7073a93653
* [Partner Nodes] feat: add Krea 2 Medium Turbo model (#14280)
* [Partner Nodes] feat: add seed input to Flux Erase node (#14283)
Signed-off-by: bigcat88 <bigcat88@icloud.com>
* chore: update workflow templates to v0.9.98 (#14284)
* Bump comfyui-frontend-package to 1.45.15 (#14265)
* Fix ideogram if model dtype gets set to fp8. (#14291)
* Consolidate audio nodes into SaveAudioAdvanced node (CORE-202) (#13871)
* Enable cfg1 optimization for DualModelGuider with CFGGuider (#14290)
* Enable cfg1 optimization for DualModelGuider
* Fix CFG Override tooltip
* Fix interoperation with external source of pinned memory pressure (#14252)
* mm: split off registration helper to doer and headroom calc
* pinned_memory: implement registration comfy side
Move away from Aimdo buffer registrations which seem fraught with
danger and do it comfy side. Just start with the basic move.
* pinned_memory: do registrations as portable memory
* pinned_memory: discard async errors on registration fail
Like the good ol days.
* pinned_memory: implement abs shortfall retry
If pinned registration happens to fail despite the previous budget
ensures, consider the allocation shortfall, ensure it again, and
try again. This allows comfy pins to interoperate with other software
that might be doing substantive pinning.
* aimdo 049 (#14300)
* [Partner Nodes] feat: add new Gemini text node (#14299)
* [Partner Nodes] feat: add temperature and top_p to NanoBanan node (#14305)
* feat: add PreviewGaussianSplat + PreviewPointCloud nodes (#14194)
* Update AMD portable readme. (#14303)
* BE-1172 fix(3d): save Preview3DAdvanced / PreviewGaussianSplat / PreviewPointCloud to temp/, rename viewport input (#14294)
* feat(3d): reorder Preview3DAdvanced / PreviewGaussianSplat / PreviewPointCloud inputs and outputs (#14308)
* Update line endings check to ignore .ci files. (#14319)
* Use windows line endings for windows portable readmes. (#14334)
* Add SeedVR2 support (CORE-6) (#14110)
* chore: update embedded docs to v0.5.3 (#14350)
* Add Color primitive (#14260)
* Improve ResolutionSelector (#14309)
* feat(assets): extract image dimensions at ingest and emit on asset responses (#13991)
* feat(assets): extract image dimensions at ingest and emit on asset responses
Image assets now carry width/height under the existing `metadata` field on
asset responses, shaped as `{"kind": "image", "width": W, "height": H}`.
This lets consumers get original dimensions (e.g. for clients that render
server-side thumbnails and can't recover them from naturalWidth/Height)
without an extra round-trip.
Dimensions are written to AssetReference.system_metadata across three
ingest paths:
- Direct file ingest (upload, in-place registration): Pillow reads the
image header right after hashing, while the file is still in OS page
cache. Non-image MIME types are skipped without touching the file.
- From-hash registration: this path never reads the file bytes, so
dimensions are best-effort copied from any prior sibling reference of
the same asset that already carries kind=image metadata. Missing
siblings, non-image siblings, or absent dimension keys leave the new
reference's metadata unchanged.
- Scanner enrichment: extends the existing system_metadata write in
enrich_asset so scanner-registered images get the same treatment as
uploaded ones.
Existing system_metadata keys (e.g. safetensors fields written by the
enricher, download provenance) are preserved through merge. Existing
assets ingested before this change retain their current metadata — no
automatic backfill in this PR.
Tests cover image emission, non-image no-op, merge preservation, and the
from-hash sibling back-fill (including the no-sibling and non-image-sibling
cases).
* fix(assets): validate sibling dimensions before backfilling
Per CodeRabbit review on #13991: the previous loop accepted any sibling
with `kind == "image"` and copied whichever dimension keys happened to
be present, then returned. A partial sibling (kind set but missing or
invalid width/height) could persist incomplete metadata onto the new
reference even when a later sibling had valid dimensions.
Now we validate that the sibling has both width and height as positive
integers before adopting its dimensions, and continue scanning to the
next sibling otherwise.
* fix(assets): reject booleans in sibling dimension validation (use type-is)
Per CodeRabbit follow-up on #13991: bool is a subclass of int in Python,
so isinstance(True, int) is True. The previous strict-int gate would
have accepted width=True (truthy + > 0) as a valid dimension.
