy.text_encoders.hunyuan_video.llama_detect(state_dict, "{}qwen3vl_8b.transformer.".format(pref))
+        return supported_models_base.ClipTarget(comfy.text_encoders.boogu.BooguTokenizer, comfy.text_encoders.boogu.te(**hunyuan_detect))
+
+class Ideogram4(supported_models_base.BASE):
+    unet_config = {
+        "image_model": "ideogram4",
+    }
+
+    sampling_settings = {
+        "multiplier": 1.0,
+        "shift": 1.0,
+    }
+
+    memory_usage_factor = 11.6
+
+    unet_extra_config = {
+        "num_attention_heads": 18,
+        "attention_head_dim": 256,
+        "intermediate_size": 12288,
+        "adaln_dim": 512,
+        "llm_features_dim": 53248,
+        "rope_theta": 5000000,
+        "mrope_section": [24, 20, 20],
+        "norm_eps": 1e-5,
+    }
+    latent_format = latent_formats.Flux2
+
+    supported_inference_dtypes = [torch.bfloat16, torch.float32]
+
+    vae_key_prefix = ["vae."]
+    text_encoder_key_prefix = ["text_encoders."]
+
+    def get_model(self, state_dict, prefix="", device=None):
+        out = model_base.Ideogram4(self, device=device)
+        return out
+
+    def clip_target(self, state_dict={}):
+        pref = self.text_encoder_key_prefix[0]
+        hunyuan_detect = comfy.text_encoders.hunyuan_video.llama_detect(state_dict, "{}qwen3vl_8b.transformer.".format(pref))
+        return supported_models_base.ClipTarget(comfy.text_encoders.ideogram4.Ideogram4Tokenizer, comfy.text_encoders.ideogram4.te(**hunyuan_detect))
+
+
+class Krea2(supported_models_base.BASE):
+    unet_config = {
+        "image_model": "krea2",
+    }
+
+    sampling_settings = {
+        "multiplier": 1.0,
+        "shift": 1.15,
+    }
+
+    memory_usage_factor = 2.2
+
+    latent_format = latent_formats.Wan21
+
+    supported_inference_dtypes = [torch.bfloat16, torch.float16, torch.float32]
+
+    vae_key_prefix = ["vae."]
+    text_encoder_key_prefix = ["text_encoders."]
+
+    def get_model(self, state_dict, prefix="", device=None):
+        out = model_base.Krea2(self, device=device)
+        return out
+
+    def clip_target(self, state_dict={}):
+        pref = self.text_encoder_key_prefix[0]
+        hunyuan_detect = comfy.text_encoders.hunyuan_video.llama_detect(state_dict, "{}qwen3vl_4b.transformer.".format(pref))
+        return supported_models_base.ClipTarget(comfy.text_encoders.krea2.Krea2Tokenizer, comfy.text_encoders.krea2.te(**hunyuan_detect))
+
 class QwenImage(supported_models_base.BASE):
     unet_config = {
         "image_model": "qwen_image",
@@ -2006,6 +2108,23 @@ class RT_DETR_v4(supported_models_base.BASE):
         return None
 
 
+class DepthAnything3(supported_models_base.BASE):
+    unet_config = {
+        "image_model": "DepthAnything3",
+    }
+
+    # Mono path: no num_heads / num_head_channels needed.
+    unet_extra_config = {}
+
+    supported_inference_dtypes = [torch.float16, torch.bfloat16, torch.float32]
+
+    def get_model(self, state_dict, prefix="", device=None):
+        return model_base.DepthAnything3(self, device=device)
+
+    def clip_target(self, state_dict={}):
+        return None
+
+
 class ErnieImage(supported_models_base.BASE):
     unet_config = {
         "image_model": "ernie",
@@ -2220,6 +2339,7 @@ models = [
     WAN22_Animate,
     WAN21_FlowRVS,
     WAN21_SCAIL,
+    WAN21_SCAIL2,
     WAN22_WanDancer,
     Hunyuan3Dv2mini,
     Hunyuan3Dv2,
@@ -2232,7 +2352,10 @@ models = [
     ACEStep,
     ACEStep15,
     Omnigen2,
+    Boogu,
     QwenImage,
+    Ideogram4,
+    Krea2,
     Flux2,
     Lens,
     Kandinsky5Image,
@@ -2246,4 +2369,5 @@ models = [
     CogVideoX_I2V,
     CogVideoX_T2V,
     SVD_img2vid,
+    DepthAnything3,
 ]

comfy/text_encoders/boogu.py

@@ -0,0 +1,58 @@
+"""Boogu-Image text encoder: full Qwen3-VL-8B, last hidden state (4096-dim).
+
+Boogu uses the final hidden state of Qwen3-VL as the per-token instruction feature
+(num_instruction_feature_layers=1, reduce_type=mean -> just the last layer).
+The model itself is the standard Qwen3-VL TE, only the chat template differs
+(a fixed system prompt and no <think> block).
+"""
+
+import comfy.text_encoders.qwen3vl
+from comfy import sd1_clip
+
+
+# System prompts from the reference pipeline (pipeline_boogu.py).
+# T2I (non-empty instruction, no image) uses the helpful-assistant prompt
+# everything else (the CFG negative / "drop" condition, and any image case) uses the TI2I "describe" prompt.
+BOOGU_T2I_SYSTEM = "You are a helpful assistant that generates high-quality images based on user instructions. The instructions are as follows."
+BOOGU_DROP_SYSTEM = "Describe the key features of the input image (color, shape, size, texture, objects, background), then explain how the user's text instruction should alter or modify the image. Generate a new image that meets the user's requirements while maintaining consistency with the original input where appropriate."
+
+
+class BooguTokenizer(comfy.text_encoders.qwen3vl.Qwen3VLTokenizer):
+    def __init__(self, embedding_directory=None, tokenizer_data={}):
+        super().__init__(embedding_directory=embedding_directory, tokenizer_data=tokenizer_data, model_type="qwen3vl_8b")
+        # apply_chat_template without add_generation_prompt
+        self.llama_template = "<|im_start|>system\n" + BOOGU_T2I_SYSTEM + "<|im_end|>\n<|im_start|>user\n{}<|im_end|>\n"
+        self.llama_template_images = "<|im_start|>system\n" + BOOGU_DROP_SYSTEM + "<|im_end|>\n<|im_start|>user\n<|vision_start|><|image_pad|><|vision_end|>{}<|im_end|>\n"
+        # Reference SYSTEM_PROMPT_DROP: used for the empty negative/uncond instruction.
+        self.llama_template_drop = "<|im_start|>system\n" + BOOGU_DROP_SYSTEM + "<|im_end|>\n<|im_start|>user\n{}<|im_end|>\n"
+
+    def tokenize_with_weights(self, text, return_word_ids=False, llama_template=None, images=[], prevent_empty_text=False, thinking=True, **kwargs):
+        if llama_template is None and len(images) == 0 and text.strip() == "":
+            llama_template = self.llama_template_drop
+        # Boogu conditions on the no-think template; thinking=True drops the empty <think> block qwen3vl adds by default.
+        return super().tokenize_with_weights(text, return_word_ids=return_word_ids, llama_template=llama_template, images=images, prevent_empty_text=prevent_empty_text, thinking=thinking, **kwargs)
+
+
+class BooguQwen3VLClipModel(comfy.text_encoders.qwen3vl.Qwen3VLClipModel):
+    def __init__(self, device="cpu", dtype=None, attention_mask=True, model_options={}, model_type="qwen3vl_8b"):
+        super().__init__(device=device, dtype=dtype, attention_mask=attention_mask, model_options=model_options, model_type=model_type)
+        # apply the final RMSNorm to the tapped last layer
+        self.layer_norm_hidden_state = True
+
+
+class BooguTEModel(sd1_clip.SD1ClipModel):
+    def __init__(self, device="cpu", dtype=None, model_options={}):
+        clip_model = lambda **kw: BooguQwen3VLClipModel(**kw, model_type="qwen3vl_8b")
+        super().__init__(device=device, dtype=dtype, name="qwen3vl_8b", clip_model=clip_model, model_options=model_options)
+
+
+def te(dtype_llama=None, llama_quantization_metadata=None):
+    class BooguTEModel_(BooguTEModel):
+        def __init__(self, device="cpu", dtype=None, model_options={}):
+            if dtype_llama is not None:
+                dtype = dtype_llama
+            if llama_quantization_metadata is not None:
+                model_options = model_options.copy()
+                model_options["quantization_metadata"] = llama_quantization_metadata
+            super().__init__(device=device, dtype=dtype, model_options=model_options)
+    return BooguTEModel_

comfy/text_encoders/ideogram4.py

@@ -0,0 +1,120 @@
+"""Ideogram 4 text encoder: Qwen3-VL-8B language model, 13-layer tap.
+
+Ideogram 4 conditions on the concatenation of hidden states from 13 layers of
+Qwen3-VL (layers 0,3,...,33,35), giving a 4096*13 = 53248-dim feature per token.
+"""
+
+import os
+
+from transformers import Qwen2Tokenizer
+
+import comfy.text_encoders.llama
+import comfy.text_encoders.qwen3vl
+from comfy import sd1_clip
+
+# Reference taps outputs of layers (0,3,...,35); comfy captures layer inputs, offset by +1.
+IDEOGRAM4_TAP_LAYERS = [1, 4, 7, 10, 13, 16, 19, 22, 25, 28, 31, 34, 36]
+
+
+class Qwen3VLTokenizer(sd1_clip.SDTokenizer):
+    def __init__(self, embedding_directory=None, tokenizer_data={}):
+        tokenizer_path = os.path.join(os.path.dirname(os.path.realpath(__file__)), "qwen25_tokenizer")
+        super().__init__(tokenizer_path, pad_with_end=False, embedding_directory=embedding_directory,
+                         embedding_size=4096, embedding_key='qwen3vl_8b', tokenizer_class=Qwen2Tokenizer,
+                         has_start_token=False, has_end_token=False, pad_to_max_length=False,
+                         max_length=99999999, min_length=1, pad_token=151643, tokenizer_data=tokenizer_data)
+
+
+class Ideogram4Tokenizer(sd1_clip.SD1Tokenizer):
+    def __init__(self, embedding_directory=None, tokenizer_data={}):
+        super().__init__(embedding_directory=embedding_directory, tokenizer_data=tokenizer_data,
+                         name="qwen3vl_8b", tokenizer=Qwen3VLTokenizer)
+
+        self.llama_template = "<|im_start|>user\n{}<|im_end|>\n<|im_start|>assistant\n"
+
+    def tokenize_with_weights(self, text, return_word_ids=False, llama_template=None, **kwargs):
+        if text.startswith('<|im_start|>'):
+            llama_text = text
+        elif llama_template is None:
+            llama_text = self.llama_template.format(text)
+        else:
+            llama_text = llama_template.format(text)
+        return super().tokenize_with_weights(llama_text, return_word_ids=return_word_ids, disable_weights=True, **kwargs)
+
+
+# Qwen3-VL-8B = 5e6 (vs plain Qwen3-8B's 1e6)
+# final_norm/lm_head off -> Ideogram only reads raw tapped hidden states
+QWEN3VL_8B_CONFIG = {"rope_theta": 5000000.0, "final_norm": False, "lm_head": False}
+
+
+class Qwen3VL8BModel(sd1_clip.SDClipModel):
+    def __init__(self, device="cpu", layer="hidden", layer_idx=None, dtype=None, attention_mask=True, model_options={}):
+        super().__init__(device=device, layer=IDEOGRAM4_TAP_LAYERS, layer_idx=None,
+                         textmodel_json_config=dict(QWEN3VL_8B_CONFIG),
+                         dtype=dtype, special_tokens={"pad": 151643}, layer_norm_hidden_state=False,
+                         model_class=comfy.text_encoders.llama.Qwen3_8B,
+                         enable_attention_masks=attention_mask, return_attention_masks=attention_mask,
+                         model_options=model_options)
+
+
+class Ideogram4TEModel(sd1_clip.SD1ClipModel):
+    def __init__(self, device="cpu", dtype=None, model_options={}):
+        super().__init__(device=device, dtype=dtype, name="qwen3vl_8b", clip_model=Qwen3VL8BModel, model_options=model_options)
+
+    def encode_token_weights(self, token_weight_pairs):
+        out, pooled, extra = super().encode_token_weights(token_weight_pairs)
+        b, n, seq, h = out.shape # (B, n_taps=13, seq, 4096) stacked in ascending layer order.
+        out = out.permute(0, 2, 3, 1).reshape(b, seq, h * n) # (B, seq, 4096*13). permute -> (B, seq, H, taps).
+        return out, pooled, extra
+
+
+def te(dtype_llama=None, llama_quantization_metadata=None):
+    class Ideogram4TEModel_(Ideogram4TEModel):
+        def __init__(self, device="cpu", dtype=None, model_options={}):
+            if dtype_llama is not None:
+                dtype = dtype_llama
+            if llama_quantization_metadata is not None:
+                model_options = model_options.copy()
+                model_options["quantization_metadata"] = llama_quantization_metadata
+            super().__init__(device=device, dtype=dtype, model_options=model_options)
+    return Ideogram4TEModel_
+
+
+# Full Qwen3-VL-8B variant with vision
+
+class Ideogram4Qwen3VLClipModel(comfy.text_encoders.qwen3vl.Qwen3VLClipModel):
+    def __init__(self, device="cpu", dtype=None, attention_mask=True, model_options={}):
+        super().__init__(device=device, layer=IDEOGRAM4_TAP_LAYERS, layer_idx=None, dtype=dtype,
+                         attention_mask=attention_mask, model_options=model_options, model_type="qwen3vl_8b")
+
+
+class Ideogram4Qwen3VLTEModel(sd1_clip.SD1ClipModel):
+    def __init__(self, device="cpu", dtype=None, model_options={}):
+        super().__init__(device=device, dtype=dtype, name="qwen3vl_8b", clip_model=Ideogram4Qwen3VLClipModel, model_options=model_options)
+
+    def encode_token_weights(self, token_weight_pairs):
+        out, pooled, extra = super().encode_token_weights(token_weight_pairs)
+        b, n, seq, h = out.shape  # (B, n_taps=13, seq, 4096), ascending layer order.
+        out = out.permute(0, 2, 3, 1).reshape(b, seq, h * n)  # (B, seq, 4096*13 = 53248).
+        return out, pooled, extra
+
+
+class Ideogram4Qwen3VLTokenizer(comfy.text_encoders.qwen3vl.Qwen3VLTokenizer):
+    def __init__(self, embedding_directory=None, tokenizer_data={}):
+        super().__init__(embedding_directory=embedding_directory, tokenizer_data=tokenizer_data, model_type="qwen3vl_8b")
+
+    def tokenize_with_weights(self, text, return_word_ids=False, llama_template=None, images=[], prevent_empty_text=False, thinking=True, **kwargs):
+        # Ideogram 4 conditions on the no-think template; default thinking=True drops the empty think block qwen3vl adds.
+        return super().tokenize_with_weights(text, return_word_ids=return_word_ids, llama_template=llama_template, images=images, prevent_empty_text=prevent_empty_text, thinking=thinking, **kwargs)
+
+
+def te_qwen3vl(dtype_llama=None, llama_quantization_metadata=None):
+    class Ideogram4Qwen3VLTEModel_(Ideogram4Qwen3VLTEModel):
+        def __init__(self, device="cpu", dtype=None, model_options={}):
+            if dtype_llama is not None:
+                dtype = dtype_llama
+            if llama_quantization_metadata is not None:
+                model_options = model_options.copy()
+                model_options["quantization_metadata"] = llama_quantization_metadata
+            super().__init__(device=device, dtype=dtype, model_options=model_options)
+    return Ideogram4Qwen3VLTEModel_

comfy/text_encoders/krea2.py

@@ -0,0 +1,84 @@
+"""Krea 2 (K2) text encoder: Qwen3-VL-4B, 12-layer tap.
+
+K2 conditions on a stack of hidden states from 12 layers of Qwen3-VL-4B
+(reference taps ``hidden_states[2,5,8,...,35]``), kept as a ``(B, 12, seq, 2560)`` tensor and
+consumed by the DiT's internal ``txtfusion`` adapter. Comfy carries conditioning as a 3D tensor,
+so the 12-layer stack is flattened to ``(B, seq, 12*2560)`` here and unpacked inside the model.
+"""
+
+import numbers
+
+import torch
+
+import comfy.text_encoders.qwen3vl
+from comfy import sd1_clip
+
+# tap k == hidden_states[k] (no offset).
+KREA2_TAP_LAYERS = [2, 5, 8, 11, 14, 17, 20, 23, 26, 29, 32, 35]
+
+# Identical system template to Qwen-Image; Krea2 strips the system+user-opening prefix.
+KREA2_TEMPLATE = "<|im_start|>system\nDescribe the image by detailing the color, shape, size, texture, quantity, text, spatial relationships of the objects and background:<|im_end|>\n<|im_start|>user\n{}<|im_end|>\n<|im_start|>assistant\n"
+
+
+class Krea2Tokenizer(comfy.text_encoders.qwen3vl.Qwen3VLTokenizer):
+    def __init__(self, embedding_directory=None, tokenizer_data={}):
+        super().__init__(embedding_directory=embedding_directory, tokenizer_data=tokenizer_data, model_type="qwen3vl_4b")
+        self.llama_template = KREA2_TEMPLATE  # conditioning template; image text-gen uses qwen3vl's default image template.
+
+    def tokenize_with_weights(self, text, return_word_ids=False, llama_template=None, images=[], prevent_empty_text=False, thinking=True, **kwargs):
+        # Krea2 conditions on the no-think template; thinking=True drops the empty <think> block qwen3vl adds.
+        return super().tokenize_with_weights(text, return_word_ids=return_word_ids, llama_template=llama_template, images=images, prevent_empty_text=prevent_empty_text, thinking=thinking, **kwargs)
+
+
+class Krea2Qwen3VLClipModel(comfy.text_encoders.qwen3vl.Qwen3VLClipModel):
+    def __init__(self, device="cpu", dtype=None, attention_mask=True, model_options={}):
+        super().__init__(device=device, layer=KREA2_TAP_LAYERS, layer_idx=None, dtype=dtype,
+                         attention_mask=attention_mask, model_options=model_options, model_type="qwen3vl_4b")
+
+
+class Krea2TEModel(sd1_clip.SD1ClipModel):
+    def __init__(self, device="cpu", dtype=None, model_options={}):
+        super().__init__(device=device, dtype=dtype, name="qwen3vl_4b", clip_model=Krea2Qwen3VLClipModel, model_options=model_options)
+
+    def encode_token_weights(self, token_weight_pairs, template_end=-1):
+        out, pooled, extra = super().encode_token_weights(token_weight_pairs)  # out: (B, 12, seq, 2560)
+        tok_pairs = token_weight_pairs["qwen3vl_4b"][0]
+
+        # Strip the system + user-opening prefix
+        count_im_start = 0
+        if template_end == -1:
+            for i, v in enumerate(tok_pairs):
+                elem = v[0]
+                if not torch.is_tensor(elem) and isinstance(elem, numbers.Integral):
+                    if elem == 151644 and count_im_start < 2:
+                        template_end = i
+                        count_im_start += 1
+            if out.shape[2] > (template_end + 3):
+                if tok_pairs[template_end + 1][0] == 872:      # "user"
+                    if tok_pairs[template_end + 2][0] == 198:   # "\n"
+                        template_end += 3
+
+        out = out[:, :, template_end:]
+
+        b, n, seq, h = out.shape
+        # Flatten the 12-layer axis into the feature dim: (B, seq, 12*2560). Unpacked in the model.
+        out = out.permute(0, 2, 1, 3).reshape(b, seq, n * h)
+
+        if "attention_mask" in extra:
+            extra["attention_mask"] = extra["attention_mask"][:, template_end:]
+            if extra["attention_mask"].sum() == torch.numel(extra["attention_mask"]):
+                extra.pop("attention_mask")
+
+        return out, pooled, extra
+
+
+def te(dtype_llama=None, llama_quantization_metadata=None):
+    class Krea2TEModel_(Krea2TEModel):
+        def __init__(self, device="cpu", dtype=None, model_options={}):
+            if llama_quantization_metadata is not None:
+                model_options = model_options.copy()
+                model_options["quantization_metadata"] = llama_quantization_metadata
+            if dtype_llama is not None:
+                dtype = dtype_llama
+            super().__init__(device=device, dtype=dtype, model_options=model_options)
+    return Krea2TEModel_

comfy/text_encoders/llama.py

@@ -251,6 +251,19 @@ class Qwen3_8BConfig:
     lm_head: bool = True
     stop_tokens = [151643, 151645]
 
+@dataclass
+class Qwen3VL_8BConfig(Qwen3_8BConfig):
+    max_position_embeddings: int = 262144
+    rope_theta: float = 5000000.0
+    rope_dims = [24, 20, 20]
+    interleaved_mrope = True
+
+@dataclass
+class Qwen3VL_4BConfig(Qwen3VL_8BConfig):
+    hidden_size: int = 2560
+    intermediate_size: int = 9728
+    lm_head: bool = False  # 4B ties word embeddings
+
 @dataclass
 class Ovis25_2BConfig:
     vocab_size: int = 151936
@@ -703,7 +716,8 @@ class Llama2_(nn.Module):
                                     interleaved_mrope=getattr(self.config, "interleaved_mrope", False),
                                     device=device)
 
-    def forward(self, x, attention_mask=None, embeds=None, num_tokens=None, intermediate_output=None, final_layer_norm_intermediate=True, dtype=None, position_ids=None, embeds_info=[], past_key_values=None, input_ids=None):
+    def forward(self, x, attention_mask=None, embeds=None, num_tokens=None, intermediate_output=None, final_layer_norm_intermediate=True,
+                dtype=None, position_ids=None, embeds_info=[], past_key_values=None, input_ids=None,deepstack_embeds=None, visual_pos_masks=None):
         if embeds is not None:
             x = embeds
         else:
@@ -767,6 +781,10 @@ class Llama2_(nn.Module):
             if current_kv is not None:
                 next_key_values.append(current_kv)
 
+            # DeepStack: add per-layer visual features into the first len() decoder layers at image positions (Qwen3-VL)
+            if deepstack_embeds is not None and i < len(deepstack_embeds):
+                x[visual_pos_masks] = x[visual_pos_masks] + deepstack_embeds[i].to(x)
+
             if i == intermediate_output:
                 intermediate = x.clone()
 
@@ -860,7 +878,7 @@ class BaseGenerate:
                                     torch.empty([batch, model_config.num_key_value_heads, max_cache_len, model_config.head_dim], device=device, dtype=execution_dtype), 0))
         return past_key_values
 
-    def generate(self, embeds=None, do_sample=True, max_length=256, temperature=1.0, top_k=50, top_p=0.9, min_p=0.0, repetition_penalty=1.0, seed=42, stop_tokens=None, initial_tokens=[], execution_dtype=None, min_tokens=0, presence_penalty=0.0, initial_input_ids=None):
+    def generate(self, embeds=None, do_sample=True, max_length=256, temperature=1.0, top_k=50, top_p=0.9, min_p=0.0, repetition_penalty=1.0, seed=42, stop_tokens=None, initial_tokens=[], execution_dtype=None, min_tokens=0, presence_penalty=0.0, initial_input_ids=None, position_ids=None, deepstack_embeds=None, visual_pos_masks=None):
         device = embeds.device
 
         if stop_tokens is None:
@@ -884,10 +902,18 @@ class BaseGenerate:
         generated_token_ids = []
         pbar = comfy.utils.ProgressBar(max_length)
 
+        # MRoPE: prefill uses explicit 3D position_ids, decode continues from the last position
+        next_pos = int(position_ids[:, -1].max()) + 1 if position_ids is not None else None
+
         # Generation loop
         current_input_ids = initial_input_ids
         for step in tqdm(range(max_length), desc="Generating tokens"):
-            x, _, past_key_values = self.model.forward(None, embeds=embeds, attention_mask=None, past_key_values=past_key_values, input_ids=current_input_ids)
+            # DeepStack visual features are injected on the prefill only; gemma4's forward lacks these kwargs.
+            extra = {}
+            if step == 0 and deepstack_embeds is not None:
+                extra["deepstack_embeds"] = deepstack_embeds
+                extra["visual_pos_masks"] = visual_pos_masks
+            x, _, past_key_values = self.model.forward(None, embeds=embeds, attention_mask=None, past_key_values=past_key_values, input_ids=current_input_ids, position_ids=position_ids, **extra)
             logits = self.logits(x)[:, -1]
             next_token = self.sample_token(logits, temperature, top_k, top_p, min_p, repetition_penalty, initial_tokens + generated_token_ids, generator, do_sample=do_sample, presence_penalty=presence_penalty)
             token_id = next_token[0].item()
@@ -895,6 +921,9 @@ class BaseGenerate:
 
             embeds = self.model.embed_tokens(next_token).to(execution_dtype)
             current_input_ids = next_token if initial_input_ids is not None else None
+            if next_pos is not None:  # advance MRoPE position for the next (decode) step
+                position_ids = torch.tensor([[next_pos]], device=device)
+                next_pos += 1
             pbar.update(1)
 
             if token_id in stop_tokens:

comfy/text_encoders/qwen35.py

@@ -3,7 +3,6 @@ import torch.nn as nn
 import torch.nn.functional as F
 from dataclasses import dataclass, field
 import os
-import math
 
 import comfy.model_management
 from comfy.ldm.modules.attention import optimized_attention_for_device
@@ -563,6 +562,8 @@ class Qwen35VisionModel(nn.Module):
             for _ in range(config["depth"])
         ])
         self.merger = Qwen35VisionPatchMerger(self.hidden_size, self.spatial_merge_size, config["out_hidden_size"], device=device, dtype=dtype, ops=ops)
+        self.deepstack_visual_indexes = [] # DeepStack, per-layer visual features (Qwen3-VL)
+        self.deepstack_merger_list = None
 
     def rot_pos_emb(self, grid_thw):
         merge_size = self.spatial_merge_size
@@ -664,9 +665,14 @@ class Qwen35VisionModel(nn.Module):
         ).cumsum(dim=0, dtype=torch.int32)
         cu_seqlens = F.pad(cu_seqlens, (1, 0), value=0)
         optimized_attention = optimized_attention_for_device(x.device, mask=False, small_input=True)
-        for blk in self.blocks:
+        deepstack_features = []
+        for layer_num, blk in enumerate(self.blocks):
             x = blk(x, cu_seqlens=cu_seqlens, position_embeddings=position_embeddings, optimized_attention=optimized_attention)
+            if self.deepstack_merger_list is not None and layer_num in self.deepstack_visual_indexes:
+                deepstack_features.append(self.deepstack_merger_list[self.deepstack_visual_indexes.index(layer_num)](x))
         merged = self.merger(x)
+        if self.deepstack_merger_list is not None:
+            return merged, deepstack_features
         return merged
 