Realistic occurrence is low (extract_image_dimensions returns proper
ints, JSON doesn't serialize bools as numbers), but the validation gate
exists for defense-in-depth so it should be actually strict.
---------
Co-authored-by: guill <jacob.e.segal@gmail.com>
* Revert "Add SeedVR2 support (CORE-6) (#14110)" (#14359)
This reverts commit 7863cf0e53.
* chore(openapi): sync shared API contract from cloud@5273c30 (#14266)
* fix: Add back apply_rotary_emb for Qwen Image (#14364)
* Allow custom templates with Ideogram4 TE (#14374)
* main/server: Add --debug-hang (#14371)
Add an option to debug a hang with ctrl-C, dumping the backtraces to
see where its stuck or slow.
* Add LoRA key mapping for LTXV/LTXAV models (#14349)
* feat: Add model support for SCAIL-2 (#14373)
* initial SCAIL2 support
* Move bg_removal_model input socket to first position for nicer display (#14353)
* mm: dont reset cast buffers in cleanup_models_gc() (#14372)
cleanup_models_gc can be called once per load_models_gpu via
free_memory, which in turn can de-activate an active model via
this reset_cast_buffers.
cleanup_models_gc() could also come via obscure garbage collector
paths so limit reset_cast_buffers to the post-node callsite instead.
* Ensure conditions are not trainable to avoid bugs (#14368)
* feat: Add Bernini-R model support (Wan video) (CORE-279) (#14216)
* Depth anything 3 (Core-135) (#13853)
Co-authored-by: Alexis Rolland <alexisrolland@hotmail.com>
* Always enable cuda malloc on cu130 and higher. (#14381)
* chore(openapi): sync shared API contract from cloud@ca12913 (#14367)
* [Trainer/bug] Ensure model is not inference mode (CORE-72) (#13400)
* Ensure model is not inference mode
* force clone inside training mode to avoid inference tensor
* Allow force deepcopy for model patcher
* chore(assets): drop vestigial tags.tag_type column (#14248)
tag_type was always "user" in practice — no code path ever set it to anything
else (no system/seeded classification was wired up) and nothing queried it. The
column, its ix_tags_tag_type index, and the TagUsage.type API field were dead
weight, so they're removed. Adds alembic migration 0004 to drop the column and
index.
Verified: asset-seeder tests pass; migration applies cleanly on a fresh SQLite
(tags retains only name; tag_type column + index dropped).
Co-authored-by: guill <jacob.e.segal@gmail.com>
* feat(assets): cursor-based pagination on GET /api/assets (#14014)
* spec(assets): add cursor pagination params to GET /api/assets
Add 'after' query param and 'next_cursor' response field for keyset
pagination. Matches the cloud Go implementation (BE-893) so frontend
sees a unified contract across runtimes. Offset/limit remain as a
deprecated fallback.
* feat(assets): add cursor encode/decode helpers for keyset pagination
Port of cloud common/pagination/cursor.go. Wire format is base64url of
{"s", "v", "id"} JSON; times are Unix microseconds UTC to match
PostgreSQL timestamp precision.
Includes a byte-identity fixture pinned against the cloud Go wire
format so cross-runtime FE pagination can't silently drift.
* feat(assets): thread cursor through schemas, service, and query layer
list_assets_page accepts an opaque 'after' cursor and returns
next_cursor when more pages are available. The query applies a keyset
WHERE clause and a secondary ORDER BY id for deterministic tiebreak.
Cursor sort field is validated against the request sort, and a
last_access_time sort (OSS-only) falls back to offset/limit. Offset is
ignored whenever a cursor is supplied.
* feat(assets): wire cursor pagination through GET /api/assets handler
Adds integration tests for: full cursor walk, invalid-cursor 400,
sort/cursor mismatch 400, cursor-wins-over-offset, absent next_cursor
when no more results, and pagination stability across deletes.
* fix(assets): address cursor-review verified findings
- Mint next_cursor on every cursor-supported sort, not only when 'after'
was supplied. A first request (no 'after') previously returned
next_cursor=None, leaving cursor mode unreachable from a clean start.
- Over-fetch limit+1 so an exactly-full terminal page doesn't mint a
spurious cursor pointing at a phantom next page.
- Map crafted out-of-range microsecond cursors (OverflowError / OSError
in datetime construction) to 400 INVALID_CURSOR instead of leaking 500.
- Bump MAX_CURSOR_VALUE_LENGTH 256 -> 512 to match the AssetReference
name column max; without this, a long-named asset minted a cursor the
same server then refused on the next request. Cross-runtime byte
identity with cloud is unaffected because no cloud cursor ever carries
a value > 256 (cloud schema doesn't permit it).
- Return None from _encode_next_cursor when the boundary row carries a
NULL sort value (e.g. an Asset without size_bytes backfilled), instead
of silently encoding 0 and mis-positioning the keyset.
- Fix schemas_in.py comment so it matches actual handler behavior
(last_access_time + 'after' raises 400, does not fall back).
- Add AssetsApiError schema + 400 response to GET /api/assets in
openapi.yaml so generated clients know the INVALID_CURSOR envelope.
- Extend integration coverage: first-page mint, exact-multiple terminal
page, cursor walks for created_at/updated_at/size sorts, datetime
overflow surfaces as 400 not 500.
- Add unit coverage for datetime overflow and 512-char round-trip.
* feat(assets): bind cursor to sort order + Go-compat JSON escaping
Address three needs-judgment items from the cursor-review judge synthesis:
1. Cursor wire format now includes an "o" key carrying the sort
direction ("asc" / "desc") it was minted under. A request that
replays the cursor with a flipped `order` parameter is rejected
with 400 INVALID_CURSOR instead of silently walking the wrong
direction. Legacy cursors without "o" still decode (the binding
is best-effort until cloud mirrors the field — follow-up filed
separately).
2. JSON serialization now escapes `<`, `>`, `&`, U+2028, U+2029
to mirror Go's default `json.Marshal` behavior. Without this, an
asset name containing those characters produced different bytes on
Python vs cloud Go. The escaped form is what both runtimes emit.
3. Add direct query-layer tests for the keyset tiebreaker — the secondary
ORDER BY id branch was previously unexercised. Two scenarios: all
rows share a primary sort value, and mixed ties straddle page
boundaries. Both assert no row is dropped or duplicated across the
walk.
Wire-format note: Python cursors now differ from current cloud cursors
by exactly the "o" key. Cloud follow-up will bring the two back into
byte alignment.
* fix(assets): address bot review comments
- Soften offset param prose: it's not deprecated, just not preferred for
sequential walks. Random-access UIs (jump-to-page, item count displays)
legitimately still want offset, so dropping the 'deprecated' framing
rather than promoting it to a machine-readable deprecated:true flag.
- Add explicit HTTP status assertions before every json() / next_cursor
read in test_list_cursor.py so a failing request surfaces as an HTTP
error instead of a confusing KeyError on a 4xx/5xx body.
* feat(assets): require cursor o field, drop legacy permissive path
Cursor pagination hasn't shipped on either runtime yet — this PR is
still draft and cloud's mirror is just behind it — so there are no
legacy no-o cursors in the wild. Make o mandatory from day one
rather than landing permissive and tightening later.
decode_cursor now rejects any payload without o (or with a non-string
o) as malformed. CursorPayload.order becomes a required str. Tests
that constructed CursorPayload directly now pass order="desc";
test_legacy_cursor_without_order_accepted flips to
test_cursor_without_order_rejected.
* chore(assets): drop cross-repo prose from cursor comments
Strip prose references to sibling Go implementations and external
ticket IDs from cursor.py, the cursor tests, the keyset integration
tests, asset_management's sort-field comment, and the legacy
prompt_id alias comment. Pure docstring/comment scrub — no behavior
or wire-format changes. x-runtime: [cloud] field annotations in
openapi.yaml are unchanged; those are the spec's structural
cross-runtime convention, not internal references.
* test(assets): include 'o' in microsecond-boundary cursor payload
The boundary test was building a cursor without the required `o` key, so
decode failed on the missing-order branch before reaching the µs-overflow
path the test is asserting. Both paths return 400 INVALID_CURSOR so the
assertion passed for the wrong reason. Add `o` to the payload and matching
`order=` to the request so the decode reaches the intended branch.