 # Model Wrapper
@@ -690,30 +696,7 @@ class Qwen35(BaseLlama, BaseGenerate, torch.nn.Module):
         return None, None
 
     def forward(self, x, attention_mask=None, embeds=None, num_tokens=None, intermediate_output=None, final_layer_norm_intermediate=True, dtype=None, embeds_info=[], past_key_values=None):
-        grid = None
-        position_ids = None
-        offset = 0
-        for e in embeds_info:
-            if e.get("type") == "image":
-                grid = e.get("extra", None)
-                start = e.get("index")
-                if position_ids is None:
-                    position_ids = torch.zeros((3, embeds.shape[1]), device=embeds.device)
-                    position_ids[:, :start] = torch.arange(0, start, device=embeds.device)
-                end = e.get("size") + start
-                len_max = int(grid.max()) // 2
-                start_next = len_max + start
-                position_ids[:, end:] = torch.arange(start_next + offset, start_next + (embeds.shape[1] - end) + offset, device=embeds.device)
-                position_ids[0, start:end] = start + offset
-                max_d = int(grid[0][1]) // 2
-                position_ids[1, start:end] = torch.arange(start + offset, start + max_d + offset, device=embeds.device).unsqueeze(1).repeat(1, math.ceil((end - start) / max_d)).flatten(0)[:end - start]
-                max_d = int(grid[0][2]) // 2
-                position_ids[2, start:end] = torch.arange(start + offset, start + max_d + offset, device=embeds.device).unsqueeze(0).repeat(math.ceil((end - start) / max_d), 1).flatten(0)[:end - start]
-                offset += len_max - (end - start)
-
-        if grid is None:
-            position_ids = None
-
+        position_ids = comfy.text_encoders.qwen_vl.qwen2vl_mrope_position_ids(embeds_info, embeds.shape[1], embeds.device)
         return super().forward(x, attention_mask=attention_mask, embeds=embeds, num_tokens=num_tokens, intermediate_output=intermediate_output, final_layer_norm_intermediate=final_layer_norm_intermediate, dtype=dtype, position_ids=position_ids, past_key_values=past_key_values)
 
     def init_kv_cache(self, batch, max_cache_len, device, execution_dtype):

comfy/text_encoders/qwen3vl.py

@@ -0,0 +1,193 @@
+import os
+
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+from transformers import Qwen2Tokenizer
+
+from comfy import sd1_clip
+import comfy.text_encoders.qwen_vl
+from .qwen35 import Qwen35VisionModel
+from .llama import BaseLlama, BaseQwen3, BaseGenerate, Llama2_, Qwen3VL_4BConfig, Qwen3VL_8BConfig
+
+
+QWEN3VL_VISION = {
+    "qwen3vl_4b": dict(hidden_size=1024, intermediate_size=4096, depth=24, deepstack_visual_indexes=[5, 11, 17]),
+    "qwen3vl_8b": dict(hidden_size=1152, intermediate_size=4304, depth=27, deepstack_visual_indexes=[8, 16, 24]),
+}
+QWEN3VL_VISION_COMMON = dict(num_heads=16, patch_size=16, temporal_patch_size=2, in_channels=3,
+                             spatial_merge_size=2, num_position_embeddings=2304)
+
+QWEN3VL_CONFIGS = {"qwen3vl_4b": Qwen3VL_4BConfig, "qwen3vl_8b": Qwen3VL_8BConfig}
+
+
+class Qwen3VLDeepstackMerger(nn.Module):
+    # DeepStack merger: postshuffle LayerNorm (applied after spatial merge), unlike the main merger.
+    def __init__(self, hidden_size, spatial_merge_size, out_hidden_size, device=None, dtype=None, ops=None):
+        super().__init__()
+        self.merge_dim = hidden_size * (spatial_merge_size ** 2)
+        self.norm = ops.LayerNorm(self.merge_dim, eps=1e-6, device=device, dtype=dtype)
+        self.linear_fc1 = ops.Linear(self.merge_dim, self.merge_dim, device=device, dtype=dtype)
+        self.linear_fc2 = ops.Linear(self.merge_dim, out_hidden_size, device=device, dtype=dtype)
+
+    def forward(self, x):
+        x = self.norm(x.view(-1, self.merge_dim))
+        return self.linear_fc2(F.gelu(self.linear_fc1(x)))
+
+
+class Qwen3VLVisionModel(Qwen35VisionModel):
+    # Qwen3.5 vision + DeepStack
+    def __init__(self, config, device=None, dtype=None, ops=None):
+        super().__init__(config, device=device, dtype=dtype, ops=ops)
+        self.deepstack_visual_indexes = config["deepstack_visual_indexes"]
+        self.deepstack_merger_list = nn.ModuleList([
+            Qwen3VLDeepstackMerger(self.hidden_size, self.spatial_merge_size, config["out_hidden_size"], device=device, dtype=dtype, ops=ops)
+            for _ in self.deepstack_visual_indexes
+        ])
+
+
+class Qwen3VL(BaseLlama, BaseQwen3, BaseGenerate, torch.nn.Module):
+    model_type = "qwen3vl_8b"
+
+    def __init__(self, config_dict, dtype, device, operations):
+        super().__init__()
+        config = QWEN3VL_CONFIGS[self.model_type](**config_dict)
+        self.num_layers = config.num_hidden_layers
+        self.model = Llama2_(config, device=device, dtype=dtype, ops=operations)
+        vision_config = {**QWEN3VL_VISION_COMMON, **QWEN3VL_VISION[self.model_type], "out_hidden_size": config.hidden_size}
+        self.visual = Qwen3VLVisionModel(vision_config, device=device, dtype=dtype, ops=operations)
+        self.dtype = dtype
+
+    def preprocess_embed(self, embed, device):
+        if embed["type"] == "image":
+            # Qwen3-VL normalizes to [-1, 1] (mean/std 0.5), unlike Qwen2.5-VL's CLIP normalization.
+            image, grid = comfy.text_encoders.qwen_vl.process_qwen2vl_images(embed["data"], patch_size=16, image_mean=[0.5, 0.5, 0.5], image_std=[0.5, 0.5, 0.5])
+            merged, deepstack = self.visual(image.to(device, dtype=torch.float32), grid)
+            return merged, {"grid": grid, "deepstack": deepstack}
+        return None, None
+
+    def build_image_inputs(self, embeds, embeds_info):
+        # Returns (position_ids, visual_pos_masks, deepstack) for the prompt
+        images = sorted([e for e in embeds_info if e.get("type") == "image"], key=lambda e: e["index"])
+        if len(images) == 0:
+            return None, None, None
+
+        device = embeds.device
+        seq = embeds.shape[1]
+        position_ids = comfy.text_encoders.qwen_vl.qwen2vl_mrope_position_ids(embeds_info, seq, device)
+
+        # DeepStack: mask of image positions + per-vision-layer features to inject there.
+        visual_pos_masks = torch.zeros((1, seq), dtype=torch.bool, device=device)
+        deepstack = None
+        for e in images:
+            start = e["index"]
+            end = e["size"] + start
+            visual_pos_masks[0, start:end] = True
+            ds = e["extra"]["deepstack"]
+            if deepstack is None:
+                deepstack = [d for d in ds]
+            else:
+                deepstack = [torch.cat([deepstack[i], ds[i]], dim=0) for i in range(len(ds))]
+        return position_ids, visual_pos_masks, deepstack
+
+
+def _make_qwen3vl_model(model_type):
+    class Qwen3VL_(Qwen3VL):
+        pass
+    Qwen3VL_.model_type = model_type
+    return Qwen3VL_
+
+
+class Qwen3VLClipModel(sd1_clip.SDClipModel):
+    def __init__(self, device="cpu", layer="hidden", layer_idx=-1, dtype=None, attention_mask=True, model_options={}, model_type="qwen3vl_8b"):
+        super().__init__(device=device, layer=layer, layer_idx=layer_idx, textmodel_json_config={},
+                         dtype=dtype, special_tokens={"pad": 151643}, layer_norm_hidden_state=False,
+                         model_class=_make_qwen3vl_model(model_type), enable_attention_masks=attention_mask,
+                         return_attention_masks=attention_mask, model_options=model_options)
+
+    def generate(self, tokens, do_sample, max_length, temperature, top_k, top_p, min_p, repetition_penalty, seed, presence_penalty=0.0):
+        if isinstance(tokens, dict):
+            tokens = next(iter(tokens.values()))
+        tokens_only = [[t[0] for t in b] for b in tokens]
+        embeds, _, _, embeds_info = self.process_tokens(tokens_only, self.execution_device)
+        position_ids, visual_pos_masks, deepstack = self.transformer.build_image_inputs(embeds, embeds_info)
+        return self.transformer.generate(embeds, do_sample, max_length, temperature, top_k, top_p, min_p, repetition_penalty, seed,
+                                         presence_penalty=presence_penalty, position_ids=position_ids,
+                                         visual_pos_masks=visual_pos_masks, deepstack_embeds=deepstack)
+
+
+class Qwen3VLTEModel(sd1_clip.SD1ClipModel):
+    def __init__(self, device="cpu", dtype=None, model_options={}, model_type="qwen3vl_8b"):
+        clip_model = lambda **kw: Qwen3VLClipModel(**kw, model_type=model_type)
+        super().__init__(device=device, dtype=dtype, name=model_type, clip_model=clip_model, model_options=model_options)
+
+
+class Qwen3VLSDTokenizer(sd1_clip.SDTokenizer):
+    def __init__(self, embedding_directory=None, tokenizer_data={}, embedding_size=4096, embedding_key="qwen3vl_8b"):
+        tokenizer_path = os.path.join(os.path.dirname(os.path.realpath(__file__)), "qwen25_tokenizer")
+        super().__init__(tokenizer_path, pad_with_end=False, embedding_directory=embedding_directory, embedding_size=embedding_size, embedding_key=embedding_key, tokenizer_class=Qwen2Tokenizer,
+                         has_start_token=False, has_end_token=False, pad_to_max_length=False, max_length=99999999, min_length=1, pad_token=151643, tokenizer_data=tokenizer_data)
+
+
+class Qwen3VLTokenizer(sd1_clip.SD1Tokenizer):
+    def __init__(self, embedding_directory=None, tokenizer_data={}, model_type="qwen3vl_8b"):
+        embedding_size = 2560 if model_type == "qwen3vl_4b" else 4096
+        tokenizer = lambda *a, **kw: Qwen3VLSDTokenizer(*a, **kw, embedding_size=embedding_size, embedding_key=model_type)
+        super().__init__(embedding_directory=embedding_directory, tokenizer_data=tokenizer_data, name=model_type, tokenizer=tokenizer)
+        self.llama_template = "<|im_start|>user\n{}<|im_end|>\n<|im_start|>assistant\n"
+        self.llama_template_images = "<|im_start|>user\n<|vision_start|><|image_pad|><|vision_end|>{}<|im_end|>\n<|im_start|>assistant\n"
+
+    def tokenize_with_weights(self, text, return_word_ids=False, llama_template=None, images=[], prevent_empty_text=False, thinking=False, **kwargs):
+        image = kwargs.get("image", None)
+        if image is not None and len(images) == 0:
+            images = [image[i:i + 1] for i in range(image.shape[0])]
+
+        skip_template = text.startswith('<|im_start|>')
+        if prevent_empty_text and text == '':
+            text = ' '
+
+        if skip_template:
+            llama_text = text
+        else:
+            if llama_template is not None:
+                template = llama_template
+            elif len(images) == 0:
+                template = self.llama_template
+            else:
+                template = self.llama_template_images
+                if len(images) > 1:
+                    vision_block = "<|vision_start|><|image_pad|><|vision_end|>"
+                    template = template.replace(vision_block, vision_block * len(images), 1)
+            llama_text = template.format(text)
+            if not thinking:  # Qwen3 convention: empty think block suppresses reasoning
+                llama_text += "<think>\n\n</think>\n\n"
+
+        tokens = super().tokenize_with_weights(llama_text, return_word_ids=return_word_ids, disable_weights=True, **kwargs)
+        key_name = next(iter(tokens))
+        embed_count = 0
+        for r in tokens[key_name]:
+            for i in range(len(r)):
+                if isinstance(r[i][0], (int, float)) and r[i][0] == 151655:  # <|image_pad|>
+                    if len(images) > embed_count:
+                        r[i] = ({"type": "image", "data": images[embed_count], "original_type": "image"},) + r[i][1:]
+                        embed_count += 1
+        return tokens
+
+
+def tokenizer(model_type="qwen3vl_8b"):
+    class Qwen3VLTokenizer_(Qwen3VLTokenizer):
+        def __init__(self, embedding_directory=None, tokenizer_data={}):
+            super().__init__(embedding_directory=embedding_directory, tokenizer_data=tokenizer_data, model_type=model_type)
+    return Qwen3VLTokenizer_
+
+
+def te(dtype_llama=None, llama_quantization_metadata=None, model_type="qwen3vl_8b"):
+    class Qwen3VLTEModel_(Qwen3VLTEModel):
+        def __init__(self, device="cpu", dtype=None, model_options={}):
+            if dtype_llama is not None:
+                dtype = dtype_llama
+            if llama_quantization_metadata is not None:
+                model_options = model_options.copy()
+                model_options["quantization_metadata"] = llama_quantization_metadata
+            super().__init__(device=device, dtype=dtype, model_options=model_options, model_type=model_type)
+    return Qwen3VLTEModel_

comfy/text_encoders/qwen_vl.py

@@ -88,6 +88,32 @@ def process_qwen2vl_images(
     return flatten_patches, image_grid_thw
 
 
+def qwen2vl_mrope_position_ids(embeds_info, seq_len, device):
+    # (3, seq_len) T/H/W MRoPE position ids: text runs sequentially, each image span gets its grid positions.
+    # Returns None when there are no image embeds. `extra` is the image grid_thw, or a dict carrying it under "grid".
+    position_ids = None
+    offset = 0
+    for e in embeds_info:
+        if e.get("type") == "image":
+            extra = e.get("extra", None)
+            grid = extra["grid"] if isinstance(extra, dict) else extra
+            start = e.get("index")
+            if position_ids is None:
+                position_ids = torch.zeros((3, seq_len), device=device)
+                position_ids[:, :start] = torch.arange(0, start, device=device)
+            end = e.get("size") + start
+            len_max = int(grid.max()) // 2
+            start_next = len_max + start
+            position_ids[:, end:] = torch.arange(start_next + offset, start_next + (seq_len - end) + offset, device=device)
+            position_ids[0, start:end] = start + offset
+            max_d = int(grid[0][1]) // 2
+            position_ids[1, start:end] = torch.arange(start + offset, start + max_d + offset, device=device).unsqueeze(1).repeat(1, math.ceil((end - start) / max_d)).flatten(0)[:end - start]
+            max_d = int(grid[0][2]) // 2
+            position_ids[2, start:end] = torch.arange(start + offset, start + max_d + offset, device=device).unsqueeze(0).repeat(math.ceil((end - start) / max_d), 1).flatten(0)[:end - start]
+            offset += len_max - (end - start)
+    return position_ids
+
+
 class VisionPatchEmbed(nn.Module):
     def __init__(
         self,

comfy/utils.py

@@ -818,6 +818,44 @@ def z_image_to_diffusers(mmdit_config, output_prefix=""):
 
     return key_map
 
+def krea2_to_diffusers(mmdit_config, output_prefix=""):
+    n_layers = mmdit_config.get("layers", 0)
+    n_txt_layerwise = 2  # TextFusionTransformer hardcodes 2 layerwise + 2 refiner blocks
+    n_txt_refiner = 2
+    key_map = {}
+
+    def add_block(prefix_to, prefix_from):
+        block_map = {
+            "attn.to_q": "attn.wq", "attn.to_k": "attn.wk", "attn.to_v": "attn.wv",
+            "attn.to_gate": "attn.gate", "attn.to_out.0": "attn.wo",
+            "attn.to_out": "attn.wo",  # some tools drop the ".0" on to_out
+            "ff.gate": "mlp.gate", "ff.up": "mlp.up", "ff.down": "mlp.down",
+        }
+        for d, c in block_map.items():
+            key_map["{}.{}.weight".format(prefix_to, d)] = "{}{}.{}.weight".format(output_prefix, prefix_from, c)
+
+    for i in range(n_layers):
+        add_block("transformer_blocks.{}".format(i), "blocks.{}".format(i))
+    for i in range(n_txt_layerwise):
+        add_block("text_fusion.layerwise_blocks.{}".format(i), "txtfusion.layerwise_blocks.{}".format(i))
+    for i in range(n_txt_refiner):
+        add_block("text_fusion.refiner_blocks.{}".format(i), "txtfusion.refiner_blocks.{}".format(i))
+
+    MAP_BASIC = [
+        ("img_in", "first"),
+        ("time_embed.linear_1", "tmlp.0"),
+        ("time_embed.linear_2", "tmlp.2"),
+        ("time_mod_proj", "tproj.1"),
+        ("txt_in.linear_1", "txtmlp.1"),
+        ("txt_in.linear_2", "txtmlp.3"),
+        ("text_fusion.projector", "txtfusion.projector"),
+        ("final_layer.linear", "last.linear"),
+    ]
+    for d, c in MAP_BASIC:
+        key_map["{}.weight".format(d)] = "{}{}.weight".format(output_prefix, c)
+
+    return key_map
+
 def repeat_to_batch_size(tensor, batch_size, dim=0):
     if tensor.shape[dim] > batch_size:
         return tensor.narrow(dim, 0, batch_size)

comfy_api/feature_flags.py

@@ -25,6 +25,11 @@ CLI_FEATURE_FLAG_REGISTRY: dict[str, FeatureFlagInfo] = {
         "default": False,
         "description": "Show the sign-in button in the frontend even when not signed in",
     },
+    "enable_telemetry": {
+        "type": "bool",
+        "default": False,
+        "description": "Signal the frontend that telemetry collection is enabled",
+    },
 }
 
 

comfy_api/latest/_input/video_types.py

@@ -27,10 +27,13 @@ class VideoInput(ABC):
         path: Union[str, IO[bytes]],
         format: VideoContainer = VideoContainer.AUTO,
         codec: VideoCodec = VideoCodec.AUTO,
-        metadata: Optional[dict] = None
+        metadata: Optional[dict] = None,
+        bit_depth: int | None = None,
     ):
         """
         Abstract method to save the video input to a file.
+
+        bit_depth selects the encoded bit depth; None keeps the video's native depth.
         """
         pass
 
@@ -83,6 +86,14 @@ class VideoInput(ABC):
         components = self.get_components()
         return components.images.shape[2], components.images.shape[1]
 
+    def get_bit_depth(self) -> int:
+        """
+        Returns the bit depth of the video (e.g. 8 or 10).
+
+        Default implementation returns 8; subclasses report their real depth.
+        """
+        return 8
+
     def get_duration(self) -> float:
         """
         Returns the duration of the video in seconds.

comfy_api/latest/_input_impl/video_types.py

@@ -52,6 +52,12 @@ def get_open_write_kwargs(
     return open_kwargs
 
 
+def video_stream_bit_depth(stream) -> int:
+    if stream is None or stream.format is None or not stream.format.components:
+        return 8
+    return max(component.bits for component in stream.format.components)
+
+
 class VideoFromFile(VideoInput):
     """
     Class representing video input from a file.
@@ -97,6 +103,13 @@ class VideoFromFile(VideoInput):
                     return stream.width, stream.height
         raise ValueError(f"No video stream found in file '{self.__file}'")
 
+    def get_bit_depth(self) -> int:
+        if isinstance(self.__file, io.BytesIO):
+            self.__file.seek(0)  # Reset the BytesIO object to the beginning
+        with av.open(self.__file, mode="r") as container:
+            video_stream = container.streams.video[0] if len(container.streams.video) > 0 else None
+            return video_stream_bit_depth(video_stream)
+
     def get_duration(self) -> float:
         """
         Returns the duration of the video in seconds.
@@ -257,6 +270,7 @@ class VideoFromFile(VideoInput):
 
         image_format = 'gbrpf32le'
         process_image_format = lambda a: a
+        align_graph = None
         audio = None
 
         streams = [video_stream]
@@ -310,7 +324,28 @@ class VideoFromFile(VideoInput):
 
                             checked_alpha = True
 
-                        img = frame.to_ndarray(format=image_format)  # shape: (H, W, 4)
+                        # Fix non-deterministic video decode when the video width is not a multiple of 32
+                        # For non-yuvj pixel formats: most H.264/H.265 video and static images (e.g. lossy WebP via LoadImage)
+                        # Pad both axes to a multiple of 32 and smear the border so the alignment padding never bleeds into the cropped edges
+                        if image_format in ('gbrpf32le', 'gbrapf32le') and frame.width % 32 != 0:
+                            if align_graph is None:
+                                pad_w = ((frame.width + 31) // 32) * 32
+                                pad_h = ((frame.height + 31) // 32) * 32
+                                g = av.filter.Graph()
+                                g_src = g.add_buffer(width=frame.width, height=frame.height,
+                                                     format=frame.format.name, time_base=video_stream.time_base)
+                                g_pad = g.add('pad', f'{pad_w}:{pad_h}:0:0')
+                                g_fill = g.add('fillborders', f'left=0:right={pad_w - frame.width}:top=0:bottom={pad_h - frame.height}:mode=smear')
+                                g_sink = g.add('buffersink')
+                                g_src.link_to(g_pad)
+                                g_pad.link_to(g_fill)
+                                g_fill.link_to(g_sink)
+                                g.configure()
+                                align_graph = (g, g_src, g_sink)
+                            align_graph[1].push(frame)
+                            img = np.ascontiguousarray(align_graph[2].pull().to_ndarray(format=image_format)[:frame.height, :frame.width])
+                        else:
+                            img = frame.to_ndarray(format=image_format)
                         if frame.rotation != 0:
                             k = int(round(frame.rotation // 90))
                             img = np.rot90(img, k=k, axes=(0, 1)).copy()
@@ -377,25 +412,32 @@ class VideoFromFile(VideoInput):
         format: VideoContainer = VideoContainer.AUTO,
         codec: VideoCodec = VideoCodec.AUTO,
         metadata: Optional[dict] = None,
+        bit_depth: int | None = None,
     ):
         if isinstance(self.__file, io.BytesIO):
             self.__file.seek(0)  # Reset the BytesIO object to the beginning
         with av.open(self.__file, mode='r') as container:
             container_format = container.format.name
-            video_encoding = container.streams.video[0].codec.name if len(container.streams.video) > 0 else None
+            video_stream = container.streams.video[0] if len(container.streams.video) > 0 else None
+            video_encoding = video_stream.codec.name if video_stream is not None else None
+            source_bit_depth = video_stream_bit_depth(video_stream)
             reuse_streams = True
             if format != VideoContainer.AUTO and format not in container_format.split(","):
                 reuse_streams = False
             if codec != VideoCodec.AUTO and codec != video_encoding and video_encoding is not None:
                 reuse_streams = False
+            if bit_depth is not None and video_encoding is not None and bit_depth != source_bit_depth:
+                reuse_streams = False
             if self.__start_time or self.__duration:
                 reuse_streams = False
 
             if not reuse_streams:
+                if bit_depth is None:
+                    bit_depth = source_bit_depth
                 components = self.get_components_internal(container)
                 video = VideoFromComponents(components)
                 return video.save_to(
-                    path, format=format, codec=codec, metadata=metadata
+                    path, format=format, codec=codec, metadata=metadata, bit_depth=bit_depth,
                 )
 
             streams = container.streams
@@ -451,8 +493,10 @@ class VideoFromComponents(VideoInput):
     Class representing video input from tensors.
     """
 
-    def __init__(self, components: VideoComponents):
+    def __init__(self, components: VideoComponents, bit_depth: int = 8):
         self.__components = components
+        # Tensor components have no inherent bit depth; this is the depth used when encoding.
+        self.__bit_depth = bit_depth
 
     def get_components(self) -> VideoComponents:
         return VideoComponents(
@@ -461,18 +505,26 @@ class VideoFromComponents(VideoInput):
             frame_rate=self.__components.frame_rate,
         )
 
+    def get_bit_depth(self) -> int:
+        return self.__bit_depth
+
     def save_to(
         self,
         path: str,
         format: VideoContainer = VideoContainer.AUTO,
         codec: VideoCodec = VideoCodec.AUTO,
         metadata: Optional[dict] = None,
+        bit_depth: int | None = None,
     ):
         """Save the video to a file path or BytesIO buffer."""
         if format != VideoContainer.AUTO and format != VideoContainer.MP4:
             raise ValueError("Only MP4 format is supported for now")
         if codec != VideoCodec.AUTO and codec != VideoCodec.H264:
             raise ValueError("Only H264 codec is supported for now")
+        # None means "use the depth this video was created with" (CreateVideo's choice).
+        if bit_depth is None:
+            bit_depth = self.__bit_depth
+        is_10bit = bit_depth >= 10
         extra_kwargs = {}
         if isinstance(format, VideoContainer) and format != VideoContainer.AUTO:
             extra_kwargs["format"] = format.value
@@ -488,10 +540,11 @@ class VideoFromComponents(VideoInput):
 
             frame_rate = Fraction(round(self.__components.frame_rate * 1000), 1000)
             # Create a video stream
+            pix_fmt = "yuv420p10le" if is_10bit else "yuv420p"
             video_stream = output.add_stream('h264', rate=frame_rate)
             video_stream.width = self.__components.images.shape[2]
             video_stream.height = self.__components.images.shape[1]
-            video_stream.pix_fmt = 'yuv420p'
+            video_stream.pix_fmt = pix_fmt
 
             # Create an audio stream
             audio_sample_rate = 1
@@ -505,9 +558,14 @@ class VideoFromComponents(VideoInput):
 
             # Encode video
             for i, frame in enumerate(self.__components.images):
-                img = (frame * 255).clamp(0, 255).byte().cpu().numpy() # shape: (H, W, 3)
-                frame = av.VideoFrame.from_ndarray(img, format='rgb24')
-                frame = frame.reformat(format='yuv420p')  # Convert to YUV420P as required by h264
+                if is_10bit:
+                    # 16-bit RGB keeps float precision through the conversion to 10-bit YUV.
+                    img = (frame.float() * 65535).clamp(0, 65535).cpu().numpy().astype(np.uint16)  # shape: (H, W, 3)
+                    frame = av.VideoFrame.from_ndarray(img, format="rgb48le")
+                else:
+                    img = (frame * 255).clamp(0, 255).byte().cpu().numpy() # shape: (H, W, 3)
+                    frame = av.VideoFrame.from_ndarray(img, format='rgb24')
+                frame = frame.reformat(format=pix_fmt)
                 packet = video_stream.encode(frame)
                 output.mux(packet)
 

comfy_api/latest/_io.py

@@ -755,6 +755,18 @@ class File3DKSPLAT(ComfyTypeIO):
     Type = File3D
 
 
+@comfytype(io_type="FILE_3D_SPLAT_ANY")
+class File3DSplatAny(ComfyTypeIO):
+    """General 3D Gaussian splat file type - accepts any supported splat container (.ply / .spz / .splat / .ksplat)."""
+    Type = File3D
+
+
+@comfytype(io_type="FILE_3D_POINT_CLOUD_ANY")
+class File3DPointCloudAny(ComfyTypeIO):
+    """General point cloud file type - accepts any supported point cloud container (currently .ply)."""
+    Type = File3D
+
+
 @comfytype(io_type="HOOKS")
 class Hooks(ComfyTypeIO):
     if TYPE_CHECKING:
@@ -879,6 +891,14 @@ class Tracks(ComfyTypeIO):
         track_visibility: torch.Tensor
     Type = TrackDict
 