* fix(assets): address ultrareview findings on cursor pagination
Six fact-checked findings from the multi-model review pass:
- Encoder/decoder length asymmetry: encode_cursor now rejects empty id,
oversized id (>128), oversized value (>512), and invalid order tokens
symmetrically with decode_cursor. Prevents the same server from minting
a cursor it then 400s on the next request (e.g. a filesystem-scanned
asset name >512 chars). The bad-order path now raises InvalidCursorError
(still subclasses ValueError) so route-layer handling stays uniform.
- Raw U+2028/U+2029 in cursor.py source: ripgrep treated those lines as
line-terminators, confirming the bytes were the actual separators. Any
editor save / autoformat / git tooling that normalizes invisibles would
silently break the encoder. Replaced with explicit
/
Python escape sequences.
- set(seen) == set(names) hid ordering regressions: a cursor walk that
dropped a row at a page boundary or returned duplicates could pass.
Reworked the assertion to (1) reject duplicates, (2) require full
coverage, and (3) assert strict positional order for size sort, the
only field with a clock-independent ordering.
- Flaky time.sleep(0.05) between inserts: Windows CI clock resolution is
~15ms, so back-to-back inserts under load could collide and exercise
the tiebreaker instead of the documented path. Removed the sleep and
let the strengthened assertion above carry coverage / no-duplicates,
with size sort carrying strict order.
- Cursor error envelope diverged from the rest of routes.py: cursor 400s
emitted {error: {code, message}} while every other 400 in the file
emits {error: {code, message, details}} via _build_error_response.
Switched to _build_error_response and added the details field to the
AssetsApiError schema in openapi.yaml.
- "Byte-identity fixtures" only checked substring containment, defeating
the test class's stated purpose of pinning the wire format. Switched
to exact-bytes equality against an inline expected payload string per
fixture, so any whitespace / key-order / escape drift fails loudly.
Also dropped Go / json.Marshal references from docstrings — the byte
format is the contract, not the runtime that mints it.
* fix(assets): cap cursors by encoded wire size, not just char count
Char-count guards on value/id can still let multibyte or escape-heavy
inputs blow past MAX_ENCODED_CURSOR_LENGTH once UTF-8 + escape expansion
+ base64url runs. A 512-character name of 'é' (2 bytes UTF-8) or '<'
(serializes to the 6-byte '<' escape) passes the char check, mints
a ~1500-byte cursor, then 400s when handed back on the next request.
Compute the final encoded form and reject it before returning if it
exceeds the wire cap. Adds regression tests for both inflation paths.
* refactor(assets): extract cursor JSON escaping helper; size wire cap above per-field caps
Addresses review feedback on cursor.py:
- Extract the inline escape chain into _apply_wire_compatible_json_escapes()
with a comment pinning it to the wire format's escape set, so the parity
intent is explicit rather than reading as an ad-hoc transform.
- Raise MAX_ENCODED_CURSOR_LENGTH to 8192 (comfortably above the ~5.2KB
worst-case the per-field caps can produce) and drop the mint-time length
guard. Encoder/decoder symmetry now holds by construction: the encoder
can't produce a cursor the decode path rejects, so there is no confusing
user-visible 'cursor too long' failure at mint time.
- Rewrite the two over-wire-cap tests to assert worst-case multibyte and
escape-heavy values mint and round-trip, instead of being rejected.
* refactor(assets): drop cross-runtime cursor escaping; cursors are opaque
The custom JSON escaping of <, >, &, U+2028, and U+2029 existed only to
keep the encoded cursor byte-identical with the Cloud implementation of
the same payload format. Cursors are opaque tokens, so byte-level
compatibility across implementations is not needed — plain json.dumps
output is sufficient. Remove the escaping helper and the byte-identity
test fixtures that pinned the wire format; keep round-trip coverage for
the affected characters.
---------
Co-authored-by: guill <jacob.e.segal@gmail.com>
* fix(assets): remove unused delete_content param from deleteAsset (#14241)
* fix(assets): remove unused delete_content param from deleteAsset
The delete_content query param on DELETE /api/assets/{id} was introduced
in #12125 and had its default flipped to false in #12621. In practice no
client sends it: the frontend issues a bare DELETE /assets/{id}, so every
real caller already gets the default soft-delete (the reference is hidden,
content preserved). The only thing that set delete_content=true was this
repo's own test teardown.
Remove the param from the route and the OpenAPI spec so the contract
matches what clients actually use (and lines up with the cloud surface).
The route now always soft-deletes. The underlying delete_asset_reference
helper keeps its delete_content_if_orphan option, so orphan reclamation
remains available internally for a future GC path — it's just no longer
exposed on the public endpoint. Tests that used delete_content=true for
hard cleanup now soft-delete; test_delete_upon_reference_count asserts
content preservation instead of orphan removal.
* test/docs: address review on deleteAsset delete_content removal
- Rename test_delete_upon_reference_count ->
test_soft_delete_preserves_asset_identity_across_references; the old name
implied last-ref cleanup, but it now verifies the opposite (soft delete
preserves identity across references).
- Strengthen the re-association assertion: also check asset_hash == src_hash
so it proves content reuse rather than relying on the now-tautological
created_new is False.
- Document delete_asset_reference: the orphan-reclamation branch is
intentionally internal-only; the public endpoint always soft-deletes.
- Normalize the soft-delete comment phrasing.
* test(assets): make seed content unique per test for isolation
Removing the delete_content param means delete is always a soft delete, so
content created by one test now survives into the next. The suite had been
relying on hard-delete teardown for isolation, so shared fixed-content
fixtures started colliding: seeded_asset (b"A"*4096) and
make_asset_bytes (deterministic on name) produced the same hash every test,
so the second seed deduped to the surviving asset and returned 200 instead
of 201, cascading into ~14 failures/errors.
Salt both fixtures with a per-test uuid so each test creates fresh content
(created_new True, 201), while keeping content deterministic within a test
(same name/size -> same bytes) and preserving exact byte length so size-based
list/sort assertions are unaffected.
* main: force cudnn.benchmark to false (#14390)
Some custom nodes try to set this true globally. It messes with dynamic
VRAM with one-off spikes that can OOM but this is also very high risk
for windows where such allocations might get serviced by shared memory
fallback.
Trump it.
* feat(assets): add job_ids filter to GET /api/assets (#13998)
* feat(assets): add job_ids filter to GET /api/assets
Mirrors the existing cloud `job_ids` query param on the local Python server:
clients can pass a comma-separated list (or repeated query params) of UUIDs
to filter assets by their associated job.
The `AssetReference.job_id` column already exists, so no migration is
needed — this just plumbs the filter through schema → service → query.
Marks the parameter as available in both runtimes by dropping the
`[cloud-only]` description prefix and the `x-runtime: [cloud]` tag from
the OpenAPI spec, per the OSS field-drift convention (absent runtime tag
= populated by both local and cloud).
* fix(assets): tighten job_ids — array schema, max_length, narrow except
From cursor-reviews on the parent commit:
- OpenAPI: declare job_ids as `type: array, items: string format: uuid`
with `style: form, explode: true` so it matches the documented
contract (and matches sibling include_tags/exclude_tags shape).
Description now states both accepted shapes explicitly.
- Schema: cap `job_ids` at 500 entries (max_length on the Pydantic
field) so a client can't splice an unbounded list into the IN clauses.
- Schema: drop `AttributeError` from the except — `raw` only contains
`str` items by construction, so `uuid.UUID(<str>)` raises `ValueError`
exclusively; the second clause was dead code.
* fix(assets): tighten job_ids validator + add schema-level tests
Aligns with the parallel hardening from draft PR #13848 (now closed as
a duplicate). The validator now:
- Raises ValueError on non-string list items (was: silently dropped).
- Raises ValueError on non-string / non-list top-level values like dict
or int (was: silently passed through to Pydantic's downstream coercion).
Adds tests-unit/assets_test/queries/test_list_assets_query.py covering
the validator end-to-end: CSV canonicalization, dedup order, default
empty, invalid UUID, non-string list item, non-string non-list value,
and the max_length=500 boundary.
* feat(prompt): enforce canonical UUID prompt_id at job creation
POST /prompt previously accepted any client-supplied prompt_id verbatim,
str()-coercing even non-strings, and minting the literal job id "None"
for an explicit JSON null. The new GET /api/assets job_ids filter matches
stored job ids as canonical UUIDs exactly, so a non-UUID id minted a job
whose assets could never be filtered.
- validate_job_id (comfy_execution/jobs.py): requires a string in the
canonical lowercase hyphenated UUID form; raises ValueError otherwise,
including parseable-but-non-canonical spellings (uppercase, braced, URN,
bare hex), which would otherwise be silently rewritten and then miss
every exact-match lookup downstream (history keys, websocket
correlation, /interrupt, the assets job_ids filter).