+@comfytype(io_type="DICT")
+class Dict(ComfyTypeIO):
+    Type = dict
+
+@comfytype(io_type="ARRAY")
+class Array(ComfyTypeIO):
+    Type = list
+
 @comfytype(io_type="COMFY_MULTITYPED_V3")
 class MultiType:
     Type = Any
@@ -1241,6 +1261,155 @@ class DynamicSlot(ComfyTypeI):
             out_dict[input_type][finalized_id] = value
             out_dict["dynamic_paths"][finalized_id] = finalize_prefix(curr_prefix, curr_prefix[-1])
 
+@comfytype(io_type="COMFY_DYNAMICGROUP_V3")
+class DynamicGroup(ComfyTypeI):
+    """A repeatable group of widget inputs (e.g. lora_name + strength stacked into N rows).
+
+    At execution time the node receives a ``list[dict]`` where each element is a row.
+
+    Example::
+
+        io.DynamicGroup.Input(
+            "loras",
+            template=[
+                io.Combo.Input("lora_name", options=folder_paths.get_filename_list("loras")),
+                io.Float.Input("strength", default=1.0, min=-100, max=100, step=0.01),
+            ],
+            min=0,
+            max=50,
+        )
+        # execute receives: loras: list[dict] = [{"lora_name": "x.safetensors", "strength": 1.0}, ...]
+    """
+
+    Type = list[dict[str, Any]]
+    _MaxRows = 100
+
+    class Input(DynamicInput):
+        def __init__(
+            self,
+            id: str,
+            template: list["Input"],
+            min: int = 0,
+            max: int = 50,
+            display_name: str = None,
+            optional: bool = False,
+            tooltip: str = None,
+            lazy: bool = None,
+            extra_dict=None,
+            group_name: str = "Group",
+        ):
+            super().__init__(id, display_name, optional, tooltip, lazy, extra_dict)
+            assert len(template) > 0, "DynamicGroup template must have at least one field."
+            for t in template:
+                assert isinstance(t, WidgetInput), (
+                    f"DynamicGroup template field '{t.id}' must be a WidgetInput subclass "
+                    f"(Combo, Float, Int, String, Boolean, Color). Got {type(t).__name__}."
+                )
+                assert not isinstance(t, DynamicInput), (
+                    f"DynamicGroup template field '{t.id}' must not be a DynamicInput. "
+                    "Nesting dynamic inputs inside DynamicGroup is not supported."
+                )
+            field_ids = [t.id for t in template]
+            assert len(field_ids) == len(set(field_ids)), (
+                f"DynamicGroup template field ids must be unique within a row. Got: {field_ids}"
+            )
+            # Reject "." in group id and template field ids: slot_id encoding uses "." as a
+            # delimiter (<group_id>.<row>.<field_id>), so any "." in these names would cause
+            # path.split(".") to produce the wrong number of segments during decoding.
+            assert "." not in id, (
+                f"DynamicGroup id must not contain '.'. Got: '{id}'"
+            )
+            for t in template:
+                assert "." not in t.id, (
+                    f"DynamicGroup template field id must not contain '.'. Got: '{t.id}'"
+                )
+            assert min >= 0, "DynamicGroup min must be >= 0."
+            assert max >= 1, "DynamicGroup max must be >= 1."
+            assert max <= DynamicGroup._MaxRows, f"DynamicGroup max must be <= {DynamicGroup._MaxRows}."
+            assert min <= max, "DynamicGroup min must be <= max."
+            self.template = template
+            self.min = min
+            self.max = max
+            self.group_name = group_name
+
+        def get_all(self) -> list["Input"]:
+            return [self] + list(self.template)
+
+        def as_dict(self):
+            return super().as_dict() | prune_dict({
+                "template": create_input_dict_v1(self.template),
+                "min": self.min,
+                "max": self.max,
+                "group_name": self.group_name,
+            })
+
+        def validate(self):
+            for t in self.template:
+                t.validate()
+
+    @staticmethod
+    def _expand_schema_for_dynamic(
+        out_dict: dict[str, Any],
+        live_inputs: dict[str, Any],
+        value: tuple[str, dict[str, Any]],
+        input_type: str,
+        curr_prefix: list[str] | None,
+    ):
+        info = value[1]
+        min_rows: int = info.get("min", 0)
+        max_rows: int = info.get("max", DynamicGroup._MaxRows)
+        template: dict[str, Any] = info.get("template", {})
+
+        # Collect all template field specs across required/optional sections
+        field_specs: list[tuple[str, tuple[str, dict[str, Any]], bool]] = []
+        for field_required_key in ("required", "optional"):
+            section = template.get(field_required_key, {})
+            is_required_field = field_required_key == "required"
+            for field_id, field_value in section.items():
+                field_specs.append((field_id, field_value, is_required_field))
+
+        # Determine how many rows are currently present by scanning live_inputs
+        finalized_prefix = finalize_prefix(curr_prefix)
+        present_rows = 0
+        for live_key in live_inputs:
+            # Keys look like "<prefix>.<row>.<field_id>"
+            if live_key.startswith(finalized_prefix + "."):
+                remainder = live_key[len(finalized_prefix) + 1:]
+                parts = remainder.split(".", 1)
+                if len(parts) >= 1:
+                    try:
+                        row_idx = int(parts[0])
+                        present_rows = max(present_rows, row_idx + 1)
+                    except ValueError:
+                        pass
+
+        if present_rows > max_rows:
+            raise ValueError(
+                f"DynamicGroup input '{finalized_prefix}' received {present_rows} rows but max is {max_rows}."
+            )
+        row_count = max(min_rows, present_rows)
+
+        for row in range(row_count):
+            for field_id, field_value, is_required_field in field_specs:
+                slot_id = f"{finalized_prefix}.{row}.{field_id}"
+                if row < min_rows and is_required_field:
+                    out_dict["required"][slot_id] = field_value
+                else:
+                    out_dict["optional"][slot_id] = field_value
+                # Register into dynamic_paths so build_nested_inputs places value at the right path
+                out_dict["dynamic_paths"][slot_id] = slot_id
+
+        # Track the list root path so build_nested_inputs can convert the index dict to a list
+        out_dict.setdefault("list_paths", set()).add(finalized_prefix)
+
+        # Handle the empty case (0 rows) – emit an empty-list default for the parent.
+        # This must only fire when there are genuinely no rows; otherwise the parent
+        # path would clobber the per-row dict built from the slot ids above.
+        if row_count == 0:
+            out_dict["dynamic_paths"][finalized_prefix] = finalized_prefix
+            out_dict["dynamic_paths_default_value"][finalized_prefix] = DynamicPathsDefaultValue.EMPTY_LIST
+
+
 @comfytype(io_type="IMAGECOMPARE")
 class ImageCompare(ComfyTypeI):
   Type = dict
@@ -1267,6 +1436,19 @@ class Color(ComfyTypeIO):
       def as_dict(self):
           return super().as_dict()
 
+
+@comfytype(io_type="COLORS")
+class Colors(ComfyTypeIO):
+    Type = list[Color.Type]
+
+    class Input(WidgetInput):
+        def __init__(self, id: str, display_name: str=None, optional=False, tooltip: str=None,
+                     socketless: bool=True, default: list[str]=None, advanced: bool=None):
+            super().__init__(id, display_name, optional, tooltip, None, default, socketless, None, None, None, None, advanced)
+            if default is None:
+                self.default = []
+
+
 @comfytype(io_type="BOUNDING_BOX")
 class BoundingBox(ComfyTypeIO):
     class BoundingBoxDict(TypedDict):
@@ -1314,6 +1496,20 @@ class Curve(ComfyTypeIO):
             return d
 
 
+@comfytype(io_type="BOUNDING_BOXES")
+class BoundingBoxes(ComfyTypeIO):
+    class BoundingBoxWithMetadata(BoundingBox.BoundingBoxDict):
+        metadata: dict
+    Type = list[BoundingBoxWithMetadata]
+
+    class Input(WidgetInput):
+        def __init__(self, id: str, display_name: str=None, optional=False, tooltip: str=None,
+                     socketless: bool=True, default: list[dict]=None, advanced: bool=None):
+            super().__init__(id, display_name, optional, tooltip, None, default, socketless, None, None, None, None, advanced)
+            if default is None:
+                self.default = []
+
+
 @comfytype(io_type="HISTOGRAM")
 class Histogram(ComfyTypeIO):
     """A histogram represented as a list of bin counts."""
@@ -1371,6 +1567,8 @@ def setup_dynamic_input_funcs():
     register_dynamic_input_func(DynamicCombo.io_type, DynamicCombo._expand_schema_for_dynamic)
     # DynamicSlot.Input
     register_dynamic_input_func(DynamicSlot.io_type, DynamicSlot._expand_schema_for_dynamic)
+    # DynamicGroup.Input
+    register_dynamic_input_func(DynamicGroup.io_type, DynamicGroup._expand_schema_for_dynamic)
 
 if len(DYNAMIC_INPUT_LOOKUP) == 0:
     setup_dynamic_input_funcs()
@@ -1382,13 +1580,16 @@ class V3Data(TypedDict):
     'Dictionary where the keys are the input ids and the values dictate how to turn the inputs into a nested dictionary.'
     dynamic_paths_default_value: dict[str, Any]
     'Dictionary where the keys are the input ids and the values are a string from DynamicPathsDefaultValue for the inputs if value is None.'
+    list_paths: set[str]
+    'Set of top-level keys whose index-keyed dict values should be converted to a sorted list[dict] after build_nested_inputs runs.'
     create_dynamic_tuple: bool
     'When True, the value of the dynamic input will be in the format (value, path_key).'
 
 class HiddenHolder:
     def __init__(self, unique_id: str, prompt: Any,
                  extra_pnginfo: Any, dynprompt: Any,
-                 auth_token_comfy_org: str, api_key_comfy_org: str, **kwargs):
+                 auth_token_comfy_org: str, api_key_comfy_org: str,
+                 comfy_usage_source: str = None, **kwargs):
         self.unique_id = unique_id
         """UNIQUE_ID is the unique identifier of the node, and matches the id property of the node on the client side. It is commonly used in client-server communications (see messages)."""
         self.prompt = prompt
@@ -1401,6 +1602,8 @@ class HiddenHolder:
         """AUTH_TOKEN_COMFY_ORG is a token acquired from signing into a ComfyOrg account on frontend."""
         self.api_key_comfy_org = api_key_comfy_org
         """API_KEY_COMFY_ORG is an API Key generated by ComfyOrg that allows skipping signing into a ComfyOrg account on frontend."""
+        self.comfy_usage_source = comfy_usage_source
+        """COMFY_USAGE_SOURCE identifies the client that submitted the prompt (e.g. comfyui-frontend, comfy-cli, comfyui-mcp); forwarded to API nodes' upstream requests via the Comfy-Usage-Source header."""
 
     def __getattr__(self, key: str):
         '''If hidden variable not found, return None.'''
@@ -1417,6 +1620,7 @@ class HiddenHolder:
             dynprompt=d.get(Hidden.dynprompt, None),
             auth_token_comfy_org=d.get(Hidden.auth_token_comfy_org, None),
             api_key_comfy_org=d.get(Hidden.api_key_comfy_org, None),
+            comfy_usage_source=d.get(Hidden.comfy_usage_source, None),
         )
 
     @classmethod
@@ -1439,6 +1643,8 @@ class Hidden(str, Enum):
     """AUTH_TOKEN_COMFY_ORG is a token acquired from signing into a ComfyOrg account on frontend."""
     api_key_comfy_org = "API_KEY_COMFY_ORG"
     """API_KEY_COMFY_ORG is an API Key generated by ComfyOrg that allows skipping signing into a ComfyOrg account on frontend."""
+    comfy_usage_source = "COMFY_USAGE_SOURCE"
+    """COMFY_USAGE_SOURCE identifies the client that submitted the prompt (e.g. comfyui-frontend, comfy-cli, comfyui-mcp); forwarded to API nodes' upstream requests via the Comfy-Usage-Source header."""
 
 
 @dataclass
@@ -1642,6 +1848,8 @@ class Schema:
                 self.hidden.append(Hidden.auth_token_comfy_org)
             if Hidden.api_key_comfy_org not in self.hidden:
                 self.hidden.append(Hidden.api_key_comfy_org)
+            if Hidden.comfy_usage_source not in self.hidden:
+                self.hidden.append(Hidden.comfy_usage_source)
         # if is an output_node, will need prompt and extra_pnginfo
         if self.is_output_node:
             if Hidden.prompt not in self.hidden:
@@ -1715,6 +1923,7 @@ def get_finalized_class_inputs(d: dict[str, Any], live_inputs: dict[str, Any], i
         "optional": {},
         "dynamic_paths": {},
         "dynamic_paths_default_value": {},
+        "list_paths": set(),
     }
     d = d.copy()
     # ignore hidden for parsing
@@ -1730,6 +1939,10 @@ def get_finalized_class_inputs(d: dict[str, Any], live_inputs: dict[str, Any], i
     dynamic_paths_default_value = out_dict.pop("dynamic_paths_default_value", None)
     if dynamic_paths_default_value is not None and len(dynamic_paths_default_value) > 0:
         v3_data["dynamic_paths_default_value"] = dynamic_paths_default_value
+    # list_paths: keys whose nested dict should be post-converted to a sorted list[dict]
+    list_paths = out_dict.pop("list_paths", None)
+    if list_paths:
+        v3_data["list_paths"] = list_paths
     return out_dict, hidden, v3_data
 
 def parse_class_inputs(out_dict: dict[str, Any], live_inputs: dict[str, Any], curr_dict: dict[str, Any], curr_prefix: list[str] | None=None) -> None:
@@ -1765,10 +1978,12 @@ def add_to_dict_v1(i: Input, d: dict):
 
 class DynamicPathsDefaultValue:
     EMPTY_DICT = "empty_dict"
+    EMPTY_LIST = "empty_list"
 
 def build_nested_inputs(values: dict[str, Any], v3_data: V3Data):
     paths = v3_data.get("dynamic_paths", None)
     default_value_dict = v3_data.get("dynamic_paths_default_value", {})
+    list_paths: set[str] = v3_data.get("list_paths", set()) or set()
     if paths is None:
         return values
     values = values.copy()
@@ -1791,6 +2006,8 @@ def build_nested_inputs(values: dict[str, Any], v3_data: V3Data):
                     default_option = default_value_dict.get(key, None)
                     if default_option == DynamicPathsDefaultValue.EMPTY_DICT:
                         value = {}
+                    elif default_option == DynamicPathsDefaultValue.EMPTY_LIST:
+                        value = []
                 if create_tuple:
                     value = (value, key)
                 current[p] = value
@@ -1798,6 +2015,34 @@ def build_nested_inputs(values: dict[str, Any], v3_data: V3Data):
                 current = current.setdefault(p, {})
 
     values.update(result)
+
+    # Post-pass: convert index-keyed dicts to sorted lists for io.DynamicGroup fields
+    for list_path in list_paths:
+        parts = list_path.split(".")
+        # Navigate to the parent container, then convert the leaf
+        container = values
+        for part in parts[:-1]:
+            if not isinstance(container, dict) or part not in container:
+                container = None
+                break
+            container = container[part]
+        if container is None:
+            continue
+        leaf_key = parts[-1]
+        leaf = container.get(leaf_key, None)
+        if isinstance(leaf, dict):
+            try:
+                sorted_rows = [leaf[k] for k in sorted(leaf.keys(), key=int)]
+                container[leaf_key] = sorted_rows
+            except (ValueError, TypeError):
+                # Keys are not all integers; leave as-is
+                pass
+        elif isinstance(leaf, list):
+            # Already a list (e.g. the EMPTY_LIST default was applied above)
+            pass
+        elif leaf is None:
+            container[leaf_key] = []
+
     return values
 
 
@@ -2336,6 +2581,8 @@ __all__ = [
     "File3DSPLAT",
     "File3DSPZ",
     "File3DKSPLAT",
+    "File3DSplatAny",
+    "File3DPointCloudAny",
     "Hooks",
     "HookKeyframes",
     "TimestepsRange",
@@ -2354,11 +2601,15 @@ __all__ = [
     "AnyType",
     "MultiType",
     "Tracks",
+    "Dict",
+    "Array",
     "Color",
     # Dynamic Types
     "MatchType",
     "DynamicCombo",
+    "DynamicSlot",
     "Autogrow",
+    "DynamicGroup",
     # Other classes
     "HiddenHolder",
     "Hidden",
@@ -2372,6 +2623,8 @@ __all__ = [
     "PriceBadgeDepends",
     "PriceBadge",
     "BoundingBox",
+    "BoundingBoxes",
+    "Colors",
     "Curve",
     "Histogram",
     "Range",

comfy_api/latest/_ui.py

@@ -285,7 +285,7 @@ class AudioSaveHelper:
         results = []
         for batch_number, waveform in enumerate(audio["waveform"].cpu()):
             filename_with_batch_num = filename.replace("%batch_num%", str(batch_number))
-            file = f"{filename_with_batch_num}_{counter:05}_.{format}"
+            file = f"{filename_with_batch_num}_{counter:05}.{format}"
             output_path = os.path.join(full_output_folder, file)
 
             # Use original sample rate initially

comfy_api_nodes/apis/__init__.py

@@ -1310,13 +1310,6 @@ class KlingTaskStatus(str, Enum):
     failed = 'failed'
 
 
-class KlingTextToVideoModelName(str, Enum):
-    kling_v1 = 'kling-v1'
-    kling_v1_6 = 'kling-v1-6'
-    kling_v2_1_master = 'kling-v2-1-master'
-    kling_v2_5_turbo = 'kling-v2-5-turbo'
-
-
 class KlingVideoGenAspectRatio(str, Enum):
     field_16_9 = '16:9'
     field_9_16 = '9:16'
@@ -5179,7 +5172,7 @@ class KlingText2VideoRequest(BaseModel):
     duration: Optional[KlingVideoGenDuration] = '5'
     external_task_id: Optional[str] = Field(None, description='Customized Task ID')
     mode: Optional[KlingVideoGenMode] = 'std'
-    model_name: Optional[KlingTextToVideoModelName] = 'kling-v1'
+    model_name: Optional[str] = 'kling-v1'
     negative_prompt: Optional[str] = Field(
         None, description='Negative text prompt', max_length=2500
     )

comfy_api_nodes/apis/bfl.py

@@ -43,6 +43,7 @@ class BFLFluxEraseRequest(BaseModel):
         "white (255) marks areas to remove, black (0) marks areas to preserve.",
     )
     dilate_pixels: int = Field(10)
+    seed: int | None = Field(None)
     output_format: str = Field("png")
 
 

comfy_api_nodes/apis/bria.py

@@ -97,3 +97,28 @@ class BriaRemoveVideoBackgroundResult(BaseModel):
 class BriaRemoveVideoBackgroundResponse(BaseModel):
     status: str = Field(...)
     result: BriaRemoveVideoBackgroundResult | None = Field(None)
+
+
+class BriaVideoGreenScreenRequest(BaseModel):
+    video: str = Field(..., description="Publicly accessible URL of the input video.")
+    green_shade: str = Field(
+        default="broadcast_green",
+        description="Solid chroma-key shade applied behind the foreground "
+        "(broadcast_green, chroma_green, or blue_screen).",
+    )
+    output_container_and_codec: str = Field(...)
+    preserve_audio: bool = Field(True)
+    seed: int = Field(...)
+
+
+class BriaVideoReplaceBackgroundRequest(BaseModel):
+    video: str = Field(..., description="Publicly accessible URL of the input (foreground) video.")
+    background_url: str = Field(
+        ...,
+        description="Publicly accessible URL of the background image or video to composite behind "
+        "the foreground. Stretched to the foreground frame; match its aspect ratio for "
+        "undistorted results.",
+    )
+    output_container_and_codec: str = Field(...)
+    preserve_audio: bool = Field(True)
+    seed: int = Field(...)

comfy_api_nodes/apis/bytedance.py

@@ -1,4 +1,4 @@
-from typing import Literal
+from typing import Any, Literal
 
 from pydantic import BaseModel, Field
 
@@ -163,15 +163,31 @@ class SeedanceVirtualLibraryCreateAssetRequest(BaseModel):
     asset_type: str | None = Field(None, description="BytePlus asset type. Defaults to Image server-side when omitted.")
 
 
-# Dollars per 1K tokens, keyed by (model_id, has_video_input).
+# Dollars per 1K tokens, keyed by (model_id, has_video_input, resolution).
 SEEDANCE2_PRICE_PER_1K_TOKENS = {
-    ("dreamina-seedance-2-0-260128", False): 0.007,
-    ("dreamina-seedance-2-0-260128", True): 0.0043,
-    ("dreamina-seedance-2-0-fast-260128", False): 0.0056,
-    ("dreamina-seedance-2-0-fast-260128", True): 0.0033,
+    ("dreamina-seedance-2-0-260128", False, "480p"): 0.007,
+    ("dreamina-seedance-2-0-260128", True, "480p"): 0.0043,
+    ("dreamina-seedance-2-0-260128", False, "720p"): 0.007,
+    ("dreamina-seedance-2-0-260128", True, "720p"): 0.0043,
+    ("dreamina-seedance-2-0-260128", False, "1080p"): 0.0077,
+    ("dreamina-seedance-2-0-260128", True, "1080p"): 0.0047,
+    ("dreamina-seedance-2-0-260128", False, "4k"): 0.004,
+    ("dreamina-seedance-2-0-260128", True, "4k"): 0.0024,
+    ("dreamina-seedance-2-0-fast-260128", False, "480p"): 0.0056,
+    ("dreamina-seedance-2-0-fast-260128", True, "480p"): 0.0033,
+    ("dreamina-seedance-2-0-fast-260128", False, "720p"): 0.0056,
+    ("dreamina-seedance-2-0-fast-260128", True, "720p"): 0.0033,
+    ("dreamina-seedance-2-0-mini", False, "480p"): 0.0035,
+    ("dreamina-seedance-2-0-mini", True, "480p"): 0.0021,
+    ("dreamina-seedance-2-0-mini", False, "720p"): 0.0035,
+    ("dreamina-seedance-2-0-mini", True, "720p"): 0.0021,
 }
 
 
+def seedance2_price_per_1k_tokens(model_id: str, has_video_input: bool, resolution: str) -> float | None:
+    return SEEDANCE2_PRICE_PER_1K_TOKENS.get((model_id, has_video_input, resolution))
+
+
 RECOMMENDED_PRESETS = [
     ("1024x1024 (1:1)", 1024, 1024),
     ("864x1152 (3:4)", 864, 1152),
@@ -266,6 +282,10 @@ SEEDANCE2_REF_VIDEO_PIXEL_LIMITS = {
         "480p": {"min": 409_600, "max": 927_408},
         "720p": {"min": 409_600, "max": 927_408},
     },
+    "dreamina-seedance-2-0-mini": {
+        "480p": {"min": 409_600, "max": 927_408},
+        "720p": {"min": 409_600, "max": 927_408},
+    },
 }
 
 # The time in this dictionary are given for 10 seconds duration.
@@ -296,3 +316,36 @@ VIDEO_TASKS_EXECUTION_TIME = {
         "1080p": 150,
     },
 }
+
+
+class SeedAudioConfig(BaseModel):
+    format: str = Field(default="mp3")
+    sample_rate: int = Field(default=24000)
+    speech_rate: int = Field(default=0)
+    loudness_rate: int = Field(default=0)
+    pitch_rate: int = Field(default=0)
+
+
+class SeedAudioReference(BaseModel):
+    speaker: str | None = Field(default=None)
+    audio_data: str | None = Field(default=None)
+    audio_url: str | None = Field(default=None)
+    image_data: str | None = Field(default=None)
+    image_url: str | None = Field(default=None)
+
+
+class SeedAudioRequest(BaseModel):
+    model: str = Field(default="seed-audio-1.0")
+    text_prompt: str = Field(...)
+    references: list[SeedAudioReference] | None = Field(default=None)
+    audio_config: SeedAudioConfig = Field(default_factory=SeedAudioConfig)
+    watermark: dict[str, Any] = Field(default_factory=dict)
+
+
+class SeedAudioResponse(BaseModel):
+    audio: str | None = Field(default=None)
+    url: str | None = Field(default=None)
+    duration: float | None = Field(default=None)
+    original_duration: float | None = Field(default=None)
+    code: int | None = Field(default=None)
+    message: str | None = Field(default=None)

comfy_api_nodes/apis/gemini.py

@@ -108,13 +108,20 @@ class GeminiVideoMetadata(BaseModel):
     startOffset: GeminiOffset | None = Field(None)
 
 
+class GeminiThinkingConfig(BaseModel):
+    includeThoughts: bool | None = Field(None)
+    thinkingLevel: str = Field(...)
+
+
 class GeminiGenerationConfig(BaseModel):
-    maxOutputTokens: int | None = Field(None, ge=16, le=8192)
+    maxOutputTokens: int | None = Field(None, ge=16, le=65536)
     seed: int | None = Field(None)
     stopSequences: list[str] | None = Field(None)
     temperature: float | None = Field(None, ge=0.0, le=2.0)
     topK: int | None = Field(None, ge=1)
     topP: float | None = Field(None, ge=0.0, le=1.0)
+    thinkingConfig: GeminiThinkingConfig | None = Field(None)
+    responseModalities: list[str] | None = Field(None)
 
 
 class GeminiImageOutputOptions(BaseModel):
@@ -128,11 +135,6 @@ class GeminiImageConfig(BaseModel):
     imageOutputOptions: GeminiImageOutputOptions = Field(default_factory=GeminiImageOutputOptions)
 