- POST /prompt: absent or null prompt_id means the server mints uuid4;
invalid means 400 invalid_prompt_id on the standard error envelope.
- openapi.yaml: document the request-side prompt_id (format uuid,
nullable) on PromptRequest.
- tests: unit matrix for validate_job_id; integration tests against the
booted server covering rejection, acceptance, and null handling.
---------
Co-authored-by: guill <jacob.e.segal@gmail.com>
* feat(assets): include asset id in executed WebSocket message (#13862)
* feat(assets): enrich executed WS message with asset metadata
When --enable-assets is set, each file-type output entry in the
`executed` WebSocket message now includes id, name, asset_hash, size,
and mime_type — matching the shape already returned by /upload/image.
The enrichment lives in comfy_execution/asset_enrichment.py (no torch
dependency) and is called from both send sites in execution.py: freshly
executed nodes register the file inline via register_file_in_place;
cached node re-sends look up the existing AssetReference by file path
to avoid re-hashing. Errors are caught per-entry so a failure never
blocks the WS message from sending.
* fix(assets): inject only id in executed WS message per Asset Identity RFC
Per the Asset Identity RFC, the executed WebSocket payload should carry
id alone — hash is already encoded in the filename, and name/preview_url/
size belong behind GET /api/assets/{id} rather than being pushed eagerly.
Simplifies the DB lookup path: we only need ref.id, so the asset.hash
null-check is no longer required as a fallback trigger.
* fix(assets): reject path traversal when resolving output abs_path
Subfolder/filename were joined and absolutized without containment check,
so '..' segments or an absolute filename could escape the type's base
directory and register an unrelated on-disk file as an asset.
Add commonpath-based containment check; skip enrichment (warn, leave
entry unchanged) when the resolved path escapes base. Catches ValueError
from cross-drive paths on Windows.
* docs(assets): drop Asset Identity RFC reference from docstring
* docs(assets): trim docstring to what enrichment does, not what it doesn't
* test(assets): use real platform paths so containment check works on Windows
The previous test setup patched os.path.abspath to identity and used a
POSIX-style '/output' base, which collided with Windows path separators
in os.path.commonpath. Drop the abspath/join patches and use a real
tempdir-rooted base so the containment check runs against actual
platform paths.
* refactor(assets): enrich at output-processing time, not in the WS send path
Per review: enrichment lived inside the client_id-guarded send sites, so a
headless run (no websocket client) never registered assets at all, and
ui_outputs/history stored the un-enriched entries.
Now output_ui is enriched once, right after the node produces it and before
it is stored in ui_outputs — so registration happens regardless of connected
clients, and the asset id flows into history and the execution cache for
free. _send_cached_ui re-sends the stored (already-enriched) dict verbatim,
which lets the DB-lookup-by-path fallback be deleted: every enrichment is
now a fresh output, and register_file_in_place re-hashes on upsert so an
overwritten path can never carry a stale id.
* revert(assets): drop job_ids filter from GET /api/assets (#14408)
The job_ids query filter added in #13998 has no live consumer: the
frontend Generated tab kept sourcing from GET /jobs, and the cloud side
removed its equivalent filter from the shared asset spec. Carrying it on
the local server only re-introduces Core<->Cloud drift on the shared
contract, so remove it to match.
Removed: the job_ids field + validator on ListAssetsQuery, the IN(...)
clauses in list_references_page, the service/route passthrough, and the
filter-only tests.
Kept: the canonical-UUID prompt_id enforcement at job creation (also
landed in #13998). It stands on its own -- job ids are matched verbatim
by history keys, websocket correlation, and /interrupt -- and cloud
inherits it by running core for execution, so no divergence is created.
* chore(openapi): sync shared API contract from cloud@e3c52ad (#14406)
* I don't think this actually works anymore. (#14403)
* ops: tolerate already force casted dynamic weight (#14410)
Some custom nodes .to weights completely out of load context which
can wreak havoc if its for a model that is not active. Detect this
condition and just let it fall-through to the non-dynamic loader
straight up.