 
-class GeminiThinkingConfig(BaseModel):
-    includeThoughts: bool | None = Field(None)
-    thinkingLevel: str = Field(...)
-
-
 class GeminiImageGenerationConfig(GeminiGenerationConfig):
     responseModalities: list[str] | None = Field(None)
     imageConfig: GeminiImageConfig | None = Field(None)

comfy_api_nodes/apis/ideogram.py

@@ -33,53 +33,6 @@ class IdeogramColorPalette(
     )
 
 
-class ImageRequest(BaseModel):
-    aspect_ratio: Optional[str] = Field(
-        None,
-        description="Optional. The aspect ratio (e.g., 'ASPECT_16_9', 'ASPECT_1_1'). Cannot be used with resolution. Defaults to 'ASPECT_1_1' if unspecified.",
-    )
-    color_palette: Optional[Dict[str, Any]] = Field(
-        None, description='Optional. Color palette object. Only for V_2, V_2_TURBO.'
-    )
-    magic_prompt_option: Optional[str] = Field(
-        None, description="Optional. MagicPrompt usage ('AUTO', 'ON', 'OFF')."
-    )
-    model: str = Field(..., description="The model used (e.g., 'V_2', 'V_2A_TURBO')")
-    negative_prompt: Optional[str] = Field(
-        None,
-        description='Optional. Description of what to exclude. Only for V_1, V_1_TURBO, V_2, V_2_TURBO.',
-    )
-    num_images: Optional[int] = Field(
-        1,
-        description='Optional. Number of images to generate (1-8). Defaults to 1.',
-        ge=1,
-        le=8,
-    )
-    prompt: str = Field(
-        ..., description='Required. The prompt to use to generate the image.'
-    )
-    resolution: Optional[str] = Field(
-        None,
-        description="Optional. Resolution (e.g., 'RESOLUTION_1024_1024'). Only for model V_2. Cannot be used with aspect_ratio.",
-    )
-    seed: Optional[int] = Field(
-        None,
-        description='Optional. A number between 0 and 2147483647.',
-        ge=0,
-        le=2147483647,
-    )
-    style_type: Optional[str] = Field(
-        None,
-        description="Optional. Style type ('AUTO', 'GENERAL', 'REALISTIC', 'DESIGN', 'RENDER_3D', 'ANIME'). Only for models V_2 and above.",
-    )
-
-
-class IdeogramGenerateRequest(BaseModel):
-    image_request: ImageRequest = Field(
-        ..., description='The image generation request parameters.'
-    )
-
-
 class Datum(BaseModel):
     is_image_safe: Optional[bool] = Field(
         None, description='Indicates whether the image is considered safe.'
@@ -113,20 +66,6 @@ class StyleCode(RootModel[str]):
     root: str = Field(..., pattern='^[0-9A-Fa-f]{8}$')
 
 
-class Datum1(BaseModel):
-    is_image_safe: Optional[bool] = None
-    prompt: Optional[str] = None
-    resolution: Optional[str] = None
-    seed: Optional[int] = None
-    style_type: Optional[str] = None
-    url: Optional[str] = None
-
-
-class IdeogramV3IdeogramResponse(BaseModel):
-    created: Optional[datetime] = None
-    data: Optional[List[Datum1]] = None
-
-
 class RenderingSpeed1(str, Enum):
     TURBO = 'TURBO'
     DEFAULT = 'DEFAULT'
@@ -290,3 +229,19 @@ class IdeogramV3Request(BaseModel):
         None,
         description='Optional masks for character reference images. When provided, must match the number of character_reference_images. Each mask should be a grayscale image of the same dimensions as the corresponding character reference image. The images should be in JPEG, PNG or WebP format.'
     )
+
+
+class IdeogramV4Request(BaseModel):
+    text_prompt: str | None = Field(
+        None,
+        description="Natural-language prompt; Magic Prompt is applied automatically. "
+        "Supply exactly one of text_prompt or json_prompt.",
+    )
+    json_prompt: dict[str, Any] | None = Field(
+        None,
+        description="Structured V4 prompt object consumed directly (disables Magic Prompt). "
+        "Supply exactly one of text_prompt or json_prompt.",
+    )
+    resolution: str | None = Field(None, description="Output resolution in WIDTHxHEIGHT (e.g. '2048x2048').")
+    rendering_speed: str | None = Field(None, description="Rendering speed: 'TURBO', 'DEFAULT', or 'QUALITY'.")
+    enable_copyright_detection: bool | None = Field(None, description="Opt into post-generation copyright detection.")

comfy_api_nodes/apis/kling.py

@@ -149,3 +149,59 @@ class MotionControlRequest(BaseModel):
     character_orientation: str = Field(...)
     mode: str = Field(..., description="'pro' or 'std'")
     model_name: str = Field(...)
+
+
+class Kling3TurboSettings(BaseModel):
+    resolution: str = Field("720p", description="'720p' or '1080p'")
+    aspect_ratio: str | None = Field(None, description="'16:9'/'9:16'/'1:1'; text-to-video only")
+    duration: int = Field(5, description="3-15 second")
+
+
+class Kling3TurboText2VideoRequest(BaseModel):
+    prompt: str = Field(..., description="<=3072 chars; may use multi-shot 'shot n, m, words; ...'")
+    settings: Kling3TurboSettings | None = Field(None)
+
+
+class Kling3TurboContent(BaseModel):
+    type: str = Field(..., description="'prompt' or 'first_frame'")
+    text: str | None = Field(None, description="for type=prompt; <=2500 chars")
+    url: str | None = Field(None, description="for type=first_frame")
+
+
+class Kling3TurboImage2VideoRequest(BaseModel):
+    contents: list[Kling3TurboContent] = Field(..., description="prompt + first_frame materials")
+    settings: Kling3TurboSettings | None = Field(None)
+
+
+class Kling3TurboCreateData(BaseModel):
+    id: str | None = Field(None, description="Task ID")
+    status: str | None = Field(None)
+    message: str | None = Field(None)
+
+
+class Kling3TurboCreateResponse(BaseModel):
+    code: int | None = Field(None)
+    message: str | None = Field(None)
+    request_id: str | None = Field(None)
+    data: Kling3TurboCreateData | None = Field(None)
+
+
+class Kling3TurboOutput(BaseModel):
+    type: str | None = Field(None, description="'video', 'image', 'audio', ...")
+    id: str | None = Field(None)
+    url: str | None = Field(None)
+    duration: str | None = Field(None)
+
+
+class Kling3TurboTaskData(BaseModel):
+    id: str | None = Field(None)
+    status: str | None = Field(None, description="submitted | processing | succeeded | failed")
+    message: str | None = Field(None)
+    outputs: list[Kling3TurboOutput] | None = Field(None)
+
+
+class Kling3TurboQueryResponse(BaseModel):
+    code: int | None = Field(None)
+    message: str | None = Field(None)
+    request_id: str | None = Field(None)
+    data: list[Kling3TurboTaskData] | None = Field(None)

comfy_api_nodes/apis/luma.py

@@ -10,6 +10,7 @@ from pydantic import BaseModel, Field, confloat
 class LumaIO:
     LUMA_REF = "LUMA_REF"
     LUMA_CONCEPTS = "LUMA_CONCEPTS"
+    LUMA_RAY32_KEYFRAME = "LUMA_RAY32_KEYFRAME"
 
 
 class LumaReference:
@@ -20,13 +21,14 @@ class LumaReference:
     def create_api_model(self, download_url: str):
         return LumaImageRef(url=download_url, weight=self.weight)
 
+
 class LumaReferenceChain:
-    def __init__(self, first_ref: LumaReference=None):
+    def __init__(self, first_ref: LumaReference = None):
         self.refs: list[LumaReference] = []
         if first_ref:
             self.refs.append(first_ref)
 
-    def add(self, luma_ref: LumaReference=None):
+    def add(self, luma_ref: LumaReference = None):
         self.refs.append(luma_ref)
 
     def create_api_model(self, download_urls: list[str], max_refs=4):
@@ -124,7 +126,7 @@ def get_luma_concepts(include_none=False):
         "pull_out",
         "aerial",
         "crane_up",
-        "eye_level"
+        "eye_level",
     ]
 
 
@@ -162,8 +164,8 @@ class LumaVideoModelOutputDuration(str, Enum):
 
 
 class LumaGenerationType(str, Enum):
-    video = 'video'
-    image = 'image'
+    video = "video"
+    image = "image"
 
 
 class LumaState(str, Enum):
@@ -174,86 +176,109 @@ class LumaState(str, Enum):
 
 
 class LumaAssets(BaseModel):
-    video: Optional[str] = Field(None, description='The URL of the video')
-    image: Optional[str] = Field(None, description='The URL of the image')
-    progress_video: Optional[str] = Field(None, description='The URL of the progress video')
+    video: Optional[str] = Field(None, description="The URL of the video")
+    image: Optional[str] = Field(None, description="The URL of the image")
+    progress_video: Optional[str] = Field(None, description="The URL of the progress video")
 
 
 class LumaImageRef(BaseModel):
     """Used for image gen"""
-    url: str = Field(..., description='The URL of the image reference')
-    weight: confloat(ge=0.0, le=1.0) = Field(..., description='The weight of the image reference')
+
+    url: str = Field(..., description="The URL of the image reference")
+    weight: confloat(ge=0.0, le=1.0) = Field(..., description="The weight of the image reference")
 
 
 class LumaImageReference(BaseModel):
     """Used for video gen"""
-    type: Optional[str] = Field('image', description='Input type, defaults to image')
-    url: str = Field(..., description='The URL of the image')
+
+    type: Optional[str] = Field("image", description="Input type, defaults to image")
+    url: str = Field(..., description="The URL of the image")
 
 
 class LumaModifyImageRef(BaseModel):
-    url: str = Field(..., description='The URL of the image reference')
-    weight: confloat(ge=0.0, le=1.0) = Field(..., description='The weight of the image reference')
+    url: str = Field(..., description="The URL of the image reference")
+    weight: confloat(ge=0.0, le=1.0) = Field(..., description="The weight of the image reference")
 
 
 class LumaCharacterRef(BaseModel):
-    identity0: LumaImageIdentity = Field(..., description='The image identity object')
+    identity0: LumaImageIdentity = Field(..., description="The image identity object")
 
 
 class LumaImageIdentity(BaseModel):
-    images: list[str] = Field(..., description='The URLs of the image identity')
+    images: list[str] = Field(..., description="The URLs of the image identity")
 
 
 class LumaGenerationReference(BaseModel):
-    type: str = Field('generation', description='Input type, defaults to generation')
-    id: str = Field(..., description='The ID of the generation')
+    type: str = Field("generation", description="Input type, defaults to generation")
+    id: str = Field(..., description="The ID of the generation")
 
 
 class LumaKeyframes(BaseModel):
-    frame0: Optional[Union[LumaImageReference, LumaGenerationReference]] = Field(None, description='')
-    frame1: Optional[Union[LumaImageReference, LumaGenerationReference]] = Field(None, description='')
+    frame0: Optional[Union[LumaImageReference, LumaGenerationReference]] = Field(None, description="")
+    frame1: Optional[Union[LumaImageReference, LumaGenerationReference]] = Field(None, description="")
 
 
 class LumaConceptObject(BaseModel):
-    key: str = Field(..., description='Camera Concept name')
+    key: str = Field(..., description="Camera Concept name")
 
 
 class LumaImageGenerationRequest(BaseModel):
-    prompt: str = Field(..., description='The prompt of the generation')
-    model: LumaImageModel = Field(LumaImageModel.photon_1, description='The image model used for the generation')
-    aspect_ratio: Optional[LumaAspectRatio] = Field(LumaAspectRatio.ratio_16_9, description='The aspect ratio of the generation')
-    image_ref: Optional[list[LumaImageRef]] = Field(None, description='List of image reference objects')
-    style_ref: Optional[list[LumaImageRef]] = Field(None, description='List of style reference objects')
-    character_ref: Optional[LumaCharacterRef] = Field(None, description='The image identity object')
-    modify_image_ref: Optional[LumaModifyImageRef] = Field(None, description='The modify image reference object')
+    prompt: str = Field(..., description="The prompt of the generation")
+    model: LumaImageModel = Field(LumaImageModel.photon_1, description="The image model used for the generation")
+    aspect_ratio: Optional[LumaAspectRatio] = Field(LumaAspectRatio.ratio_16_9)
+    image_ref: Optional[list[LumaImageRef]] = Field(None, description="List of image reference objects")
+    style_ref: Optional[list[LumaImageRef]] = Field(None, description="List of style reference objects")
+    character_ref: Optional[LumaCharacterRef] = Field(None, description="The image identity object")
+    modify_image_ref: Optional[LumaModifyImageRef] = Field(None, description="The modify image reference object")
 
 
 class LumaGenerationRequest(BaseModel):
-    prompt: str = Field(..., description='The prompt of the generation')
-    model: LumaVideoModel = Field(LumaVideoModel.ray_2, description='The video model used for the generation')
-    duration: Optional[LumaVideoModelOutputDuration] = Field(None, description='The duration of the generation')
-    aspect_ratio: Optional[LumaAspectRatio] = Field(None, description='The aspect ratio of the generation')
-    resolution: Optional[LumaVideoOutputResolution] = Field(None, description='The resolution of the generation')
-    loop: Optional[bool] = Field(None, description='Whether to loop the video')
-    keyframes: Optional[LumaKeyframes] = Field(None, description='The keyframes of the generation')
-    concepts: Optional[list[LumaConceptObject]] = Field(None, description='Camera Concepts to apply to generation')
+    prompt: str = Field(..., description="The prompt of the generation")
+    model: LumaVideoModel = Field(LumaVideoModel.ray_2, description="The video model used for the generation")
+    duration: Optional[LumaVideoModelOutputDuration] = Field(None, description="The duration of the generation")
+    aspect_ratio: Optional[LumaAspectRatio] = Field(None, description="The aspect ratio of the generation")
+    resolution: Optional[LumaVideoOutputResolution] = Field(None, description="The resolution of the generation")
+    loop: Optional[bool] = Field(None, description="Whether to loop the video")
+    keyframes: Optional[LumaKeyframes] = Field(None, description="The keyframes of the generation")
+    concepts: Optional[list[LumaConceptObject]] = Field(None, description="Camera Concepts to apply to generation")
 
 
 class LumaGeneration(BaseModel):
-    id: str = Field(..., description='The ID of the generation')
-    generation_type: LumaGenerationType = Field(..., description='Generation type, image or video')
-    state: LumaState = Field(..., description='The state of the generation')
-    failure_reason: Optional[str] = Field(None, description='The reason for the state of the generation')
-    created_at: str = Field(..., description='The date and time when the generation was created')
-    assets: Optional[LumaAssets] = Field(None, description='The assets of the generation')
-    model: str = Field(..., description='The model used for the generation')
-    request: Union[LumaGenerationRequest, LumaImageGenerationRequest] = Field(..., description="The request used for the generation")
+    id: str = Field(..., description="The ID of the generation")
+    generation_type: LumaGenerationType = Field(..., description="Generation type, image or video")
+    state: LumaState = Field(..., description="The state of the generation")
+    failure_reason: Optional[str] = Field(None, description="The reason for the state of the generation")
+    created_at: str = Field(..., description="The date and time when the generation was created")
+    assets: Optional[LumaAssets] = Field(None, description="The assets of the generation")
+    model: str = Field(..., description="The model used for the generation")
+    request: Union[LumaGenerationRequest, LumaImageGenerationRequest] = Field(...)
 
 
 class Luma2ImageRef(BaseModel):
     url: str | None = None
     data: str | None = None
     media_type: str | None = None
+    generation_id: str | None = Field(None, description="reference a prior generation (extend / source reuse)")
+
+
+class Luma2VideoEdit(BaseModel):
+    """Edit controls for Ray 3.2 ``video_edit`` generations."""
+
+    auto_controls: bool | None = Field(None, description="derive a conditioning schedule from the source (recommended)")
+    strength: str | None = Field(None, description="'adhere_1' .. 'reimagine_3'; constrained by IO.Combo")
+
+
+class Luma2VideoOptions(BaseModel):
+    """Ray 3.2 ``video`` output settings (text / image / keyframe / edit / extend)."""
+
+    resolution: str | None = Field(None, description="360p | 540p | 720p | 1080p")
+    duration: str | None = Field(None, description="5s | 10s")
+    loop: bool | None = Field(None)
+    start_frame: Luma2ImageRef | None = Field(None)
+    end_frame: Luma2ImageRef | None = Field(None)
+    keyframes: list[Luma2ImageRef] | None = Field(None)
+    keyframe_indexes: list[int] | None = Field(None)
+    edit: Luma2VideoEdit | None = Field(None)
 
 
 class Luma2GenerationRequest(BaseModel):
@@ -266,6 +291,7 @@ class Luma2GenerationRequest(BaseModel):
     web_search: bool | None = None
     image_ref: list[Luma2ImageRef] | None = None
     source: Luma2ImageRef | None = None
+    video: Luma2VideoOptions | None = Field(None)
 
 
 class Luma2Generation(BaseModel):
@@ -277,3 +303,31 @@ class Luma2Generation(BaseModel):
     output: list[LumaImageReference] | None = None
     failure_reason: str | None = None
     failure_code: str | None = None
+
+
+# --- Ray 3.2 multi-keyframe chain ---
+
+LUMA_KEYFRAME_MODE_FRACTION = "fraction"  # value in [0.0, 1.0] of the output video duration
+LUMA_KEYFRAME_MODE_SECONDS = "seconds"  # absolute time, in seconds, from the start of the output
+
+
+class LumaRay32KeyframeItem:
+    """One guide image anchored at a position on the Ray 3.2 output timeline."""
+
+    def __init__(self, image: torch.Tensor, mode: str, value: float):
+        self.image = image
+        self.mode = mode  # LUMA_KEYFRAME_MODE_FRACTION | LUMA_KEYFRAME_MODE_SECONDS
+        self.value = value
+
+
+class LumaRay32KeyframeChain:
+    def __init__(self):
+        self.items: list[LumaRay32KeyframeItem] = []
+
+    def add(self, item: LumaRay32KeyframeItem) -> None:
+        self.items.append(item)
+
+    def clone(self) -> "LumaRay32KeyframeChain":
+        c = LumaRay32KeyframeChain()
+        c.items = list(self.items)
+        return c

comfy_api_nodes/apis/runway.py

@@ -67,15 +67,6 @@ class RunwayImageToVideoResponse(BaseModel):
     id: Optional[str] = Field(None, description='Task ID')
 
 
-class RunwayTaskStatusEnum(str, Enum):
-    SUCCEEDED = 'SUCCEEDED'
-    RUNNING = 'RUNNING'
-    FAILED = 'FAILED'
-    PENDING = 'PENDING'
-    CANCELLED = 'CANCELLED'
-    THROTTLED = 'THROTTLED'
-
-
 class RunwayTaskStatusResponse(BaseModel):
     createdAt: datetime = Field(..., description='Task creation timestamp')
     id: str = Field(..., description='Task ID')
@@ -86,7 +77,7 @@ class RunwayTaskStatusResponse(BaseModel):
         ge=0.0,
         le=1.0,
     )
-    status: RunwayTaskStatusEnum
+    status: str = Field(..., description="SUCCEEDED, RUNNING, FAILED, PENDING, CANCELLED or THROTTLED")
 
 
 class Model4(str, Enum):
@@ -125,3 +116,144 @@ class RunwayTextToImageRequest(BaseModel):
 
 class RunwayTextToImageResponse(BaseModel):
     id: Optional[str] = Field(None, description='Task ID')
+
+
+class RunwayAleph2IO:
+    """Custom socket types for chaining Aleph2 guidance images."""
+
+    KEYFRAME = "RUNWAY_ALEPH2_KEYFRAME"
+    PROMPT_IMAGE = "RUNWAY_ALEPH2_PROMPT_IMAGE"
+
+
+# Keyframe timing modes (anchored to the INPUT video). Stored on the chain item and used to
+# choose the request model below. The values match the Aleph2 keyframe union field names.
+KEYFRAME_MODE_SECONDS = "seconds"  # absolute time, in seconds, from the start of the input video
+KEYFRAME_MODE_AT = "at"  # fraction [0.0, 1.0] of the input video duration
+
+# Prompt-image position modes (anchored to the OUTPUT video). Values match the Aleph2 position `type`.
+PROMPT_IMAGE_MODE_TIMESTAMP = "timestamp"  # absolute time, in seconds, from the start of the output video
+PROMPT_IMAGE_MODE_POSITION = "position"  # fraction [0.0, 1.0] of the output video duration
+
+
+class RunwayAleph2KeyframeItem:
+    """A guidance image anchored to a point of the INPUT video (one Aleph2 ``keyframe``)."""
+
+    def __init__(self, image, mode: str, value: float):
+        self.image = image
+        self.mode = mode  # KEYFRAME_MODE_SECONDS | KEYFRAME_MODE_AT
+        self.value = value
+
+
+class RunwayAleph2KeyframeChain:
+    """An ordered collection of keyframes, built by chaining Runway Aleph2 Keyframe nodes."""
+
+    def __init__(self):
+        self.items: list[RunwayAleph2KeyframeItem] = []
+
+    def add(self, item: RunwayAleph2KeyframeItem) -> None:
+        self.items.append(item)
+
+    def clone(self) -> "RunwayAleph2KeyframeChain":
+        c = RunwayAleph2KeyframeChain()
+        c.items = list(self.items)
+        return c
+
+
+class RunwayAleph2PromptImageItem:
+    """A guidance image anchored to a point of the OUTPUT video (one Aleph2 ``promptImage``)."""
+
+    def __init__(self, image, mode: str, value: float):
+        self.image = image
+        self.mode = mode  # PROMPT_IMAGE_MODE_TIMESTAMP | PROMPT_IMAGE_MODE_POSITION
+        self.value = value
+
+
+class RunwayAleph2PromptImageChain:
+    """An ordered collection of prompt images, built by chaining Runway Aleph2 Prompt Image nodes."""
+
+    def __init__(self):
+        self.items: list[RunwayAleph2PromptImageItem] = []
+
+    def add(self, item: RunwayAleph2PromptImageItem) -> None:
+        self.items.append(item)
+
+    def clone(self) -> "RunwayAleph2PromptImageChain":
+        c = RunwayAleph2PromptImageChain()
+        c.items = list(self.items)
+        return c
+
+
+class RunwayAleph2KeyframeSeconds(BaseModel):
+    seconds: float = Field(
+        ...,
+        description="Absolute timestamp in seconds from the start of the input video when this guidance image should apply.",
+        ge=0.0,
+    )
+    uri: str = Field(...)
+
+
+class RunwayAleph2KeyframeAt(BaseModel):
+    at: float = Field(
+        ...,
+        description="Position as a fraction [0.0, 1.0] of the input video duration.",
+        ge=0.0,
+        le=1.0,
+    )
+    uri: str = Field(...)
+
+
+class RunwayAleph2TimestampPosition(BaseModel):
+    type: str = Field(default="timestamp")
+    timestampSeconds: float = Field(
+        ...,
+        description="Absolute timestamp in seconds from the start of the output video.",
+        ge=0.0,
+    )
+
+
+class RunwayAleph2RelativePosition(BaseModel):
+    type: str = Field(default="position")
+    positionPercentage: float = Field(
+        ...,
+        description="Position as a fraction [0.0, 1.0] of the total output video duration.",
+        ge=0.0,
+        le=1.0,
+    )
+
+
+class RunwayAleph2PromptImage(BaseModel):
+    position: RunwayAleph2TimestampPosition | RunwayAleph2RelativePosition
+    uri: str = Field(...)
+
+
+class RunwayAleph2ContentModeration(BaseModel):
+    publicFigureThreshold: str = Field(
+        ...,
+        description='When set to "low", the content moderation system is less strict about '
+        'recognizable public figures. One of "auto" or "low".',
+    )
+
+
+class RunwayAleph2Request(BaseModel):
+    model: str = Field(default="aleph2")
+    promptText: str = Field(
+        ...,
+        description="A non-empty string describing what should appear in the output.",
+        min_length=1,
+        max_length=1000,
+    )
+    videoUri: str = Field(...)
+    seed: int = Field(..., description="Random seed for generation", ge=0, le=4294967295)
+    contentModeration: RunwayAleph2ContentModeration = Field(...)
+    keyframes: list[RunwayAleph2KeyframeSeconds | RunwayAleph2KeyframeAt] | None = Field(
+        None,
+        description="Timed guidance images placed at specific points in the input video. Up to 5.",
+    )
+    promptImage: list[RunwayAleph2PromptImage] | None = Field(
+        None,
+        description="Up to 5 image keyframes for guiding the edit at specific points in the output video.",
+    )
+
+
+class RunwayAleph2Response(BaseModel):
+    id: str | None = Field(None, description="Task ID")

comfy_api_nodes/apis/stability.py

@@ -1,147 +0,0 @@
-from enum import Enum
-from typing import Optional
-
-from pydantic import BaseModel, Field, confloat
-
-
-class StabilityFormat(str, Enum):
-    png = 'png'
-    jpeg = 'jpeg'
-    webp = 'webp'
-
-
-class StabilityAspectRatio(str, Enum):
-    ratio_1_1 = "1:1"
-    ratio_16_9 = "16:9"
-    ratio_9_16 = "9:16"
-    ratio_3_2 = "3:2"
-    ratio_2_3 = "2:3"
-    ratio_5_4 = "5:4"
-    ratio_4_5 = "4:5"
-    ratio_21_9 = "21:9"
-    ratio_9_21 = "9:21"
-
-
-def get_stability_style_presets(include_none=True):
-    presets = []
-    if include_none:
-        presets.append("None")
-    return presets + [x.value for x in StabilityStylePreset]
-
-
-class StabilityStylePreset(str, Enum):
-    _3d_model = "3d-model"
-    analog_film = "analog-film"
-    anime = "anime"
-    cinematic = "cinematic"
-    comic_book = "comic-book"
-    digital_art = "digital-art"
-    enhance = "enhance"
-    fantasy_art = "fantasy-art"
-    isometric = "isometric"
-    line_art = "line-art"
-    low_poly = "low-poly"
-    modeling_compound = "modeling-compound"
-    neon_punk = "neon-punk"
-    origami = "origami"
-    photographic = "photographic"
-    pixel_art = "pixel-art"
-    tile_texture = "tile-texture"
-
-
-class Stability_SD3_5_Model(str, Enum):
-    sd3_5_large = "sd3.5-large"
-    # sd3_5_large_turbo = "sd3.5-large-turbo"
-    sd3_5_medium = "sd3.5-medium"
-
-
-class Stability_SD3_5_GenerationMode(str, Enum):
-    text_to_image = "text-to-image"
-    image_to_image = "image-to-image"
-
-
-class StabilityStable3_5Request(BaseModel):
-    model: str = Field(...)
-    mode: str = Field(...)
-    prompt: str = Field(...)
-    negative_prompt: Optional[str] = Field(None)
-    aspect_ratio: Optional[str] = Field(None)
-    seed: Optional[int] = Field(None)
-    output_format: Optional[str] = Field(StabilityFormat.png.value)
-    image: Optional[str] = Field(None)
-    style_preset: Optional[str] = Field(None)
-    cfg_scale: float = Field(...)
-    strength: Optional[confloat(ge=0.0, le=1.0)] = Field(None)
-
-
-class StabilityUpscaleConservativeRequest(BaseModel):
-    prompt: str = Field(...)
-    negative_prompt: Optional[str] = Field(None)
-    seed: Optional[int] = Field(None)
-    output_format: Optional[str] = Field(StabilityFormat.png.value)
-    image: Optional[str] = Field(None)
-    creativity: Optional[confloat(ge=0.2, le=0.5)] = Field(None)
-
-
-class StabilityUpscaleCreativeRequest(BaseModel):
-    prompt: str = Field(...)
-    negative_prompt: Optional[str] = Field(None)
-    seed: Optional[int] = Field(None)
-    output_format: Optional[str] = Field(StabilityFormat.png.value)
-    image: Optional[str] = Field(None)
-    creativity: Optional[confloat(ge=0.1, le=0.5)] = Field(None)
-    style_preset: Optional[str] = Field(None)
-
-
-class StabilityStableUltraRequest(BaseModel):
-    prompt: str = Field(...)
-    negative_prompt: Optional[str] = Field(None)
-    aspect_ratio: Optional[str] = Field(None)
-    seed: Optional[int] = Field(None)
-    output_format: Optional[str] = Field(StabilityFormat.png.value)
-    image: Optional[str] = Field(None)
-    style_preset: Optional[str] = Field(None)
-    strength: Optional[confloat(ge=0.0, le=1.0)] = Field(None)
-
-
-class StabilityStableUltraResponse(BaseModel):
-    image: Optional[str] = Field(None)
-    finish_reason: Optional[str] = Field(None)
-    seed: Optional[int] = Field(None)
-
-
-class StabilityResultsGetResponse(BaseModel):
-    image: Optional[str] = Field(None)
-    finish_reason: Optional[str] = Field(None)
-    seed: Optional[int] = Field(None)
-    id: Optional[str] = Field(None)
-    name: Optional[str] = Field(None)
-    errors: Optional[list[str]] = Field(None)
-    status: Optional[str] = Field(None)
-    result: Optional[str] = Field(None)
-
-
-class StabilityAsyncResponse(BaseModel):
-    id: Optional[str] = Field(None)
-
-
-class StabilityTextToAudioRequest(BaseModel):
-    model: str = Field(...)
-    prompt: str = Field(...)
-    duration: int = Field(190, ge=1, le=190)
-    seed: int = Field(0, ge=0, le=4294967294)
-    steps: int = Field(8, ge=4, le=8)
-    output_format: str = Field("wav")
-
-
-class StabilityAudioToAudioRequest(StabilityTextToAudioRequest):
-    strength: float = Field(0.01, ge=0.01, le=1.0)
-
-
-class StabilityAudioInpaintRequest(StabilityTextToAudioRequest):
-    mask_start: int = Field(30, ge=0, le=190)
-    mask_end: int = Field(190, ge=0, le=190)
-
-
-class StabilityAudioResponse(BaseModel):
-    audio: Optional[str] = Field(None)

comfy_api_nodes/apis/tripo.py

@@ -208,6 +208,10 @@ class TripoMultiviewToModelRequest(BaseModel):
     quad: bool | None = Field(False, description="Whether to apply quad to the generated model")
 
 
+class TripoTexturePrompt(BaseModel):
+    text: str | None = Field(None, description="Text guidance for texture generation")
+
+
 class TripoTextureModelRequest(BaseModel):
     type: TripoTaskType = Field(TripoTaskType.TEXTURE_MODEL, description="Type of task")
     original_model_task_id: str = Field(..., description="The task ID of the original model")
@@ -219,6 +223,11 @@ class TripoTextureModelRequest(BaseModel):
     texture_alignment: TripoTextureAlignment | None = Field(
         TripoTextureAlignment.ORIGINAL_IMAGE, description="The texture alignment method"
     )
+    texture_prompt: TripoTexturePrompt | None = Field(
+        None,
+        description="Optional guidance for texturing. Required in practice for imported models, "
+        "which carry no source image to infer texture from.",
+    )
 
 
 class TripoRefineModelRequest(BaseModel):
@@ -307,6 +316,17 @@ class TripoP1MultiviewToModelRequest(TripoP1CommonRequest):
     orientation: str | None = None
 
 
+class TripoImportModelRequest(BaseModel):
+    """Request for the comfy-api composite import endpoint (/proxy/tripo/v2/openapi/import).
+
+    The model file is uploaded to ComfyUI API storage first; the backend downloads it from
+    `url`, re-uploads it to Tripo's storage and creates the import_model task server-side.
+    """
+
+    url: str = Field(..., description="ComfyUI API storage download URL of the model file")
+    format: str = Field(..., description='File format: "glb", "fbx", "obj" or "stl"')
+
+
 class TripoTaskOutput(BaseModel):
     model: str | None = Field(None, description="URL to the model")
     base_model: str | None = Field(None, description="URL to the base model")

comfy_api_nodes/nodes_anthropic.py

@@ -155,7 +155,7 @@ class ClaudeNode(IO.ComfyNode):
         return IO.Schema(
             node_id="ClaudeNode",
             display_name="Anthropic Claude",
-            category="text/partner/Anthropic",
+            category="partner/text/Anthropic",
             essentials_category="Text Generation",
             description="Generate text responses with Anthropic's Claude models. "
             "Provide a text prompt and optionally one or more images for multimodal context.",

comfy_api_nodes/nodes_beeble.py

@@ -206,7 +206,7 @@ class BeebleSwitchXVideoEdit(IO.ComfyNode):
         return IO.Schema(
             node_id="BeebleSwitchXVideoEdit",
             display_name="Beeble SwitchX Video Edit",
-            category="video/partner/Beeble",
+            category="partner/video/Beeble",
             description=(
                 "Edit a video with Beeble SwitchX. Switches anything in the scene (background, "
                 "lighting, costume) while preserving the original subject's pixels and motion. "
@@ -302,7 +302,7 @@ class BeebleSwitchXImageEdit(IO.ComfyNode):
         return IO.Schema(
             node_id="BeebleSwitchXImageEdit",
             display_name="Beeble SwitchX Image Edit",
-            category="image/partner/Beeble",
+            category="partner/image/Beeble",
             description=(
                 "Edit a single image with Beeble SwitchX. Switches anything in the scene "
                 "(background, lighting, costume) while preserving the original subject's pixels. "

comfy_api_nodes/nodes_bfl.py

@@ -37,7 +37,7 @@ class FluxProUltraImageNode(IO.ComfyNode):
         return IO.Schema(
             node_id="FluxProUltraImageNode",
             display_name="Flux 1.1 [pro] Ultra Image",
-            category="image/partner/BFL",
+            category="partner/image/BFL",
             description="Generates images using Flux Pro 1.1 Ultra via api based on prompt and resolution.",
             inputs=[
                 IO.String.Input(
@@ -155,7 +155,7 @@ class FluxKontextProImageNode(IO.ComfyNode):
         return IO.Schema(
             node_id=cls.NODE_ID,
             display_name=cls.DISPLAY_NAME,
-            category="image/partner/BFL",
+            category="partner/image/BFL",
             description="Edits images using Flux.1 Kontext [pro] via api based on prompt and aspect ratio.",
             inputs=[
                 IO.String.Input(
@@ -277,7 +277,7 @@ class FluxProExpandNode(IO.ComfyNode):
         return IO.Schema(
             node_id="FluxProExpandNode",
             display_name="Flux.1 Expand Image",
-            category="image/partner/BFL",
+            category="partner/image/BFL",
             description="Outpaints image based on prompt.",
             inputs=[
                 IO.Image.Input("image"),
@@ -414,7 +414,7 @@ class FluxProFillNode(IO.ComfyNode):
         return IO.Schema(
             node_id="FluxProFillNode",
             display_name="Flux.1 Fill Image",
-            category="image/partner/BFL",
+            category="partner/image/BFL",
             description="Inpaints image based on mask and prompt.",
             inputs=[
                 IO.Image.Input("image"),
@@ -521,7 +521,7 @@ class FluxEraseNode(IO.ComfyNode):
         return IO.Schema(
             node_id="FluxEraseNode",
             display_name="Flux Erase Image",
-            category="image/partner/BFL",
+            category="partner/image/BFL",
             description="Removes the masked object from an image and reconstructs the background. "
             "Paint the mask over what you want to erase.",
             inputs=[
@@ -534,6 +534,15 @@ class FluxEraseNode(IO.ComfyNode):
                     max=25,
                     tooltip="Expands the mask boundaries to ensure clean coverage of the object's edges.",
                 ),
+                IO.Int.Input(
+                    "seed",
+                    default=0,
+                    min=0,
+                    max=2147483647,
+                    control_after_generate=True,
+                    tooltip="The random seed used for creating the noise.",
+                    optional=True,
+                ),
             ],
             outputs=[IO.Image.Output()],
             hidden=[
@@ -553,6 +562,7 @@ class FluxEraseNode(IO.ComfyNode):
         image: Input.Image,
         mask: Input.Image,
         dilate_pixels: int = 10,
+        seed: int = 0,
     ) -> IO.NodeOutput:
         validate_image_dimensions(image, min_width=256, min_height=256)
         mask = resize_mask_to_image(mask, image)
@@ -565,6 +575,7 @@ class FluxEraseNode(IO.ComfyNode):
                 image=tensor_to_base64_string(image[:, :, :, :3]),  # make sure image will have alpha channel removed
                 mask=mask,
                 dilate_pixels=dilate_pixels,
+                seed=seed,
             ),
         )
 
@@ -597,7 +608,7 @@ class FluxVTONode(IO.ComfyNode):
         return IO.Schema(
             node_id="FluxVTONode",
             display_name="Flux Virtual Try-On",
-            category="image/partner/BFL",
+            category="partner/image/BFL",
             description="Virtual try-on: dresses the person in the provided garment.",
             inputs=[
                 IO.Image.Input("person", tooltip="Image of the person to dress."),
@@ -697,7 +708,7 @@ class Flux2ProImageNode(IO.ComfyNode):
         return IO.Schema(
             node_id=cls.NODE_ID,
             display_name=cls.DISPLAY_NAME,
-            category="image/partner/BFL",
+            category="partner/image/BFL",
             description="Generates images synchronously based on prompt and resolution.",
             inputs=[
                 IO.String.Input(
@@ -868,7 +879,7 @@ class Flux2ImageNode(IO.ComfyNode):
         return IO.Schema(
             node_id="Flux2ImageNode",
             display_name="Flux.2 Image",
-            category="image/partner/BFL",
+            category="partner/image/BFL",
             description="Generate images via Flux.2 [pro] or Flux.2 [max] from a prompt and optional reference images.",
             inputs=[
                 IO.String.Input(

comfy_api_nodes/nodes_bria.py

@@ -1,14 +1,19 @@
+import av
+import torch
+from av.codec import CodecContext
 from typing_extensions import override
 
 from comfy_api.latest import IO, ComfyExtension, Input
 from comfy_api_nodes.apis.bria import (
     BriaEditImageRequest,
+    BriaImageEditResponse,
     BriaRemoveBackgroundRequest,
     BriaRemoveBackgroundResponse,
     BriaRemoveVideoBackgroundRequest,
     BriaRemoveVideoBackgroundResponse,
-    BriaImageEditResponse,
     BriaStatusResponse,
+    BriaVideoGreenScreenRequest,
+    BriaVideoReplaceBackgroundRequest,
     InputModerationSettings,
 )
 from comfy_api_nodes.util import (
@@ -31,7 +36,7 @@ class BriaImageEditNode(IO.ComfyNode):
         return IO.Schema(
             node_id="BriaImageEditNode",
             display_name="Bria FIBO Image Edit",
-            category="image/partner/Bria",
+            category="partner/image/Bria",
             description="Edit images using Bria latest model",
             inputs=[
                 IO.Combo.Input("model", options=["FIBO"]),
@@ -169,7 +174,7 @@ class BriaRemoveImageBackground(IO.ComfyNode):
         return IO.Schema(
             node_id="BriaRemoveImageBackground",
             display_name="Bria Remove Image Background",
-            category="image/partner/Bria",
+            category="partner/image/Bria",
             description="Remove the background from an image using Bria RMBG 2.0.",
             inputs=[
                 IO.Image.Input("image"),
@@ -245,7 +250,7 @@ class BriaRemoveVideoBackground(IO.ComfyNode):
         return IO.Schema(
             node_id="BriaRemoveVideoBackground",
             display_name="Bria Remove Video Background",
-            category="video/partner/Bria",
+            category="partner/video/Bria",
             description="Remove the background from a video using Bria. ",
             inputs=[
                 IO.Video.Input("video"),
@@ -284,7 +289,7 @@ class BriaRemoveVideoBackground(IO.ComfyNode):
             ],
             is_api_node=True,
             price_badge=IO.PriceBadge(
-                expr="""{"type":"usd","usd":0.14,"format":{"suffix":"/second"}}""",
+                expr="""{"type":"usd","usd":0.0042,"format":{"suffix":"/second"}}""",
             ),
         )
 
@@ -316,6 +321,251 @@ class BriaRemoveVideoBackground(IO.ComfyNode):
         return IO.NodeOutput(await download_url_to_video_output(response.result.video_url))
 
 
+class BriaVideoGreenScreen(IO.ComfyNode):
+
+    @classmethod
+    def define_schema(cls):
+        return IO.Schema(
+            node_id="BriaVideoGreenScreen",
+            display_name="Bria Video Green Screen",
+            category="partner/video/Bria",
+            description="Replace a video's background with a solid chroma-key screen using Bria.",
+            inputs=[
+                IO.Video.Input("video"),
+                IO.Combo.Input(
+                    "green_shade",
+                    options=["broadcast_green", "chroma_green", "blue_screen"],
+                    tooltip="Solid chroma-key shade applied behind the foreground: "
+                    "broadcast_green (#00B140), chroma_green (#00FF00), or blue_screen (#0000FF).",
+                ),
+                IO.Int.Input(
+                    "seed",
+                    default=0,
+                    min=0,
+                    max=2147483647,
+                    display_mode=IO.NumberDisplay.number,
+                    control_after_generate=True,
+                    tooltip="Seed controls whether the node should re-run; "
+                    "results are non-deterministic regardless of seed.",
+                ),
+            ],
+            outputs=[IO.Video.Output()],
+            hidden=[
+                IO.Hidden.auth_token_comfy_org,
+                IO.Hidden.api_key_comfy_org,
+                IO.Hidden.unique_id,
+            ],
+            is_api_node=True,
+            price_badge=IO.PriceBadge(
+                expr="""{"type":"usd","usd":0.0042,"format":{"suffix":"/second"}}""",
+            ),
+        )
+
+    @classmethod
+    async def execute(
+        cls,
+        video: Input.Video,
+        green_shade: str,
+        seed: int,
+    ) -> IO.NodeOutput:
+        validate_video_duration(video, max_duration=60.0)
+        response = await sync_op(
+            cls,
+            ApiEndpoint(path="/proxy/bria/v2/video/edit/green_screen", method="POST"),
+            data=BriaVideoGreenScreenRequest(
+                video=await upload_video_to_comfyapi(cls, video),
+                green_shade=green_shade,
+                output_container_and_codec="mp4_h264",
+                seed=seed,
+            ),
+            response_model=BriaStatusResponse,
+        )
+        response = await poll_op(
+            cls,
+            ApiEndpoint(path=f"/proxy/bria/v2/status/{response.request_id}"),
+            status_extractor=lambda r: r.status,
+            response_model=BriaRemoveVideoBackgroundResponse,
+        )
+        return IO.NodeOutput(await download_url_to_video_output(response.result.video_url))
+
+
+class BriaVideoReplaceBackground(IO.ComfyNode):
+
+    @classmethod
+    def define_schema(cls):
+        return IO.Schema(
+            node_id="BriaVideoReplaceBackground",
+            display_name="Bria Video Replace Background",
+            category="partner/video/Bria",
+            description="Replace a video's background with a supplied image or video using Bria. "
+            "The output keeps the foreground's resolution and frame rate; a background with a "
+            "different aspect ratio is stretched to fit, so match it for undistorted results.",
+            inputs=[
+                IO.Video.Input("video", tooltip="Foreground video whose background is replaced."),
+                IO.Image.Input(
+                    "background_image",
+                    optional=True,
+                    tooltip="Background image to composite behind the foreground. "
+                    "Provide either a background image or a background video, not both.",
+                ),
+                IO.Video.Input(
+                    "background_video",
+                    optional=True,
+                    tooltip="Background video to composite behind the foreground. "
+                    "Provide either a background image or a background video, not both.",
+                ),
+                IO.Int.Input(
+                    "seed",
+                    default=0,
+                    min=0,
+                    max=2147483647,
+                    display_mode=IO.NumberDisplay.number,
+                    control_after_generate=True,
+                    tooltip="Seed controls whether the node should re-run; "
+                    "results are non-deterministic regardless of seed.",
+                ),
+            ],
+            outputs=[IO.Video.Output()],
+            hidden=[
+                IO.Hidden.auth_token_comfy_org,
+                IO.Hidden.api_key_comfy_org,
+                IO.Hidden.unique_id,
+            ],
+            is_api_node=True,
+            price_badge=IO.PriceBadge(
+                expr="""{"type":"usd","usd":0.0042,"format":{"suffix":"/second"}}""",
+            ),
+        )
+
+    @classmethod
+    async def execute(
+        cls,
+        video: Input.Video,
+        seed: int,
+        background_image: Input.Image | None = None,
+        background_video: Input.Video | None = None,
+    ) -> IO.NodeOutput:
+        if (background_image is None) == (background_video is None):
+            raise ValueError("Provide either a background image or a background video, not both.")
+        validate_video_duration(video, max_duration=60.0)
+        if background_video is not None:
+            validate_video_duration(background_video, max_duration=60.0)
+            background_url = await upload_video_to_comfyapi(cls, background_video, wait_label="Uploading background")
+        else:
+            # Bria's replace_background 500s on RGBA, so drop the alpha channel before upload.
+            background_url = await upload_image_to_comfyapi(
+                cls, background_image[:, :, :, :3], wait_label="Uploading background"
+            )
+        response = await sync_op(
+            cls,
+            ApiEndpoint(path="/proxy/bria/v2/video/edit/replace_background", method="POST"),
+            data=BriaVideoReplaceBackgroundRequest(
+                video=await upload_video_to_comfyapi(cls, video),
+                background_url=background_url,
+                output_container_and_codec="mp4_h264",
+                seed=seed,
+            ),
+            response_model=BriaStatusResponse,
+        )
+        response = await poll_op(
+            cls,
+            ApiEndpoint(path=f"/proxy/bria/v2/status/{response.request_id}"),
+            status_extractor=lambda r: r.status,
+            response_model=BriaRemoveVideoBackgroundResponse,
+        )
+        return IO.NodeOutput(await download_url_to_video_output(response.result.video_url))
+
+
+def _video_to_images_and_mask(video: Input.Video) -> tuple[Input.Image, Input.Mask]:
+    """Decode a transparent webm (VP9 + alpha) into image frames and an alpha mask.
+
+    VP9 keeps its alpha in a side layer that PyAV's default vp9 decoder drops, so the frames
+    are decoded with libvpx-vp9. Returns RGB images [B,H,W,3] in 0..1 and a mask [B,H,W]
+    following the Load Image convention (1 = transparent) for compositing or Save WEBM.
+    """
+    rgb_frames: list[torch.Tensor] = []
+    alpha_frames: list[torch.Tensor] = []
+    with av.open(video.get_stream_source(), mode="r") as container:
+        stream = container.streams.video[0]
+        decoder = CodecContext.create("libvpx-vp9", "r") if stream.codec_context.name == "vp9" else None
+        for packet in container.demux(stream):
+            for frame in (decoder.decode(packet) if decoder is not None else packet.decode()):
+                rgba = torch.from_numpy(frame.to_ndarray(format="rgba")).float() / 255.0
+                rgb_frames.append(rgba[..., :3])
+                alpha_frames.append(rgba[..., 3])
+    images = torch.stack(rgb_frames) if rgb_frames else torch.zeros(0, 0, 0, 3)
+    mask = (1.0 - torch.stack(alpha_frames)) if alpha_frames else torch.zeros((images.shape[0], 64, 64))
+    return images, mask
+
+
+class BriaTransparentVideoBackground(IO.ComfyNode):
+
+    @classmethod
+    def define_schema(cls):
+        return IO.Schema(
+            node_id="BriaTransparentVideoBackground",
+            display_name="Bria Remove Video Background (Transparent)",
+            category="partner/video/Bria",
+            description="Remove the background from a video using Bria and return the cut-out frames "
+            "plus an alpha mask. Connect both to a compositing node, or feed them to Save WEBM to "
+            "write a transparent video.",
+            inputs=[
+                IO.Video.Input("video"),
+                IO.Int.Input(
+                    "seed",
+                    default=0,
+                    min=0,
+                    max=2147483647,
+                    display_mode=IO.NumberDisplay.number,
+                    control_after_generate=True,
+                    tooltip="Seed controls whether the node should re-run; "
+                    "results are non-deterministic regardless of seed.",
+                ),
+            ],
+            outputs=[
+                IO.Image.Output(display_name="images"),
+                IO.Mask.Output(display_name="mask"),
+            ],
+            hidden=[
+                IO.Hidden.auth_token_comfy_org,
+                IO.Hidden.api_key_comfy_org,
+                IO.Hidden.unique_id,
+            ],
+            is_api_node=True,
+            price_badge=IO.PriceBadge(
+                expr="""{"type":"usd","usd":0.0042,"format":{"suffix":"/second"}}""",
+            ),
+        )
+
+    @classmethod
+    async def execute(
+        cls,
+        video: Input.Video,
+        seed: int,
+    ) -> IO.NodeOutput:
+        validate_video_duration(video, max_duration=60.0)
+        response = await sync_op(
+            cls,
+            ApiEndpoint(path="/proxy/bria/v2/video/edit/remove_background", method="POST"),
+            data=BriaRemoveVideoBackgroundRequest(
+                video=await upload_video_to_comfyapi(cls, video),
+                background_color="Transparent",
+                output_container_and_codec="webm_vp9",
+                seed=seed,
+            ),
+            response_model=BriaStatusResponse,
+        )
+        response = await poll_op(
+            cls,
+            ApiEndpoint(path=f"/proxy/bria/v2/status/{response.request_id}"),
+            status_extractor=lambda r: r.status,
+            response_model=BriaRemoveVideoBackgroundResponse,
+        )
+        video_out = await download_url_to_video_output(response.result.video_url)
+        images, mask = _video_to_images_and_mask(video_out)
+        return IO.NodeOutput(images, mask)
+
+
 class BriaExtension(ComfyExtension):
     @override
     async def get_node_list(self) -> list[type[IO.ComfyNode]]:
@@ -323,6 +573,9 @@ class BriaExtension(ComfyExtension):
             BriaImageEditNode,
             BriaRemoveImageBackground,
             BriaRemoveVideoBackground,
+            BriaVideoGreenScreen,
+            BriaVideoReplaceBackground,
+            BriaTransparentVideoBackground,
         ]
 
 

comfy_api_nodes/nodes_bytedance.py

@@ -1,3 +1,4 @@
+import base64
 import hashlib
 import logging
 import math
@@ -7,6 +8,7 @@ from io import BytesIO
 import torch
 from typing_extensions import override
 
+from comfy.utils import common_upscale
 from comfy_api.latest import IO, ComfyExtension, Input, Types
 from comfy_api_nodes.apis.bytedance import (
     RECOMMENDED_PRESETS,
@@ -14,12 +16,15 @@ from comfy_api_nodes.apis.bytedance import (
     RECOMMENDED_PRESETS_SEEDREAM_4_0,
     RECOMMENDED_PRESETS_SEEDREAM_4_5,
     RECOMMENDED_PRESETS_SEEDREAM_5_LITE,
-    SEEDANCE2_PRICE_PER_1K_TOKENS,
     SEEDANCE2_REF_VIDEO_PIXEL_LIMITS,
     VIDEO_TASKS_EXECUTION_TIME,
     GetAssetResponse,
     Image2VideoTaskCreationRequest,
     ImageTaskCreationResponse,
+    SeedAudioConfig,
+    SeedAudioReference,
+    SeedAudioRequest,
+    SeedAudioResponse,
     Seedance2TaskCreationRequest,
     SeedanceCreateAssetRequest,
     SeedanceCreateAssetResponse,
@@ -39,9 +44,12 @@ from comfy_api_nodes.apis.bytedance import (
     TaskVideoContentUrl,
     Text2ImageTaskCreationRequest,
     Text2VideoTaskCreationRequest,
+    seedance2_price_per_1k_tokens,
 )
 from comfy_api_nodes.util import (
     ApiEndpoint,
+    audio_bytes_to_audio_input,
+    audio_input_to_mp3,
     download_url_to_image_tensor,
     download_url_to_video_output,
     downscale_image_tensor_by_max_side,
@@ -50,11 +58,14 @@ from comfy_api_nodes.util import (
     image_tensor_pair_to_batch,
     poll_op,
     sync_op,
+    tensor_to_base64_string,
     upload_audio_to_comfyapi,
     upload_image_to_comfyapi,
     upload_images_to_comfyapi,
     upload_video_to_comfyapi,
+    upscale_image_tensor_to_min_pixels,
     upscale_video_to_min_pixels,
+    validate_audio_duration,
     validate_image_aspect_ratio,
     validate_image_dimensions,
     validate_string,
@@ -88,6 +99,7 @@ BYTEPLUS_SEEDANCE2_TASK_STATUS_ENDPOINT = "/proxy/byteplus-seedance2/api/v3/cont
 SEEDANCE_MODELS = {
     "Seedance 2.0": "dreamina-seedance-2-0-260128",
     "Seedance 2.0 Fast": "dreamina-seedance-2-0-fast-260128",
+    "Seedance 2.0 Mini": "dreamina-seedance-2-0-mini",
 }
 
 DEPRECATED_MODELS = {"seedance-1-0-lite-t2v-250428", "seedance-1-0-lite-i2v-250428"}
@@ -131,6 +143,44 @@ def _prepare_seedance_image(image: Input.Image) -> Input.Image:
     return image
 