---------
Signed-off-by: bigcat88 <bigcat88@icloud.com>
Co-authored-by: Alexander Piskun <13381981+bigcat88@users.noreply.github.com>
Co-authored-by: Daxiong (Lin) <contact@comfyui-wiki.com>
Co-authored-by: Comfy Org PR Bot <snomiao+comfy-pr@gmail.com>
Co-authored-by: comfyanonymous <121283862+comfyanonymous@users.noreply.github.com>
Co-authored-by: Alexis Rolland <alexisrolland@hotmail.com>
Co-authored-by: Jukka Seppänen <40791699+kijai@users.noreply.github.com>
Co-authored-by: rattus <46076784+rattus128@users.noreply.github.com>
Co-authored-by: Terry Jia <terryjia88@gmail.com>
Co-authored-by: John Pollock <pollockjj@users.noreply.github.com>
Co-authored-by: Silver <65376327+silveroxides@users.noreply.github.com>
Co-authored-by: Matt Miller <mattmiller@comfy.org>
Co-authored-by: guill <jacob.e.segal@gmail.com>
Co-authored-by: kelseyee <971704395@qq.com>
Co-authored-by: Kohaku-Blueleaf <59680068+KohakuBlueleaf@users.noreply.github.com>
Co-authored-by: Talmaj <Talmaj@users.noreply.github.com>
29 KiB
ComfyUI
The most powerful and modular AI engine for content creation.
ComfyUI is the AI creation engine for visual professionals who demand control over every model, every parameter, and every output. Its powerful and modular node graph interface empowers creatives to generate images, videos, 3D models, audio, and more...
- ComfyUI natively supports the latest open-source state of the art models.
- API nodes provide access to the best closed source models such as Nano Banana, Seedance, Hunyuan3D, etc.
- It is available on Windows, Linux, and macOS, locally with our desktop application, our portable install or on our cloud.
- The most sophisticated workflows can be exposed through a simple UI thanks to App Mode.
- It integrates seamlessly into production pipelines with our API endpoints.
Get Started
Local
Desktop Application
- The easiest way to get started.
- Available on Windows & macOS.
Windows Portable Package
- Get the latest commits and completely portable.
- Available on Windows.
Manual Install
Supports all operating systems and GPU types (NVIDIA, AMD, Intel, Apple Silicon, Ascend).
Cloud
Comfy Cloud
- Our official paid cloud version for those who can't afford local hardware.
Examples
See what ComfyUI can do with the newer template workflows or old example workflows.
Features
- Nodes/graph/flowchart interface to experiment and create complex Stable Diffusion workflows without needing to code anything.
- NOTE: There are many more models supported than the list below, if you want to see what is supported see our templates list inside ComfyUI.
- Image Models
- SD1.x, SD2.x (unCLIP)
- SDXL, SDXL Turbo
- Stable Cascade
- SD3 and SD3.5
- Pixart Alpha and Sigma
- AuraFlow
- HunyuanDiT
- Flux
- Lumina Image 2.0
- HiDream
- Qwen Image
- Hunyuan Image 2.1
- Flux 2
- Z Image
- Ernie Image
- Image Editing Models
- Video Models
- Audio Models
- 3D Models
- Asynchronous Queue system
- Many optimizations: Only re-executes the parts of the workflow that changes between executions.
- Smart memory management: can automatically run large models on GPUs with as low as 1GB vram with smart offloading.
- Works even if you don't have a GPU with:
--cpu(slow) - Can load ckpt and safetensors: All in one checkpoints or standalone diffusion models, VAEs and CLIP models.
- Safe loading of ckpt, pt, pth, etc.. files.
- Embeddings/Textual inversion
- Loras (regular, locon and loha)
- Hypernetworks
- Loading full workflows (with seeds) from generated PNG, WebP and FLAC files.
- Saving/Loading workflows as Json files.
- Nodes interface can be used to create complex workflows like one for Hires fix or much more advanced ones.
- Area Composition
- Inpainting with both regular and inpainting models.
- ControlNet and T2I-Adapter
- Upscale Models (ESRGAN, ESRGAN variants, SwinIR, Swin2SR, etc...)
- GLIGEN
- Model Merging
- LCM models and Loras
- Latent previews with TAESD
- Works fully offline: core will never download anything unless you want to.
- Optional API nodes to use paid models from external providers through the online Comfy API disable with:
--disable-api-nodes - Config file to set the search paths for models.
Workflow examples can be found on the Examples page
Release Process
ComfyUI follows a weekly release cycle targeting Monday but this regularly changes because of model releases or large changes to the codebase. There are three interconnected repositories:
-
- Releases a new major stable version (e.g., v0.7.0) roughly every 2 weeks.