 
+# Supported output aspect ratios, used to pre-size FLF frames to matching pixel pair to avoid the 1080p stretch jump.
+SEEDANCE2_RATIO_WH = {
+    "16:9": (16, 9),
+    "4:3": (4, 3),
+    "1:1": (1, 1),
+    "3:4": (3, 4),
+    "9:16": (9, 16),
+    "21:9": (21, 9),
+}
+SEEDANCE2_RES_SHORT_SIDE = {"480p": 480, "720p": 720, "1080p": 1080, "4k": 2160}
+
+
+def _seedance2_target_dims(resolution: str, ratio: str, image: torch.Tensor) -> tuple[int, int]:
+    """Exact supported output (width, height) for (resolution, ratio).
+
+    The shorter side equals the resolution number (e.g. 1080p 16:9 -> 1920x1080). For ratio
+    "adaptive" (or any unexpected value) the ratio is derived from the image's own aspect, snapped
+    to the nearest supported ratio, so the output keeps the frame's orientation.
+    """
+    short = SEEDANCE2_RES_SHORT_SIDE[resolution]
+    if ratio not in SEEDANCE2_RATIO_WH:
+        aspect = image.shape[-2] / image.shape[-3]  # W / H; tensor is (B, H, W, C)
+        ratio = min(SEEDANCE2_RATIO_WH, key=lambda k: abs(SEEDANCE2_RATIO_WH[k][0] / SEEDANCE2_RATIO_WH[k][1] - aspect))
+    rw, rh = SEEDANCE2_RATIO_WH[ratio]
+    if rw >= rh:  # landscape or square: shorter side is the height
+        out_w, out_h = round(short * rw / rh), short
+    else:  # portrait: shorter side is the width
+        out_w, out_h = short, round(short * rh / rw)
+    return out_w - out_w % 2, out_h - out_h % 2
+
+
+def _resize_to_exact(image: torch.Tensor, width: int, height: int) -> torch.Tensor:
+    """Center-crop to the target aspect and resize to exactly width x height (lanczos)."""
+    samples = image.movedim(-1, 1)  # (B, H, W, C) -> (B, C, H, W)
+    resized = common_upscale(samples, width, height, "lanczos", "center")
+    return resized.movedim(1, -1)
+
+
 async def _resolve_reference_assets(
     cls: type[IO.ComfyNode],
     asset_ids: list[str],
@@ -338,9 +388,9 @@ async def _seedance_virtual_library_upload_video_asset(
     return f"asset://{create_resp.asset_id}"
 
 
-def _seedance2_price_extractor(model_id: str, has_video_input: bool):
+def _seedance2_price_extractor(model_id: str, has_video_input: bool, resolution: str):
     """Returns a price_extractor closure for Seedance 2.0 poll_op."""
-    rate = SEEDANCE2_PRICE_PER_1K_TOKENS.get((model_id, has_video_input))
+    rate = seedance2_price_per_1k_tokens(model_id, has_video_input, resolution)
     if rate is None:
         return None
 
@@ -368,7 +418,7 @@ class ByteDanceImageNode(IO.ComfyNode):
         return IO.Schema(
             node_id="ByteDanceImageNode",
             display_name="ByteDance Image",
-            category="image/partner/ByteDance",
+            category="partner/image/ByteDance",
             description="Generate images using ByteDance models via api based on prompt",
             inputs=[
                 IO.Combo.Input("model", options=["seedream-3-0-t2i-250415"]),
@@ -492,7 +542,7 @@ class ByteDanceSeedreamNode(IO.ComfyNode):
         return IO.Schema(
             node_id="ByteDanceSeedreamNode",
             display_name="ByteDance Seedream 4.5 & 5.0",
-            category="image/partner/ByteDance",
+            category="partner/image/ByteDance",
             description="Unified text-to-image generation and precise single-sentence editing at up to 4K resolution.",
             inputs=[
                 IO.Combo.Input(
@@ -754,7 +804,7 @@ class ByteDanceSeedreamNodeV2(IO.ComfyNode):
         return IO.Schema(
             node_id="ByteDanceSeedreamNodeV2",
             display_name="ByteDance Seedream 4.5 & 5.0",
-            category="image/partner/ByteDance",
+            category="partner/image/ByteDance",
             description="Unified text-to-image generation and precise single-sentence editing at up to 4K resolution.",
             inputs=[
                 IO.String.Input(
@@ -920,7 +970,7 @@ class ByteDanceTextToVideoNode(IO.ComfyNode):
         return IO.Schema(
             node_id="ByteDanceTextToVideoNode",
             display_name="ByteDance Text to Video",
-            category="video/partner/ByteDance",
+            category="partner/video/ByteDance",
             description="Generate video using ByteDance models via api based on prompt",
             inputs=[
                 IO.Combo.Input(
@@ -1048,7 +1098,7 @@ class ByteDanceImageToVideoNode(IO.ComfyNode):
         return IO.Schema(
             node_id="ByteDanceImageToVideoNode",
             display_name="ByteDance Image to Video",
-            category="video/partner/ByteDance",
+            category="partner/video/ByteDance",
             description="Generate video using ByteDance models via api based on image and prompt",
             inputs=[
                 IO.Combo.Input(
@@ -1185,7 +1235,7 @@ class ByteDanceFirstLastFrameNode(IO.ComfyNode):
         return IO.Schema(
             node_id="ByteDanceFirstLastFrameNode",
             display_name="ByteDance First-Last-Frame to Video",
-            category="video/partner/ByteDance",
+            category="partner/video/ByteDance",
             description="Generate video using prompt and first and last frames.",
             inputs=[
                 IO.Combo.Input(
@@ -1333,7 +1383,7 @@ class ByteDanceImageReferenceNode(IO.ComfyNode):
         return IO.Schema(
             node_id="ByteDanceImageReferenceNode",
             display_name="ByteDance Reference Images to Video",
-            category="video/partner/ByteDance",
+            category="partner/video/ByteDance",
             description="Generate video using prompt and reference images.",
             inputs=[
                 IO.Combo.Input(
@@ -1576,16 +1626,18 @@ class ByteDance2TextToVideoNode(IO.ComfyNode):
         return IO.Schema(
             node_id="ByteDance2TextToVideoNode",
             display_name="ByteDance Seedance 2.0 Text to Video",
-            category="video/partner/ByteDance",
+            category="partner/video/ByteDance",
             description="Generate video using Seedance 2.0 models based on a text prompt.",
             inputs=[
                 IO.DynamicCombo.Input(
                     "model",
                     options=[
-                        IO.DynamicCombo.Option("Seedance 2.0", _seedance2_text_inputs(["480p", "720p", "1080p"])),
+                        IO.DynamicCombo.Option("Seedance 2.0", _seedance2_text_inputs(["480p", "720p", "1080p", "4k"])),
                         IO.DynamicCombo.Option("Seedance 2.0 Fast", _seedance2_text_inputs(["480p", "720p"])),
+                        IO.DynamicCombo.Option("Seedance 2.0 Mini", _seedance2_text_inputs(["480p", "720p"])),
                     ],
-                    tooltip="Seedance 2.0 for maximum quality; Seedance 2.0 Fast for speed optimization.",
+                    tooltip="Seedance 2.0 for maximum quality; Fast for speed optimization; "
+                    "Mini for the fastest, lowest-cost generation.",
                 ),
                 IO.Int.Input(
                     "seed",
@@ -1621,11 +1673,16 @@ class ByteDance2TextToVideoNode(IO.ComfyNode):
                   $rate480 := 10044;
                   $rate720 := 21600;
                   $rate1080 := 48800;
+                  $rate4k := 195200;
                   $m := widgets.model;
-                  $pricePer1K := $contains($m, "fast") ? 0.008008 : 0.01001;
                   $res := $lookup(widgets, "model.resolution");
                   $dur := $lookup(widgets, "model.duration");
-                  $rate := $res = "1080p" ? $rate1080 :
+                  $pricePer1K := $res = "4k"    ? 0.00572 :
+                                 $res = "1080p" ? 0.011011 :
+                                 $contains($m, "mini") ? 0.005005 :
+                                 $contains($m, "fast") ? 0.008008 : 0.01001;
+                  $rate := $res = "4k"    ? $rate4k :
+                           $res = "1080p" ? $rate1080 :
                            $res = "720p"  ? $rate720 :
                                             $rate480;
                   $cost := $dur * $rate * $pricePer1K / 1000;
@@ -1664,7 +1721,7 @@ class ByteDance2TextToVideoNode(IO.ComfyNode):
             ApiEndpoint(path=f"{BYTEPLUS_SEEDANCE2_TASK_STATUS_ENDPOINT}/{initial_response.id}"),
             response_model=TaskStatusResponse,
             status_extractor=lambda r: r.status,
-            price_extractor=_seedance2_price_extractor(model_id, has_video_input=False),
+            price_extractor=_seedance2_price_extractor(model_id, has_video_input=False, resolution=model["resolution"]),
             poll_interval=9,
         )
         return IO.NodeOutput(await download_url_to_video_output(response.content.video_url))
@@ -1677,7 +1734,7 @@ class ByteDance2FirstLastFrameNode(IO.ComfyNode):
         return IO.Schema(
             node_id="ByteDance2FirstLastFrameNode",
             display_name="ByteDance Seedance 2.0 First-Last-Frame to Video",
-            category="video/partner/ByteDance",
+            category="partner/video/ByteDance",
             description="Generate video using Seedance 2.0 from a first frame image and optional last frame image.",
             inputs=[
                 IO.DynamicCombo.Input(
@@ -1685,14 +1742,19 @@ class ByteDance2FirstLastFrameNode(IO.ComfyNode):
                     options=[
                         IO.DynamicCombo.Option(
                             "Seedance 2.0",
-                            _seedance2_text_inputs(["480p", "720p", "1080p"], default_ratio="adaptive"),
+                            _seedance2_text_inputs(["480p", "720p", "1080p", "4k"], default_ratio="adaptive"),
                         ),
                         IO.DynamicCombo.Option(
                             "Seedance 2.0 Fast",
                             _seedance2_text_inputs(["480p", "720p"], default_ratio="adaptive"),
                         ),
+                        IO.DynamicCombo.Option(
+                            "Seedance 2.0 Mini",
+                            _seedance2_text_inputs(["480p", "720p"], default_ratio="adaptive"),
+                        ),
                     ],
-                    tooltip="Seedance 2.0 for maximum quality; Seedance 2.0 Fast for speed optimization.",
+                    tooltip="Seedance 2.0 for maximum quality; Fast for speed optimization; "
+                    "Mini for the fastest, lowest-cost generation.",
                 ),
                 IO.Image.Input(
                     "first_frame",
@@ -1752,11 +1814,16 @@ class ByteDance2FirstLastFrameNode(IO.ComfyNode):
                   $rate480 := 10044;
                   $rate720 := 21600;
                   $rate1080 := 48800;
+                  $rate4k := 195200;
                   $m := widgets.model;
-                  $pricePer1K := $contains($m, "fast") ? 0.008008 : 0.01001;
                   $res := $lookup(widgets, "model.resolution");
                   $dur := $lookup(widgets, "model.duration");
-                  $rate := $res = "1080p" ? $rate1080 :
+                  $pricePer1K := $res = "4k"    ? 0.00572 :
+                                 $res = "1080p" ? 0.011011 :
+                                 $contains($m, "mini") ? 0.005005 :
+                                 $contains($m, "fast") ? 0.008008 : 0.01001;
+                  $rate := $res = "4k"    ? $rate4k :
+                           $res = "1080p" ? $rate1080 :
                            $res = "720p"  ? $rate720 :
                                             $rate480;
                   $cost := $dur * $rate * $pricePer1K / 1000;
@@ -1790,10 +1857,28 @@ class ByteDance2FirstLastFrameNode(IO.ComfyNode):
         if last_frame is not None and last_frame_asset_id:
             raise ValueError("Provide only one of last_frame or last_frame_asset_id, not both.")
 
-        if first_frame is not None:
-            first_frame = _prepare_seedance_image(first_frame)
-        if last_frame is not None:
-            last_frame = _prepare_seedance_image(last_frame)
+        request_ratio = model["ratio"]
+        if first_frame_asset_id or last_frame_asset_id:
+            if first_frame is not None:
+                first_frame = _prepare_seedance_image(first_frame)
+            if last_frame is not None:
+                last_frame = _prepare_seedance_image(last_frame)
+        else:
+            # The 1080p FLF stretch fix (pre-size frames to a supported pixel pair + submit ratio="adaptive")
+            # only applies to local image inputs we can resize.
+            request_ratio = "adaptive"
+            target_dims: tuple[int, int] | None = None
+            if first_frame is not None:
+                validate_image_aspect_ratio(first_frame, (2, 5), (5, 2), strict=False)  # 0.4 to 2.5
+                validate_image_dimensions(first_frame, min_width=300, min_height=300)
+                target_dims = _seedance2_target_dims(model["resolution"], model["ratio"], first_frame)
+                first_frame = _resize_to_exact(first_frame, *target_dims)
+            if last_frame is not None:
+                validate_image_aspect_ratio(last_frame, (2, 5), (5, 2), strict=False)  # 0.4 to 2.5
+                validate_image_dimensions(last_frame, min_width=300, min_height=300)
+                if target_dims is None:
+                    target_dims = _seedance2_target_dims(model["resolution"], model["ratio"], last_frame)
+                last_frame = _resize_to_exact(last_frame, *target_dims)
 
         asset_ids_to_resolve = [a for a in (first_frame_asset_id, last_frame_asset_id) if a]
         image_assets: dict[str, str] = {}
@@ -1844,7 +1929,7 @@ class ByteDance2FirstLastFrameNode(IO.ComfyNode):
                 content=content,
                 generate_audio=model["generate_audio"],
                 resolution=model["resolution"],
-                ratio=model["ratio"],
+                ratio=request_ratio,
                 duration=model["duration"],
                 seed=seed,
                 watermark=watermark,
@@ -1856,7 +1941,7 @@ class ByteDance2FirstLastFrameNode(IO.ComfyNode):
             ApiEndpoint(path=f"{BYTEPLUS_SEEDANCE2_TASK_STATUS_ENDPOINT}/{initial_response.id}"),
             response_model=TaskStatusResponse,
             status_extractor=lambda r: r.status,
-            price_extractor=_seedance2_price_extractor(model_id, has_video_input=False),
+            price_extractor=_seedance2_price_extractor(model_id, has_video_input=False, resolution=model["resolution"]),
             poll_interval=9,
         )
         return IO.NodeOutput(await download_url_to_video_output(response.content.video_url))
@@ -1944,7 +2029,7 @@ class ByteDance2ReferenceNode(IO.ComfyNode):
         return IO.Schema(
             node_id="ByteDance2ReferenceNode",
             display_name="ByteDance Seedance 2.0 Reference to Video",
-            category="video/partner/ByteDance",
+            category="partner/video/ByteDance",
             description="Generate, edit, or extend video using Seedance 2.0 with reference images, "
             "videos, and audio. Supports multimodal reference, video editing, and video extension.",
             inputs=[
@@ -1953,14 +2038,19 @@ class ByteDance2ReferenceNode(IO.ComfyNode):
                     options=[
                         IO.DynamicCombo.Option(
                             "Seedance 2.0",
-                            _seedance2_reference_inputs(["480p", "720p", "1080p"], default_ratio="adaptive"),
+                            _seedance2_reference_inputs(["480p", "720p", "1080p", "4k"], default_ratio="adaptive"),
                         ),
                         IO.DynamicCombo.Option(
                             "Seedance 2.0 Fast",
                             _seedance2_reference_inputs(["480p", "720p"], default_ratio="adaptive"),
                         ),
+                        IO.DynamicCombo.Option(
+                            "Seedance 2.0 Mini",
+                            _seedance2_reference_inputs(["480p", "720p"], default_ratio="adaptive"),
+                        ),
                     ],
-                    tooltip="Seedance 2.0 for maximum quality; Seedance 2.0 Fast for speed optimization.",
+                    tooltip="Seedance 2.0 for maximum quality; Fast for speed optimization; "
+                    "Mini for the fastest, lowest-cost generation.",
                 ),
                 IO.Int.Input(
                     "seed",
@@ -1999,13 +2089,21 @@ class ByteDance2ReferenceNode(IO.ComfyNode):
                   $rate480 := 10044;
                   $rate720 := 21600;
                   $rate1080 := 48800;
+                  $rate4k := 195200;
                   $m := widgets.model;
                   $hasVideo := $lookup(inputGroups, "model.reference_videos") > 0;
-                  $noVideoPricePer1K := $contains($m, "fast") ? 0.008008 : 0.01001;
-                  $videoPricePer1K := $contains($m, "fast") ? 0.004719 : 0.006149;
                   $res := $lookup(widgets, "model.resolution");
                   $dur := $lookup(widgets, "model.duration");
-                  $rate := $res = "1080p" ? $rate1080 :
+                  $noVideoPricePer1K := $res = "4k"    ? 0.00572 :
+                                        $res = "1080p" ? 0.011011 :
+                                        $contains($m, "mini") ? 0.005005 :
+                                        $contains($m, "fast") ? 0.008008 : 0.01001;
+                  $videoPricePer1K := $res = "4k"    ? 0.003432 :
+                                      $res = "1080p" ? 0.006721 :
+                                      $contains($m, "mini") ? 0.003003 :
+                                      $contains($m, "fast") ? 0.004719 : 0.006149;
+                  $rate := $res = "4k"    ? $rate4k :
+                           $res = "1080p" ? $rate1080 :
                            $res = "720p"  ? $rate720 :
                                             $rate480;
                   $noVideoCost := $dur * $rate * $noVideoPricePer1K / 1000;
@@ -2201,7 +2299,9 @@ class ByteDance2ReferenceNode(IO.ComfyNode):
             ApiEndpoint(path=f"{BYTEPLUS_SEEDANCE2_TASK_STATUS_ENDPOINT}/{initial_response.id}"),
             response_model=TaskStatusResponse,
             status_extractor=lambda r: r.status,
-            price_extractor=_seedance2_price_extractor(model_id, has_video_input=has_video_input),
+            price_extractor=_seedance2_price_extractor(
+                model_id, has_video_input=has_video_input, resolution=model["resolution"]
+            ),
             poll_interval=9,
         )
         return IO.NodeOutput(await download_url_to_video_output(response.content.video_url))
@@ -2241,7 +2341,7 @@ class ByteDanceCreateImageAsset(IO.ComfyNode):
         return IO.Schema(
             node_id="ByteDanceCreateImageAsset",
             display_name="ByteDance Create Image Asset",
-            category="image/partner/ByteDance",
+            category="partner/image/ByteDance",
             description=(
                 "Create a Seedance 2.0 personal image asset. Uploads the input image and "
                 "registers it in the given asset group. If group_id is empty, runs a real-person "
@@ -2308,7 +2408,7 @@ class ByteDanceCreateVideoAsset(IO.ComfyNode):
         return IO.Schema(
             node_id="ByteDanceCreateVideoAsset",
             display_name="ByteDance Create Video Asset",
-            category="video/partner/ByteDance",
+            category="partner/video/ByteDance",
             description=(
                 "Create a Seedance 2.0 personal video asset. Uploads the input video and "
                 "registers it in the given asset group. If group_id is empty, runs a real-person "
@@ -2384,6 +2484,311 @@ class ByteDanceCreateVideoAsset(IO.ComfyNode):
         return IO.NodeOutput(asset_id, resolved_group)
 
 
+MODE_TEXT = "text only"
+MODE_AUDIO = "audio reference"
+MODE_IMAGE = "image reference"
+MODE_SPEAKER = "preset voice"
+
+# (speaker_id, display_label) for built-in TTS 2.0 voices; resolvable ids are account-scoped.
+SEED_AUDIO_PRESET_VOICES: list[tuple[str, str]] = [
+    ("zh_female_vv_uranus_bigtts", "Vivi (Female, multilingual)"),
+    ("zh_female_xiaohe_uranus_bigtts", "Mindy (Female, multilingual)"),
+    ("en_female_stokie_uranus_bigtts", "Stokie (Female, English)"),
+    ("en_female_dacey_uranus_bigtts", "Dacey (Female, English)"),
+    ("en_male_tim_uranus_bigtts", "Tim (Male, English)"),
+    ("zh_male_m191_uranus_bigtts", "Kian (Male, multilingual)"),
+    ("zh_male_taocheng_uranus_bigtts", "Cedric (Male, multilingual)"),
+    ("zh_male_sophie_uranus_bigtts", "Sophie (Female, multilingual)"),
+    ("zh_female_yingyujiaoxue_uranus_bigtts", "Jean (Female, multilingual)"),
+    ("zh_male_dayi_uranus_bigtts", "Magnus (Male, multilingual)"),
+    ("zh_female_mizai_uranus_bigtts", "Mabel (Female, multilingual)"),
+    ("zh_female_jitangnv_uranus_bigtts", "Nadia (Female, multilingual)"),
+    ("zh_female_meilinvyou_uranus_bigtts", "Opal (Female, multilingual)"),
+    ("zh_female_liuchangnv_uranus_bigtts", "Pearl (Female, multilingual)"),
+    ("zh_male_ruyayichen_uranus_bigtts", "Quentin (Male, multilingual)"),
+    ("zh_female_vivo_uranus_bigtts", "Vienna (Female, multilingual)"),
+    ("zh_female_xiaoai_uranus_bigtts", "Alina (Female, multilingual)"),
+    ("zh_female_cancan_uranus_bigtts", "Corinne (Female, multilingual)"),
+    ("zh_female_tianmeixiaoyuan_uranus_bigtts", "Esther (Female, multilingual)"),
+    ("zh_female_tianmeitaozi_uranus_bigtts", "Freya (Female, multilingual)"),
+    ("zh_female_shuangkuaisisi_uranus_bigtts", "Gigi (Female, multilingual)"),
+    ("zh_female_peiqi_uranus_bigtts", "Holly (Female, multilingual)"),
+    ("zh_female_xiaoxue_uranus_bigtts", "Lyla (Female, multilingual)"),
+    ("zh_female_yuanqi_uranus_bigtts", "Daisy (Female, multilingual)"),
+    ("zh_female_kefunvsheng_uranus_bigtts", "Tracy (Female, multilingual)"),
+    ("zh_male_shaonianzixin_uranus_bigtts", "Jess (Male, multilingual)"),
+    ("zh_female_linjianvhai_uranus_bigtts", "Pinky (Female, multilingual)"),
+    ("zh_female_kiwi_uranus_bigtts", "Sweety (Female, multilingual)"),
+    ("zh_female_sajiaoxuemei_uranus_bigtts", "Sandy (Female, multilingual)"),
+    ("de_male_seven_uranus_bigtts", "Sven (Male, German)"),
+    ("jp_female_minimi_uranus_bigtts", "Minimi (Female, Japanese)"),
+    ("fr_male_usseau_uranus_bigtts", "Usseau (Male, French)"),
+    ("es_male_felipe_uranus_bigtts", "Felipe (Male, Spanish)"),
+    ("id_male_han_uranus_bigtts", "Han (Male, Indonesian)"),
+    ("pt_male_martins_uranus_bigtts", "Martins (Male, Portuguese)"),
+    ("it_male_enzo_uranus_bigtts", "Enzo (Male, Italian)"),
+    ("kr_male_shane_uranus_bigtts", "Shane (Male, Korean)"),
+    ("zh_male_liufei_uranus_bigtts", "Felix (Male, Chinese)"),
+    ("zh_female_qingxinnvsheng_uranus_bigtts", "Celeste (Female, Chinese)"),
+    ("zh_male_sunwukong_uranus_bigtts", "Monkey King (Male, Chinese)"),
+]
+SEED_AUDIO_VOICE_OPTIONS = [label for _, label in SEED_AUDIO_PRESET_VOICES]
+SEED_AUDIO_VOICE_MAP = {label: speaker_id for speaker_id, label in SEED_AUDIO_PRESET_VOICES}
+
+_AUDIO_TAG_RE = re.compile(r"@Audio(\d+)", re.IGNORECASE)
+
+
+def max_audio_tag(prompt: str) -> int:
+    """Highest N referenced as @AudioN in the prompt (0 if none)."""
+    nums = [int(m) for m in _AUDIO_TAG_RE.findall(prompt or "")]
+    return max(nums) if nums else 0
+
+
+def connected_audio_indices(reference_mode: dict) -> list[int]:
+    """Indices (1-based) of connected reference_audio sockets, in order."""
+    return [
+        i
+        for i in range(1, 3 + 1)
+        if reference_mode.get(f"reference_audio_{i}") is not None
+    ]
+
+
+def validate_seed_audio_inputs(
+    text_prompt: str,
+    mode: str,
+    audio_indices: list[int],
+    has_image: bool,
+    preset_voice: str | None = None,
+) -> None:
+    validate_string(text_prompt, field_name="text_prompt", min_length=1, max_length=3000)
+    max_tag = max_audio_tag(text_prompt)
+
+    if mode == MODE_TEXT:
+        if max_tag:
+            raise ValueError(
+                f"The prompt references @Audio{max_tag}, but reference mode is '{MODE_TEXT}'. "
+                f"Switch to '{MODE_AUDIO}' and connect the reference clip(s)."
+            )
+    elif mode == MODE_AUDIO:
+        if not audio_indices:
+            raise ValueError(
+                f"Reference mode '{MODE_AUDIO}' requires at least one reference_audio input "
+                f"(or switch to '{MODE_TEXT}')."
+            )
+        if audio_indices != list(range(1, len(audio_indices) + 1)):
+            raise ValueError(
+                "Connect reference_audio inputs in order without gaps: reference_audio_1, then _2, then _3."
+            )
+        if max_tag > len(audio_indices):
+            raise ValueError(
+                f"The prompt references @Audio{max_tag}, but only {len(audio_indices)} "
+                f"reference audio(s) are connected."
+            )
+    elif mode == MODE_IMAGE:
+        if not has_image:
+            raise ValueError(f"Reference mode '{MODE_IMAGE}' requires a reference_image input.")
+        if max_tag:
+            raise ValueError(
+                f"@AudioN tags are not used in '{MODE_IMAGE}' mode; the prompt should contain "
+                f"only the text to synthesize."
+            )
+    elif mode == MODE_SPEAKER:
+        if not preset_voice or preset_voice not in SEED_AUDIO_VOICE_MAP:
+            raise ValueError(f"Reference mode '{MODE_SPEAKER}' requires selecting a preset voice.")
+        if max_tag > 1:
+            raise ValueError(
+                f"'{MODE_SPEAKER}' mode uses a single voice, so @Audio{max_tag} is out of range. "
+                f"Remove the @AudioN tags — the whole prompt is read in the selected voice."
+            )
+    else:
+        raise ValueError(f"Unknown reference mode: {mode!r}")
+
+
+class ByteDanceSeedAudioNode(IO.ComfyNode):
+
+    @classmethod
+    def define_schema(cls) -> IO.Schema:
+        return IO.Schema(
+            node_id="ByteDanceSeedAudio",
+            display_name="ByteDance Seed Audio 1.0",
+            category="partner/audio/ByteDance",
+            description=(
+                "Generate speech, music, sound effects and multi-speaker dialogue from a single prompt "
+                "with ByteDance Seed Audio 1.0. Describe the voice(s), emotion, ambience, background music "
+                "and sound effects in the prompt, and include the lines to speak. Optionally pick a built-in "
+                "preset voice, clone voices from up to 3 reference clips (tagged @Audio1-3 in the prompt), "
+                "or derive a voice from a character image. Up to 2 minutes of audio per run."
+            ),
+            inputs=[
+                IO.String.Input(
+                    "text_prompt",
+                    multiline=True,
+                    default="",
+                    tooltip=(
+                        "Describe the voice(s), emotion, pacing, ambience, background music and sound "
+                        "effects, and include the lines to speak (name characters inline for dialogue). "
+                        "In 'audio reference' mode, refer to connected clips by order as @Audio1, @Audio2, "
+                        "@Audio3. Maximum 3000 characters."
+                    ),
+                ),
+                IO.DynamicCombo.Input(
+                    "reference_mode",
+                    options=[
+                        IO.DynamicCombo.Option(MODE_TEXT, []),
+                        IO.DynamicCombo.Option(
+                            MODE_AUDIO,
+                            [
+                                IO.Audio.Input(
+                                    "reference_audio_1",
+                                    optional=True,
+                                    tooltip="Reference clip for voice cloning, tagged @Audio1 in the prompt. "
+                                    "Up to 30s.",
+                                ),
+                                IO.Audio.Input(
+                                    "reference_audio_2",
+                                    optional=True,
+                                    tooltip="Reference clip tagged @Audio2 in the prompt. Up to 30s.",
+                                ),
+                                IO.Audio.Input(
+                                    "reference_audio_3",
+                                    optional=True,
+                                    tooltip="Reference clip tagged @Audio3 in the prompt. Up to 30s.",
+                                ),
+                            ],
+                        ),
+                        IO.DynamicCombo.Option(
+                            MODE_IMAGE,
+                            [
+                                IO.Image.Input(
+                                    "reference_image",
+                                    optional=True,
+                                    tooltip="A single character image; the model derives a voice from it. "
+                                    "Cannot be combined with reference audio.",
+                                ),
+                            ],
+                        ),
+                        IO.DynamicCombo.Option(
+                            MODE_SPEAKER,
+                            [
+                                IO.Combo.Input(
+                                    "preset_voice",
+                                    options=SEED_AUDIO_VOICE_OPTIONS,
+                                    default=SEED_AUDIO_VOICE_OPTIONS[0],
+                                    tooltip="A built-in TTS 2.0 voice that reads the prompt. No reference "
+                                    "clip needed, and @AudioN tags are not used in this mode.",
+                                ),
+                            ],
+                        ),
+                    ],
+                    tooltip=(
+                        "How to condition the voice: 'text only' (describe everything in the prompt), "
+                        "'audio reference' (clone up to 3 voices, tagged @Audio1-3), 'image reference' "
+                        "(derive a voice from one character image), or 'preset voice' (pick a built-in "
+                        "named voice that reads the prompt)."
+                    ),
+                ),
+                IO.Combo.Input(
+                    "sample_rate",
+                    options=["8000", "16000", "24000", "32000", "44100", "48000"],
+                    default="24000",
+                    tooltip="Output sample rate in Hz.",
+                ),
+                IO.Int.Input(
+                    "speech_rate",
+                    default=0,
+                    min=-50,
+                    max=100,
+                    tooltip="Speaking speed. 0 = normal, 100 = 2.0x, -50 = 0.5x.",
+                ),
+                IO.Int.Input(
+                    "loudness_rate",
+                    default=0,
+                    min=-50,
+                    max=100,
+                    tooltip="Loudness. 0 = normal, 100 = 2.0x, -50 = 0.5x.",
+                ),
+                IO.Int.Input(
+                    "pitch_rate",
+                    default=0,
+                    min=-12,
+                    max=12,
+                    tooltip="Pitch shift in semitones (-12 to 12).",
+                ),
+                IO.Int.Input(
+                    "seed",
+                    default=42,
+                    min=0,
+                    max=2147483647,
+                    control_after_generate=True,
+                    tooltip="Seed controls whether the node should re-run; "
+                    "results are non-deterministic regardless of seed.",
+                ),
+            ],
+            outputs=[IO.Audio.Output()],
+            hidden=[
+                IO.Hidden.auth_token_comfy_org,
+                IO.Hidden.api_key_comfy_org,
+                IO.Hidden.unique_id,
+            ],
+            is_api_node=True,
+            price_badge=IO.PriceBadge(
+                expr="""{"type":"usd","usd": 0.2145, "format":{"suffix":"/minute","approximate":true}}""",
+            ),
+        )
+
+    @classmethod
+    async def execute(
+        cls,
+        text_prompt: str,
+        reference_mode: dict,
+        sample_rate: str,
+        speech_rate: int,
+        loudness_rate: int,
+        pitch_rate: int,
+        seed: int,
+    ) -> IO.NodeOutput:
+        mode = reference_mode["reference_mode"]
+        audio_indices = connected_audio_indices(reference_mode)
+        image = reference_mode.get("reference_image")
+        preset_voice = reference_mode.get("preset_voice")
+        validate_seed_audio_inputs(text_prompt, mode, audio_indices, image is not None, preset_voice)
+
+        references: list[SeedAudioReference] | None = None
+        if mode == MODE_AUDIO:
+            references = []
+            for i in audio_indices:
+                clip = reference_mode[f"reference_audio_{i}"]
+                validate_audio_duration(clip, max_duration=30.0)
+                mp3_bytes = audio_input_to_mp3(clip).getvalue()
+                references.append(SeedAudioReference(audio_data=base64.b64encode(mp3_bytes).decode("utf-8")))
+        elif mode == MODE_IMAGE:
+            image = upscale_image_tensor_to_min_pixels(image, 160_000)
+            references = [SeedAudioReference(image_data=tensor_to_base64_string(image, mime_type="image/png"))]
+        elif mode == MODE_SPEAKER:
+            references = [SeedAudioReference(speaker=SEED_AUDIO_VOICE_MAP[preset_voice])]
+
+        response = await sync_op(
+            cls,
+            ApiEndpoint(path="/proxy/byteplus/api/v3/tts/create", method="POST"),
+            response_model=SeedAudioResponse,
+            data=SeedAudioRequest(
+                text_prompt=text_prompt,
+                references=references,
+                audio_config=SeedAudioConfig(
+                    sample_rate=int(sample_rate),
+                    speech_rate=speech_rate,
+                    loudness_rate=loudness_rate,
+                    pitch_rate=pitch_rate,
+                ),
+            ),
+        )
+        if not response.audio:
+            raise Exception(
+                f"Seed Audio returned no audio (code={response.code}): {response.message}"
+            )
+        return IO.NodeOutput(audio_bytes_to_audio_input(base64.b64decode(response.audio)))
+
+
 class ByteDanceExtension(ComfyExtension):
     @override
     async def get_node_list(self) -> list[type[IO.ComfyNode]]:
@@ -2400,6 +2805,7 @@ class ByteDanceExtension(ComfyExtension):
             ByteDance2ReferenceNode,
             ByteDanceCreateImageAsset,
             ByteDanceCreateVideoAsset,
+            ByteDanceSeedAudioNode,
         ]
 
 

comfy_api_nodes/nodes_bytedance_llm.py

@@ -144,7 +144,7 @@ class ByteDanceSeedNode(IO.ComfyNode):
         return IO.Schema(
             node_id="ByteDanceSeedNode",
             display_name="ByteDance Seed",
-            category="text/partner/ByteDance",
+            category="partner/text/ByteDance",
             essentials_category="Text Generation",
             description="Generate text responses with ByteDance's Seed 2.0 models. "
             "Provide a text prompt and optionally one or more images or videos for multimodal context.",

comfy_api_nodes/nodes_elevenlabs.py

@@ -69,7 +69,7 @@ class ElevenLabsSpeechToText(IO.ComfyNode):
         return IO.Schema(
             node_id="ElevenLabsSpeechToText",
             display_name="ElevenLabs Speech to Text",
-            category="audio/partner/ElevenLabs",
+            category="partner/audio/ElevenLabs",
             description="Transcribe audio to text. "
             "Supports automatic language detection, speaker diarization, and audio event tagging.",
             inputs=[
@@ -210,7 +210,7 @@ class ElevenLabsVoiceSelector(IO.ComfyNode):
         return IO.Schema(
             node_id="ElevenLabsVoiceSelector",
             display_name="ElevenLabs Voice Selector",
-            category="audio/partner/ElevenLabs",
+            category="partner/audio/ElevenLabs",
             description="Select a predefined ElevenLabs voice for text-to-speech generation.",
             inputs=[
                 IO.Combo.Input(
@@ -239,7 +239,7 @@ class ElevenLabsTextToSpeech(IO.ComfyNode):
         return IO.Schema(
             node_id="ElevenLabsTextToSpeech",
             display_name="ElevenLabs Text to Speech",
-            category="audio/partner/ElevenLabs",
+            category="partner/audio/ElevenLabs",
             description="Convert text to speech.",
             inputs=[
                 IO.Custom(ELEVENLABS_VOICE).Input(
@@ -414,7 +414,7 @@ class ElevenLabsAudioIsolation(IO.ComfyNode):
         return IO.Schema(
             node_id="ElevenLabsAudioIsolation",
             display_name="ElevenLabs Voice Isolation",
-            category="audio/partner/ElevenLabs",
+            category="partner/audio/ElevenLabs",
             description="Remove background noise from audio, isolating vocals or speech.",
             inputs=[
                 IO.Audio.Input(
@@ -459,7 +459,7 @@ class ElevenLabsTextToSoundEffects(IO.ComfyNode):
         return IO.Schema(
             node_id="ElevenLabsTextToSoundEffects",
             display_name="ElevenLabs Text to Sound Effects",
-            category="audio/partner/ElevenLabs",
+            category="partner/audio/ElevenLabs",
             description="Generate sound effects from text descriptions.",
             inputs=[
                 IO.String.Input(
@@ -555,7 +555,7 @@ class ElevenLabsInstantVoiceClone(IO.ComfyNode):
         return IO.Schema(
             node_id="ElevenLabsInstantVoiceClone",
             display_name="ElevenLabs Instant Voice Clone",
-            category="audio/partner/ElevenLabs",
+            category="partner/audio/ElevenLabs",
             description="Create a cloned voice from audio samples. "
             "Provide 1-8 audio recordings of the voice to clone.",
             inputs=[
@@ -658,7 +658,7 @@ class ElevenLabsSpeechToSpeech(IO.ComfyNode):
         return IO.Schema(
             node_id="ElevenLabsSpeechToSpeech",
             display_name="ElevenLabs Speech to Speech",
-            category="audio/partner/ElevenLabs",
+            category="partner/audio/ElevenLabs",
             description="Transform speech from one voice to another while preserving the original content and emotion.",
             inputs=[
                 IO.Custom(ELEVENLABS_VOICE).Input(
@@ -793,7 +793,7 @@ class ElevenLabsTextToDialogue(IO.ComfyNode):
         return IO.Schema(
             node_id="ElevenLabsTextToDialogue",
             display_name="ElevenLabs Text to Dialogue",
-            category="audio/partner/ElevenLabs",
+            category="partner/audio/ElevenLabs",
             description="Generate multi-speaker dialogue from text. Each dialogue entry has its own text and voice.",
             inputs=[
                 IO.Float.Input(

comfy_api_nodes/nodes_gemini.py

@@ -5,20 +5,20 @@ See: https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/infer
 
 import base64
 import os
-from enum import Enum
 from fnmatch import fnmatch
 from io import BytesIO
-from typing import Literal
+from typing import Any, Literal
 
 import torch
 from typing_extensions import override
 
 import folder_paths
-from comfy_api.latest import IO, ComfyExtension, Input, Types
+from comfy_api.latest import IO, ComfyExtension, Input, InputImpl, Types
 from comfy_api_nodes.apis.gemini import (
     GeminiContent,
     GeminiFileData,
     GeminiGenerateContentRequest,
+    GeminiGenerationConfig,
     GeminiGenerateContentResponse,
     GeminiImageConfig,
     GeminiImageGenerateContentRequest,
@@ -37,16 +37,23 @@ from comfy_api_nodes.util import (
     audio_to_base64_string,
     bytesio_to_image_tensor,
     download_url_to_image_tensor,
+    download_url_to_video_output,
     get_number_of_images,
     sync_op,
     tensor_to_base64_string,
+    upload_audio_to_comfyapi,
+    upload_image_to_comfyapi,
     upload_images_to_comfyapi,
+    upload_video_to_comfyapi,
     validate_string,
+    validate_video_duration,
     video_to_base64_string,
 )
 
 GEMINI_BASE_ENDPOINT = "/proxy/vertexai/gemini"
 GEMINI_MAX_INPUT_FILE_SIZE = 20 * 1024 * 1024  # 20 MB
+GEMINI_URL_INPUT_BUDGET = 10
+GEMINI_MAX_INLINE_BYTES = 18 * 1024 * 1024
 GEMINI_IMAGE_SYS_PROMPT = (
     "You are an expert image-generation engine. You must ALWAYS produce an image.\n"
     "Interpret all user input—regardless of "
@@ -72,15 +79,6 @@ GEMINI_IMAGE_2_PRICE_BADGE = IO.PriceBadge(
 )
 
 
-class GeminiImageModel(str, Enum):
-    """
-    Gemini Image Model Names allowed by comfy-api
-    """
-
-    gemini_2_5_flash_image_preview = "gemini-2.5-flash-image-preview"
-    gemini_2_5_flash_image = "gemini-2.5-flash-image"
-
-
 async def create_image_parts(
     cls: type[IO.ComfyNode],
     images: Input.Image | list[Input.Image],
@@ -233,25 +231,38 @@ async def get_image_from_response(response: GeminiGenerateContentResponse, thoug
     return torch.cat(image_tensors, dim=0)
 
 
+async def get_video_from_response(
+    response: GeminiGenerateContentResponse, cls: type[IO.ComfyNode] | None = None
+) -> InputImpl.VideoFromFile:
+    parts = get_parts_by_type(response, "video/*")
+    for part in parts:
+        if part.inlineData and part.inlineData.data:
+            return InputImpl.VideoFromFile(BytesIO(base64.b64decode(part.inlineData.data)))
+        if part.fileData and part.fileData.fileUri:
+            return await download_url_to_video_output(part.fileData.fileUri, cls=cls)
+    model_message = get_text_from_response(response).strip()
+    if model_message:
+        raise ValueError(f"Gemini did not generate a video. Model response: {model_message}")
+    raise ValueError(
+        "Gemini did not generate a video. Try rephrasing your prompt, "
+        "shortening the requested duration, or reducing the number of input images/videos."
+    )
+
+
 def calculate_tokens_price(response: GeminiGenerateContentResponse) -> float | None:
     if not response.modelVersion:
         return None
     # Define prices (Cost per 1,000,000 tokens), see https://cloud.google.com/vertex-ai/generative-ai/pricing
-    if response.modelVersion in ("gemini-2.5-pro-preview-05-06", "gemini-2.5-pro"):
+    output_video_tokens_price = 0.0
+    if response.modelVersion == "gemini-2.5-pro":
         input_tokens_price = 1.25
         output_text_tokens_price = 10.0
         output_image_tokens_price = 0.0
-    elif response.modelVersion in (
-        "gemini-2.5-flash-preview-04-17",
-        "gemini-2.5-flash",
-    ):
+    elif response.modelVersion == "gemini-2.5-flash":
         input_tokens_price = 0.30
         output_text_tokens_price = 2.50
         output_image_tokens_price = 0.0
-    elif response.modelVersion in (
-        "gemini-2.5-flash-image-preview",
-        "gemini-2.5-flash-image",
-    ):
+    elif response.modelVersion == "gemini-2.5-flash-image":
         input_tokens_price = 0.30
         output_text_tokens_price = 2.50
         output_image_tokens_price = 30.0
@@ -259,18 +270,27 @@ def calculate_tokens_price(response: GeminiGenerateContentResponse) -> float | N
         input_tokens_price = 2
         output_text_tokens_price = 12.0
         output_image_tokens_price = 0.0
-    elif response.modelVersion == "gemini-3.1-flash-lite-preview":
+    elif response.modelVersion in ("gemini-3.1-flash-lite-preview", "gemini-3.1-flash-lite"):
         input_tokens_price = 0.25
         output_text_tokens_price = 1.50
         output_image_tokens_price = 0.0
-    elif response.modelVersion == "gemini-3-pro-image-preview":
+    elif response.modelVersion in ("gemini-3-pro-image-preview", "gemini-3-pro-image"):
         input_tokens_price = 2
         output_text_tokens_price = 12.0
         output_image_tokens_price = 120.0
-    elif response.modelVersion == "gemini-3.1-flash-image-preview":
+    elif response.modelVersion in ("gemini-3.1-flash-image-preview", "gemini-3.1-flash-image"):
         input_tokens_price = 0.5
         output_text_tokens_price = 3.0
         output_image_tokens_price = 60.0
+    elif response.modelVersion == "gemini-3.1-flash-lite-image":
+        input_tokens_price = 0.25
+        output_text_tokens_price = 1.50
+        output_image_tokens_price = 30.0
+    elif response.modelVersion == "gemini-omni-flash-preview":
+        input_tokens_price = 2.145
+        output_text_tokens_price = 12.87
+        output_image_tokens_price = 0.0
+        output_video_tokens_price = 25.025
     else:
         return None
     final_price = response.usageMetadata.promptTokenCount * input_tokens_price
@@ -278,6 +298,8 @@ def calculate_tokens_price(response: GeminiGenerateContentResponse) -> float | N
         for i in response.usageMetadata.candidatesTokensDetails:
             if i.modality == Modality.IMAGE:
                 final_price += output_image_tokens_price * i.tokenCount  # for Nano Banana models
+            elif i.modality == Modality.VIDEO:
+                final_price += output_video_tokens_price * i.tokenCount  # for Omni Flash
             else:
                 final_price += output_text_tokens_price * i.tokenCount
     if response.usageMetadata.thoughtsTokenCount:
@@ -285,6 +307,140 @@ def calculate_tokens_price(response: GeminiGenerateContentResponse) -> float | N
     return final_price / 1_000_000.0
 
 
+def create_video_parts(video_input: Input.Video) -> list[GeminiPart]:
+    """Convert a single video input to Gemini API compatible parts (inline MP4/H.264)."""
+    base_64_string = video_to_base64_string(
+        video_input, container_format=Types.VideoContainer.MP4, codec=Types.VideoCodec.H264
+    )
+    return [
+        GeminiPart(
+            inlineData=GeminiInlineData(
+                mimeType=GeminiMimeType.video_mp4,
+                data=base_64_string,
+            )
+        )
+    ]
+
+
+def create_audio_parts(audio_input: Input.Audio) -> list[GeminiPart]:
+    """Convert an audio input to Gemini API compatible parts (one inline MP3 part per batch item)."""
+    audio_parts: list[GeminiPart] = []
+    for batch_index in range(audio_input["waveform"].shape[0]):
+        # Recreate an IO.AUDIO object for the given batch dimension index
+        audio_at_index = Input.Audio(
+            waveform=audio_input["waveform"][batch_index].unsqueeze(0),
+            sample_rate=audio_input["sample_rate"],
+        )
+        # Convert to MP3 format for compatibility with Gemini API
+        audio_bytes = audio_to_base64_string(
+            audio_at_index,
+            container_format="mp3",
+            codec_name="libmp3lame",
+        )
+        audio_parts.append(
+            GeminiPart(
+                inlineData=GeminiInlineData(
+                    mimeType=GeminiMimeType.audio_mp3,
+                    data=audio_bytes,
+                )
+            )
+        )
+    return audio_parts
+
+
+def _flatten_images(images: list[Input.Image]) -> list[torch.Tensor]:
+    """Expand any batched image tensors into individual (H, W, C) frames, preserving order."""
+    frames: list[torch.Tensor] = []
+    for img in images:
+        if len(img.shape) == 4:
+            frames.extend(img[i] for i in range(img.shape[0]))
+        else:
+            frames.append(img)
+    return frames
+
+
+def _flatten_audio(audios: list[Input.Audio]) -> list[Input.Audio]:
+    """Expand any batched audio inputs into individual single-clip audio inputs, preserving order."""
+    clips: list[Input.Audio] = []
+    for audio in audios:
+        waveform = audio["waveform"]
+        for i in range(waveform.shape[0]):
+            clips.append(Input.Audio(waveform=waveform[i].unsqueeze(0), sample_rate=audio["sample_rate"]))
+    return clips
+
+
+async def _media_url_part(cls: type[IO.ComfyNode], kind: str, payload: Any) -> GeminiPart:
+    """Upload a single media unit to ComfyAPI storage and return a fileData (URL) part."""
+    if kind == "image":
+        url = await upload_image_to_comfyapi(cls, payload, mime_type="image/png", wait_label="Uploading image")
+        return GeminiPart(fileData=GeminiFileData(mimeType=GeminiMimeType.image_png, fileUri=url))
+    if kind == "audio":
+        url = await upload_audio_to_comfyapi(
+            cls, payload, container_format="mp3", codec_name="libmp3lame", mime_type="audio/mp3"
+        )
+        return GeminiPart(fileData=GeminiFileData(mimeType=GeminiMimeType.audio_mp3, fileUri=url))
+    url = await upload_video_to_comfyapi(cls, payload, wait_label="Uploading video")
+    return GeminiPart(fileData=GeminiFileData(mimeType=GeminiMimeType.video_mp4, fileUri=url))
+
+
+def _media_inline_part(kind: str, payload: Any) -> tuple[GeminiPart, int]:
+    """Encode a single media unit as an inline base64 part; returns (part, base64_length)."""
+    if kind == "image":
+        data = tensor_to_base64_string(payload, mime_type="image/webp")
+        mime = GeminiMimeType.image_webp
+    elif kind == "audio":
+        data = audio_to_base64_string(payload, container_format="mp3", codec_name="libmp3lame")
+        mime = GeminiMimeType.audio_mp3
+    else:
+        data = video_to_base64_string(
+            payload, container_format=Types.VideoContainer.MP4, codec=Types.VideoCodec.H264
+        )
+        mime = GeminiMimeType.video_mp4
+    return GeminiPart(inlineData=GeminiInlineData(mimeType=mime, data=data)), len(data)
+
+
+async def build_gemini_media_parts(
+    cls: type[IO.ComfyNode],
+    images: list[Input.Image],
+    audios: list[Input.Audio],
+    videos: list[Input.Video],
+    *,
+    url_budget: int = GEMINI_URL_INPUT_BUDGET,
+    max_inline_bytes: int = GEMINI_MAX_INLINE_BYTES,
+) -> list[GeminiPart]:
+    """Build Gemini parts for multimodal inputs (images, audio, video).
+
+    fileData URLs are preferred for every media type: the upload is fetched directly by the
+    model, keeping the request body tiny regardless of media size. The URL budget is shared
+    across all media and assigned largest-first (video, then audio, then images), so that if it
+    is ever exhausted the inline-base64 overflow is limited to the smallest items. Total inline
+    payload is capped by `max_inline_bytes`.
+    """
+    units: list[tuple[str, Any]] = (
+        [("video", v) for v in videos]
+        + [("audio", a) for a in _flatten_audio(audios)]
+        + [("image", f) for f in _flatten_images(images)]
+    )
+
+    parts: list[GeminiPart] = []
+    url_used = 0
+    inline_bytes = 0
+    for kind, payload in units:
+        if url_used < url_budget:
+            parts.append(await _media_url_part(cls, kind, payload))
+            url_used += 1
+            continue
+        part, nbytes = _media_inline_part(kind, payload)
+        inline_bytes += nbytes
+        if inline_bytes > max_inline_bytes:
+            raise ValueError(
+                f"Too much media to send inline (over {max_inline_bytes // (1024 * 1024)}MB after the first "
+                f"{url_budget} inputs are uploaded as URLs). Reduce the number or size of attached media."
+            )
+        parts.append(part)
+    return parts
+
+
 class GeminiNode(IO.ComfyNode):
     """
     Node to generate text responses from a Gemini model.
@@ -300,7 +456,7 @@ class GeminiNode(IO.ComfyNode):
         return IO.Schema(
             node_id="GeminiNode",
             display_name="Google Gemini",
-            category="text/partner/Gemini",
+            category="partner/text/Gemini",
             description="Generate text responses with Google's Gemini AI model. "
             "You can provide multiple types of inputs (text, images, audio, video) "
             "as context for generating more relevant and meaningful responses.",
@@ -315,8 +471,6 @@ class GeminiNode(IO.ComfyNode):
                 IO.Combo.Input(
                     "model",
                     options=[
-                        "gemini-2.5-pro-preview-05-06",
-                        "gemini-2.5-flash-preview-04-17",
                         "gemini-2.5-pro",
                         "gemini-2.5-flash",
                         "gemini-3-pro-preview",
@@ -407,58 +561,9 @@ class GeminiNode(IO.ComfyNode):
                 )
                 """,
             ),
+            is_deprecated=True,
         )
 
-    @classmethod
-    def create_video_parts(cls, video_input: Input.Video) -> list[GeminiPart]:
-        """Convert video input to Gemini API compatible parts."""
-
-        base_64_string = video_to_base64_string(
-            video_input, container_format=Types.VideoContainer.MP4, codec=Types.VideoCodec.H264
-        )
-        return [
-            GeminiPart(
-                inlineData=GeminiInlineData(
-                    mimeType=GeminiMimeType.video_mp4,
-                    data=base_64_string,
-                )
-            )
-        ]
-
-    @classmethod
-    def create_audio_parts(cls, audio_input: Input.Audio) -> list[GeminiPart]:
-        """
-        Convert audio input to Gemini API compatible parts.
-
-        Args:
-            audio_input: Audio input from ComfyUI, containing waveform tensor and sample rate.
-
-        Returns:
-            List of GeminiPart objects containing the encoded audio.
-        """
-        audio_parts: list[GeminiPart] = []
-        for batch_index in range(audio_input["waveform"].shape[0]):
-            # Recreate an IO.AUDIO object for the given batch dimension index
-            audio_at_index = Input.Audio(
-                waveform=audio_input["waveform"][batch_index].unsqueeze(0),
-                sample_rate=audio_input["sample_rate"],
-            )
-            # Convert to MP3 format for compatibility with Gemini API
-            audio_bytes = audio_to_base64_string(
-                audio_at_index,
-                container_format="mp3",
-                codec_name="libmp3lame",
-            )
-            audio_parts.append(
-                GeminiPart(
-                    inlineData=GeminiInlineData(
-                        mimeType=GeminiMimeType.audio_mp3,
-                        data=audio_bytes,
-                    )
-                )
-            )
-        return audio_parts
-
     @classmethod
     async def execute(
         cls,
@@ -482,9 +587,9 @@ class GeminiNode(IO.ComfyNode):
         if images is not None:
             parts.extend(await create_image_parts(cls, images))
         if audio is not None:
-            parts.extend(cls.create_audio_parts(audio))
+            parts.extend(create_audio_parts(audio))
         if video is not None:
-            parts.extend(cls.create_video_parts(video))
+            parts.extend(create_video_parts(video))
         if files is not None:
             parts.extend(files)
 
@@ -512,6 +617,210 @@ class GeminiNode(IO.ComfyNode):
         return IO.NodeOutput(output_text or "Empty response from Gemini model...")
 
 
+GEMINI_V2_MODELS: dict[str, str] = {
+    "Gemini 3.1 Pro": "gemini-3.1-pro-preview",
+    "Gemini 3.1 Flash-Lite": "gemini-3.1-flash-lite-preview",
+}
+
+
+def _gemini_text_model_inputs(thinking_default: str) -> list[Input]:
+    """Per-model inputs revealed by the model DynamicCombo (shared media + sampling controls)."""
+    return [
+        IO.Autogrow.Input(
+            "images",
+            template=IO.Autogrow.TemplateNames(
+                IO.Image.Input("image"),
+                names=[f"image_{i}" for i in range(1, 17)],
+                min=0,
+            ),
+            tooltip="Optional image(s) to use as context for the model. Up to 16 images.",
+        ),
+        IO.Autogrow.Input(
+            "audio",
+            template=IO.Autogrow.TemplateNames(
+                IO.Audio.Input("audio"),
+                names=["audio_1"],
+                min=0,
+            ),
+            tooltip="Optional audio clip to use as context for the model.",
+        ),
+        IO.Autogrow.Input(
+            "video",
+            template=IO.Autogrow.TemplateNames(
+                IO.Video.Input("video"),
+                names=["video_1"],
+                min=0,
+            ),
+            tooltip="Optional video clip to use as context for the model.",
+        ),
+        IO.Custom("GEMINI_INPUT_FILES").Input(
+            "files",
+            optional=True,
+            tooltip="Optional file(s) to use as context for the model. "
+            "Accepts inputs from the Gemini Input Files node.",
+        ),
+        IO.Combo.Input(
+            "thinking_level",
+            options=["LOW", "HIGH"],
+            default=thinking_default,
+            tooltip="How hard the model reasons internally before answering. "
+            "HIGH improves quality on difficult tasks but costs more (thinking) tokens and is slower.",
+        ),
+        IO.Float.Input(
+            "temperature",
+            default=1.0,
+            min=0.0,
+            max=2.0,
+            step=0.01,
+            tooltip="Controls randomness. Lower is more focused/deterministic, higher is more creative.",
+            advanced=True,
+        ),
+        IO.Float.Input(
+            "top_p",
+            default=0.95,
+            min=0.0,
+            max=1.0,
+            step=0.01,
+            tooltip="Nucleus sampling: sample from the smallest token set whose cumulative probability reaches top_p.",
+            advanced=True,
+        ),
+        IO.Int.Input(
+            "max_output_tokens",
+            default=32768,
+            min=16,
+            max=65536,
+            tooltip="Maximum tokens to generate, including the model's internal thinking. "
+            "With thinking_level HIGH, a low value can leave no room for the answer; raise this if "
+            "responses come back empty or truncated. The model stops early when finished, so a higher "
+            "cap costs nothing extra for short replies.",
+            advanced=True,
+        ),
+    ]
+
+
+class GeminiNodeV2(IO.ComfyNode):
+
+    @classmethod
+    def define_schema(cls):
+        return IO.Schema(
+            node_id="GeminiNodeV2",
+            display_name="Google Gemini",
+            category="partner/text/Gemini",
+            essentials_category="Text Generation",
+            description="Generate text responses with Google's Gemini models. Provide a text prompt and, "
+            "optionally, one or more images, audio clips, videos, or files as multimodal context.",
+            inputs=[
+                IO.String.Input(
+                    "prompt",
+                    multiline=True,
+                    default="",
+                    tooltip="Text input to the model. Include detailed instructions, questions, or context.",
+                ),
+                IO.DynamicCombo.Input(
+                    "model",
+                    options=[
+                        IO.DynamicCombo.Option("Gemini 3.1 Pro", _gemini_text_model_inputs("HIGH")),
+                        IO.DynamicCombo.Option("Gemini 3.1 Flash-Lite", _gemini_text_model_inputs("LOW")),
+                    ],
+                    tooltip="The Gemini model used to generate the response.",
+                ),
+                IO.Int.Input(
+                    "seed",
+                    default=42,
+                    min=0,
+                    max=2147483647,
+                    control_after_generate=True,
+                    tooltip="Seed for sampling. Set to 0 for a random seed. Deterministic output isn't guaranteed.",
+                ),
+                IO.String.Input(
+                    "system_prompt",
+                    multiline=True,
+                    default="",
+                    optional=True,
+                    advanced=True,
+                    tooltip="Foundational instructions that dictate the model's behavior.",
+                ),
+            ],
+            outputs=[
+                IO.String.Output(),
+            ],
+            hidden=[
+                IO.Hidden.auth_token_comfy_org,
+                IO.Hidden.api_key_comfy_org,
+                IO.Hidden.unique_id,
+            ],
+            is_api_node=True,
+            price_badge=IO.PriceBadge(
+                depends_on=IO.PriceBadgeDepends(widgets=["model"]),
+                expr="""
+                (
+                  $m := widgets.model;
+                  $contains($m, "lite") ? {
+                    "type": "list_usd",
+                    "usd": [0.00025, 0.0015],
+                    "format": { "approximate": true, "separator": "-", "suffix": " per 1K tokens" }
+                  } : {
+                    "type": "list_usd",
+                    "usd": [0.002, 0.012],
+                    "format": { "approximate": true, "separator": "-", "suffix": " per 1K tokens" }
+                  }
+                )
+                """,
+            ),
+        )
+
+    @classmethod
+    async def execute(
+        cls,
+        prompt: str,
+        model: dict,
+        seed: int,
+        system_prompt: str = "",
+    ) -> IO.NodeOutput:
+        validate_string(prompt, strip_whitespace=True, min_length=1)
+        model_id = GEMINI_V2_MODELS[model["model"]]
+
+        parts: list[GeminiPart] = [GeminiPart(text=prompt)]
+        images = [t for t in (model.get("images") or {}).values() if t is not None]
+        audios = [a for a in (model.get("audio") or {}).values() if a is not None]
+        videos = [v for v in (model.get("video") or {}).values() if v is not None]
+        if images or audios or videos:
+            parts.extend(await build_gemini_media_parts(cls, images, audios, videos))
+        files = model.get("files")
+        if files is not None:
+            parts.extend(files)
+
+        gemini_system_prompt = None
+        if system_prompt:
+            gemini_system_prompt = GeminiSystemInstructionContent(parts=[GeminiTextPart(text=system_prompt)], role=None)
+
+        response = await sync_op(
+            cls,
+            endpoint=ApiEndpoint(path=f"{GEMINI_BASE_ENDPOINT}/{model_id}", method="POST"),
+            data=GeminiGenerateContentRequest(
+                contents=[
+                    GeminiContent(
+                        role=GeminiRole.user,
+                        parts=parts,
+                    )
+                ],
+                generationConfig=GeminiGenerationConfig(
+                    temperature=model["temperature"],
+                    topP=model["top_p"],
+                    maxOutputTokens=model["max_output_tokens"],
+                    seed=seed if seed > 0 else None,
+                    thinkingConfig=GeminiThinkingConfig(thinkingLevel=model["thinking_level"]),
+                ),
+                systemInstruction=gemini_system_prompt,
+            ),
+            response_model=GeminiGenerateContentResponse,
+            price_extractor=calculate_tokens_price,
+        )
+
+        output_text = get_text_from_response(response)
+        return IO.NodeOutput(output_text or "Empty response from Gemini model...")
+
+
 class GeminiInputFiles(IO.ComfyNode):
     """
     Loads and formats input files for use with the Gemini API.
@@ -541,7 +850,7 @@ class GeminiInputFiles(IO.ComfyNode):
         return IO.Schema(
             node_id="GeminiInputFiles",
             display_name="Gemini Input Files",
-            category="text/partner/Gemini",
+            category="partner/text/Gemini",
             description="Loads and prepares input files to include as inputs for Gemini LLM nodes. "
             "The files will be read by the Gemini model when generating a response. "
             "The contents of the text file count toward the token limit. "
@@ -598,7 +907,7 @@ class GeminiImage(IO.ComfyNode):
         return IO.Schema(
             node_id="GeminiImageNode",
             display_name="Nano Banana (Google Gemini Image)",
-            category="image/partner/Gemini",
+            category="partner/image/Gemini",
             description="Edit images synchronously via Google API.",
             inputs=[
                 IO.String.Input(
@@ -609,8 +918,7 @@ class GeminiImage(IO.ComfyNode):
                 ),
                 IO.Combo.Input(
                     "model",
-                    options=GeminiImageModel,
-                    default=GeminiImageModel.gemini_2_5_flash_image,
+                    options=["gemini-2.5-flash-image"],
                     tooltip="The Gemini model to use for generating responses.",
                 ),
                 IO.Int.Input(
@@ -731,7 +1039,7 @@ class GeminiImage2(IO.ComfyNode):
         return IO.Schema(
             node_id="GeminiImage2Node",
             display_name="Nano Banana Pro (Google Gemini Image)",
-            category="image/partner/Gemini",
+            category="partner/image/Gemini",
             description="Generate or edit images synchronously via Google Vertex API.",
             inputs=[
                 IO.String.Input(
@@ -869,7 +1177,7 @@ class GeminiNanoBanana2(IO.ComfyNode):
         return IO.Schema(
             node_id="GeminiNanoBanana2",
             display_name="Nano Banana 2",
-            category="image/partner/Gemini",
+            category="partner/image/Gemini",
             description="Generate or edit images synchronously via Google Vertex API.",
             inputs=[
                 IO.String.Input(
@@ -1026,7 +1334,7 @@ class GeminiNanoBanana2(IO.ComfyNode):
         )
 
 
-def _nano_banana_2_v2_model_inputs():
+def _nano_banana_2_v2_model_inputs(resolutions: list[str]):
     return [
         IO.Combo.Input(
             "aspect_ratio",
@@ -1053,8 +1361,8 @@ def _nano_banana_2_v2_model_inputs():
         ),
         IO.Combo.Input(
             "resolution",
-            options=["1K", "2K", "4K"],
-            tooltip="Target output resolution. For 2K/4K the native Gemini upscaler is used.",
+            options=resolutions,
+            tooltip="Target output resolution.",
         ),
         IO.Combo.Input(
             "thinking_level",
@@ -1085,7 +1393,7 @@ class GeminiNanoBanana2V2(IO.ComfyNode):
         return IO.Schema(
             node_id="GeminiNanoBanana2V2",
             display_name="Nano Banana 2",
-            category="image/partner/Gemini",
+            category="partner/image/Gemini",
             description="Generate or edit images synchronously via Google Vertex API.",
             inputs=[
                 IO.String.Input(
@@ -1100,7 +1408,11 @@ class GeminiNanoBanana2V2(IO.ComfyNode):
                     options=[
                         IO.DynamicCombo.Option(
                             "Nano Banana 2 (Gemini 3.1 Flash Image)",
-                            _nano_banana_2_v2_model_inputs(),
+                            _nano_banana_2_v2_model_inputs(resolutions=["1K", "2K", "4K"]),
+                        ),
+                        IO.DynamicCombo.Option(
+                            "Nano Banana 2 Lite",
+                            _nano_banana_2_v2_model_inputs(resolutions=["1K"]),
                         ),
                     ],
                 ),
@@ -1129,6 +1441,26 @@ class GeminiNanoBanana2V2(IO.ComfyNode):
                     tooltip="Foundational instructions that dictate an AI's behavior.",
                     advanced=True,
                 ),
+                IO.Float.Input(
+                    "temperature",
+                    default=1.0,
+                    min=0.0,
+                    max=2.0,
+                    step=0.01,
+                    optional=True,
+                    tooltip="Controls randomness in generation. Lower is more focused/deterministic.",
+                    advanced=True,
+                ),
+                IO.Float.Input(
+                    "top_p",
+                    default=0.95,
+                    min=0.0,
+                    max=1.0,
+                    step=0.01,
+                    optional=True,
+                    tooltip="Nucleus sampling threshold. Lower is more focused, higher more diverse.",
+                    advanced=True,
+                ),
             ],
             outputs=[
                 IO.Image.Output(),
@@ -1149,9 +1481,13 @@ class GeminiNanoBanana2V2(IO.ComfyNode):
                 depends_on=IO.PriceBadgeDepends(widgets=["model", "model.resolution"]),
                 expr="""
                 (
-                  $r := $lookup(widgets, "model.resolution");
-                  $prices := {"1k": 0.0696, "2k": 0.1014, "4k": 0.154};
-                  {"type":"usd","usd": $lookup($prices, $r), "format":{"suffix":"/Image","approximate":true}}
+                  $contains(widgets.model, "lite")
+                    ? {"type":"usd","usd": 0.034, "format":{"suffix":"/Image","approximate":true}}
+                    : (
+                        $r := $lookup(widgets, "model.resolution");
+                        $prices := {"1k": 0.0696, "2k": 0.1014, "4k": 0.154};
+                        {"type":"usd","usd": $lookup($prices, $r), "format":{"suffix":"/Image","approximate":true}}
+                      )
                 )
                 """,
             ),
@@ -1165,11 +1501,15 @@ class GeminiNanoBanana2V2(IO.ComfyNode):
         seed: int,
         response_modalities: str,
         system_prompt: str = "",
+        temperature: float = 1.0,
+        top_p: float = 0.95,
     ) -> IO.NodeOutput:
         validate_string(prompt, strip_whitespace=True, min_length=1)
         model_choice = model["model"]
         if model_choice == "Nano Banana 2 (Gemini 3.1 Flash Image)":
             model_id = "gemini-3.1-flash-image-preview"
+        elif model_choice == "Nano Banana 2 Lite":
+            model_id = "gemini-3.1-flash-lite-image"
         else:
             model_id = model_choice
 
@@ -1204,6 +1544,8 @@ class GeminiNanoBanana2V2(IO.ComfyNode):
                     responseModalities=(["IMAGE"] if response_modalities == "IMAGE" else ["TEXT", "IMAGE"]),
                     imageConfig=image_config,
                     thinkingConfig=GeminiThinkingConfig(thinkingLevel=model["thinking_level"]),
+                    temperature=temperature,
+                    topP=top_p,
                 ),
                 systemInstruction=gemini_system_prompt,
             ),
@@ -1217,15 +1559,160 @@ class GeminiNanoBanana2V2(IO.ComfyNode):
         )
 
 
+OMNI_MAX_IMAGES = 14
+OMNI_MAX_VIDEOS = 3
+
+OMNI_MODELS: dict[str, str] = {
+    "Omni Flash": "gemini-omni-flash-preview",
+}
+
+
+def _omni_flash_inputs() -> list[Input]:
+    """Per-model inputs for the Omni video DynamicCombo (prompt + reference media + sampling)."""
+    return [
+        IO.String.Input(
+            "prompt",
+            multiline=True,
+            default="",
+            tooltip="Describe the video to generate. Specify the length and aspect ratio directly in the "
+            'prompt, e.g. "a 6-second clip in 16:9". Length may be 3-10 seconds; the aspect ratio must be '
+            "16:9 (landscape) or 9:16 (portrait). The output is 720p, 24 FPS, with audio.",
+        ),
+        IO.Autogrow.Input(
+            "images",
+            template=IO.Autogrow.TemplateNames(
+                IO.Image.Input("image"),
+                names=[f"image_{i}" for i in range(1, OMNI_MAX_IMAGES + 1)],
+                min=0,
+            ),
+            tooltip=f"Optional reference image(s) to guide or animate the video. Up to {OMNI_MAX_IMAGES} images.",
+        ),
+        IO.Autogrow.Input(
+            "videos",
+            template=IO.Autogrow.TemplateNames(
+                IO.Video.Input("video"),
+                names=[f"video_{i}" for i in range(1, OMNI_MAX_VIDEOS + 1)],
+                min=0,
+            ),
+            tooltip=f"Optional reference video(s) to guide or edit. Up to {OMNI_MAX_VIDEOS} videos, "
+            f"each up to 10 seconds long.",
+        ),
+        IO.Float.Input(
+            "temperature",
+            default=1.0,
+            min=0.0,
+            max=2.0,
+            step=0.01,
+            tooltip="Controls randomness. Lower is more focused/deterministic, higher is more varied.",
+            advanced=True,
+        ),
+        IO.Float.Input(
+            "top_p",
+            default=0.95,
+            min=0.0,
+            max=1.0,
+            step=0.01,
+            tooltip="Nucleus sampling: sample from the smallest token set whose cumulative probability reaches top_p.",
+            advanced=True,
+        ),
+    ]
+
+
+class GeminiVideoOmni(IO.ComfyNode):
+
+    @classmethod
+    def define_schema(cls):
+        return IO.Schema(
+            node_id="GeminiVideoOmni",
+            display_name="Google Gemini Omni (Video)",
+            category="partner/video/Gemini",
+            essentials_category="Video Generation",
+            description="Generate a video with audio from a text prompt using Google's Gemini Omni Flash model. "
+            "Optionally provide reference images and/or videos to guide or edit the result. Describe the desired "
+            "length (3-10s) and aspect ratio (16:9 or 9:16) directly in the prompt.",
+            inputs=[
+                IO.DynamicCombo.Input(
+                    "model",
+                    options=[
+                        IO.DynamicCombo.Option("Omni Flash", _omni_flash_inputs()),
+                    ],
+                    tooltip="The Gemini video model used to generate the video.",
+                ),
+                IO.Int.Input(
+                    "seed",
+                    default=42,
+                    min=0,
+                    max=2147483647,
+                    control_after_generate=True,
+                    tooltip="Seed controls whether the node should re-run; "
+                    "results are non-deterministic regardless of seed.",
+                ),
+            ],
+            outputs=[
+                IO.Video.Output(),
+                IO.String.Output(),
+            ],
+            hidden=[
+                IO.Hidden.auth_token_comfy_org,
+                IO.Hidden.api_key_comfy_org,
+                IO.Hidden.unique_id,
+            ],
+            is_api_node=True,
+            price_badge=IO.PriceBadge(
+                expr='{"type":"usd","usd":0.146,"format":{"suffix":"/second","approximate":true}}'
+            ),
+        )
+
+    @classmethod
+    async def execute(cls, model: dict, seed: int) -> IO.NodeOutput:
+        prompt = model.get("prompt") or ""
+        validate_string(prompt, strip_whitespace=True, min_length=1)
+        model_id = OMNI_MODELS[model["model"]]
+
+        images = [t for t in (model.get("images") or {}).values() if t is not None]
+        videos = [v for v in (model.get("videos") or {}).values() if v is not None]
+        if sum(get_number_of_images(t) for t in images) > OMNI_MAX_IMAGES:
+            raise ValueError(f"The current maximum number of supported images is {OMNI_MAX_IMAGES}.")
+        if len(videos) > OMNI_MAX_VIDEOS:
+            raise ValueError(f"The current maximum number of supported videos is {OMNI_MAX_VIDEOS}.")
+        for video in videos:
+            validate_video_duration(video, max_duration=10)
+
+        parts: list[GeminiPart] = []
+        if images or videos:
+            parts.extend(await build_gemini_media_parts(cls, images, [], videos))
+        parts.append(GeminiPart(text=prompt))
+        response = await sync_op(
+            cls,
+            ApiEndpoint(path=f"{GEMINI_BASE_ENDPOINT}/{model_id}", method="POST"),
+            data=GeminiGenerateContentRequest(
+                contents=[GeminiContent(role=GeminiRole.user, parts=parts)],
+                generationConfig=GeminiGenerationConfig(
+                    responseModalities=["TEXT", "VIDEO"],
+                    temperature=model.get("temperature", 1.0),
+                    topP=model.get("top_p", 0.95),
+                ),
+            ),
+            response_model=GeminiGenerateContentResponse,
+            price_extractor=calculate_tokens_price,
+        )
+        return IO.NodeOutput(
+            await get_video_from_response(response, cls=cls),
+            get_text_from_response(response),
+        )
+
+
 class GeminiExtension(ComfyExtension):
     @override
     async def get_node_list(self) -> list[type[IO.ComfyNode]]:
         return [
             GeminiNode,
+            GeminiNodeV2,
             GeminiImage,
             GeminiImage2,
             GeminiNanoBanana2,
             GeminiNanoBanana2V2,
+            GeminiVideoOmni,
             GeminiInputFiles,
         ]
 

comfy_api_nodes/nodes_grok.py

@@ -30,7 +30,7 @@ from comfy_api_nodes.util import (
 
 
 _GROK_VIDEO_MODEL_API_IDS = {
-    "grok-imagine-video-1.5": "grok-imagine-video-1.5-preview",
+    "grok-imagine-video-1.5": "grok-imagine-video-1.5",
 }
 
 
@@ -54,7 +54,7 @@ class GrokImageNode(IO.ComfyNode):
         return IO.Schema(
             node_id="GrokImageNode",
             display_name="Grok Image",
-            category="image/partner/Grok",
+            category="partner/image/Grok",
             description="Generate images using Grok based on a text prompt",
             inputs=[
                 IO.Combo.Input(
@@ -228,7 +228,7 @@ class GrokImageEditNode(IO.ComfyNode):
         return IO.Schema(
             node_id="GrokImageEditNode",
             display_name="Grok Image Edit",
-            category="image/partner/Grok",
+            category="partner/image/Grok",
             description="Modify an existing image based on a text prompt",
             inputs=[
                 IO.Combo.Input(
@@ -369,7 +369,7 @@ class GrokImageEditNodeV2(IO.ComfyNode):
         return IO.Schema(
             node_id="GrokImageEditNodeV2",
             display_name="Grok Image Edit",
-            category="image/partner/Grok",
+            category="partner/image/Grok",
             description="Modify an existing image based on a text prompt",
             inputs=[
                 IO.String.Input(
@@ -506,7 +506,7 @@ class GrokVideoNode(IO.ComfyNode):
         return IO.Schema(
             node_id="GrokVideoNode",
             display_name="Grok Video",
-            category="video/partner/Grok",
+            category="partner/video/Grok",
             description="Generate video from a prompt or an image",
             inputs=[
                 IO.Combo.Input(
@@ -521,8 +521,8 @@ class GrokVideoNode(IO.ComfyNode):
                 ),
                 IO.Combo.Input(
                     "resolution",
-                    options=["480p", "720p"],
-                    tooltip="The resolution of the output video.",
+                    options=["480p", "720p", "1080p"],
+                    tooltip="The resolution of the output video. 1080p is only available for grok-imagine-video-1.5.",
                 ),
                 IO.Combo.Input(
                     "aspect_ratio",
@@ -570,11 +570,12 @@ class GrokVideoNode(IO.ComfyNode):
                 (
                   $is15 := $contains(widgets.model, "1.5");
                   $rate := $is15
-                    ? (widgets.resolution = "720p" ? 0.2002 : 0.1144)
+                    ? (widgets.resolution = "1080p" ? 0.25 : (widgets.resolution = "720p" ? 0.14 : 0.08))
                     : (widgets.resolution = "720p" ? 0.07 : 0.05);
-                  $imgCost := $is15 ? 0.0143 : 0.002;
+                  $imgCost := $is15 ? 0.01 : 0.002;
                   $base := $rate * widgets.duration;
-                  {"type":"usd","usd": inputs.image.connected ? $base + $imgCost : $base}
+                  $total := inputs.image.connected ? $base + $imgCost : $base;
+                  {"type":"usd","usd": $is15 ? $total * 1.43 : $total}
                 )
                 """,
             ),
@@ -593,6 +594,8 @@ class GrokVideoNode(IO.ComfyNode):
     ) -> IO.NodeOutput:
         if image is None and model == "grok-imagine-video-1.5":
             raise ValueError(f"The '{model}' model requires an input image; connect one to the 'image' input.")
+        if resolution == "1080p" and model != "grok-imagine-video-1.5":
+            raise ValueError(f"1080p resolution is only available for grok-imagine-video-1.5, not '{model}'.")
         image_url = None
         if image is not None:
             if get_number_of_images(image) != 1:
@@ -630,7 +633,7 @@ class GrokVideoEditNode(IO.ComfyNode):
         return IO.Schema(
             node_id="GrokVideoEditNode",
             display_name="Grok Video Edit",
-            category="video/partner/Grok",
+            category="partner/video/Grok",
             description="Edit an existing video based on a text prompt.",
             inputs=[
                 IO.Combo.Input("model", options=["grok-imagine-video"]),
@@ -708,7 +711,7 @@ class GrokVideoReferenceNode(IO.ComfyNode):
         return IO.Schema(
             node_id="GrokVideoReferenceNode",
             display_name="Grok Reference-to-Video",
-            category="video/partner/Grok",
+            category="partner/video/Grok",
             description="Generate video guided by reference images as style and content references.",
             inputs=[
                 IO.String.Input(
@@ -841,7 +844,7 @@ class GrokVideoExtendNode(IO.ComfyNode):
         return IO.Schema(
             node_id="GrokVideoExtendNode",
             display_name="Grok Video Extend",
-            category="video/partner/Grok",
+            category="partner/video/Grok",
             description="Extend an existing video with a seamless continuation based on a text prompt.",
             inputs=[
                 IO.String.Input(

comfy_api_nodes/nodes_hitpaw.py

@@ -71,7 +71,7 @@ class HitPawGeneralImageEnhance(IO.ComfyNode):
         return IO.Schema(
             node_id="HitPawGeneralImageEnhance",
             display_name="HitPaw General Image Enhance",
-            category="image/partner/HitPaw",
+            category="partner/image/HitPaw",
             description="Upscale low-resolution images to super-resolution, eliminate artifacts and noise. "
             f"Maximum output: {MAX_MP_GENERATIVE} megapixels.",
             inputs=[
@@ -201,7 +201,7 @@ class HitPawVideoEnhance(IO.ComfyNode):
         return IO.Schema(
             node_id="HitPawVideoEnhance",
             display_name="HitPaw Video Enhance",
-            category="video/partner/HitPaw",
+            category="partner/video/HitPaw",
             description="Upscale low-resolution videos to high resolution, eliminate artifacts and noise. "
             "Prices shown are per second of video.",
             inputs=[