- Starting from v0.4.0 patch versions will be used for fixes backported onto the current stable release.
- Minor versions will be used for releases off the master branch.
- Patch versions may still be used for releases on the master branch in cases where a backport would not make sense.
- Commits outside of the stable release tags may be very unstable and break many custom nodes.
- Serves as the foundation for the desktop release
-
- Builds a new release using the latest stable core version
-
- Every 2+ weeks frontend updates are merged into the core repository
- Features are frozen for the upcoming core release
- Development continues for the next release cycle
Shortcuts
| Keybind | Explanation |
|---|---|
Ctrl + Enter |
Queue up current graph for generation |
Ctrl + Shift + Enter |
Queue up current graph as first for generation |
Ctrl + Alt + Enter |
Cancel current generation |
Ctrl + Z/Ctrl + Y |
Undo/Redo |
Ctrl + S |
Save workflow |
Ctrl + O |
Load workflow |
Ctrl + A |
Select all nodes |
Alt + C |
Collapse/uncollapse selected nodes |
Ctrl + M |
Mute/unmute selected nodes |
Ctrl + B |
Bypass selected nodes (acts like the node was removed from the graph and the wires reconnected through) |
Delete/Backspace |
Delete selected nodes |
Ctrl + Backspace |
Delete the current graph |
Space |
Move the canvas around when held and moving the cursor |
Ctrl/Shift + Click |
Add clicked node to selection |
Ctrl + C/Ctrl + V |
Copy and paste selected nodes (without maintaining connections to outputs of unselected nodes) |
Ctrl + C/Ctrl + Shift + V |
Copy and paste selected nodes (maintaining connections from outputs of unselected nodes to inputs of pasted nodes) |
Shift + Drag |
Move multiple selected nodes at the same time |
Ctrl + D |
Load default graph |
Alt + + |
Canvas Zoom in |
Alt + - |
Canvas Zoom out |
Ctrl + Shift + LMB + Vertical drag |
Canvas Zoom in/out |
P |
Pin/Unpin selected nodes |
Ctrl + G |
Group selected nodes |
Q |
Toggle visibility of the queue |
H |
Toggle visibility of history |
R |
Refresh graph |
F |
Show/Hide menu |
. |
Fit view to selection (Whole graph when nothing is selected) |
| Double-Click LMB | Open node quick search palette |
Shift + Drag |
Move multiple wires at once |
Ctrl + Alt + LMB |
Disconnect all wires from clicked slot |
Ctrl can also be replaced with Cmd instead for macOS users
Installing
Windows Portable
There is a portable standalone build for Windows that should work for running on Nvidia GPUs or for running on your CPU only on the releases page.
Direct link to download
Simply download, extract with 7-Zip or with the windows explorer on recent windows versions and run. For smaller models you normally only need to put the checkpoints (the huge ckpt/safetensors files) in: ComfyUI\models\checkpoints but many of the larger models have multiple files. Make sure to follow the instructions to know which subfolder to put them in ComfyUI\models\
If you have trouble extracting it, right click the file -> properties -> unblock
The portable above currently comes with python 3.13 and pytorch cuda 13.0. Update your Nvidia drivers if it doesn't start.
All Official Portable Downloads:
Portable for Nvidia GPUs (supports 20 series and above).
Portable for Nvidia GPUs with pytorch cuda 12.6 and python 3.12 (Supports Nvidia 10 series and older GPUs).
How do I share models between another UI and ComfyUI?
See the Config file to set the search paths for models. In the standalone windows build you can find this file in the ComfyUI directory. Rename this file to extra_model_paths.yaml and edit it with your favorite text editor.
comfy-cli
You can install and start ComfyUI using comfy-cli:
pip install comfy-cli
comfy install
Manual Install (Windows, Linux)
Python 3.14 works but some custom nodes may have issues. The free threaded variant works but some dependencies will enable the GIL so it's not fully supported.
Python 3.13 is very well supported. If you have trouble with some custom node dependencies on 3.13 you can try 3.12
torch 2.4 and above is supported but some features and optimizations might only work on newer versions. We generally recommend using the latest major version of pytorch with the latest cuda version unless it is less than 2 weeks old.
Instructions:
Git clone this repo.
Put your SD checkpoints (the huge ckpt/safetensors files) in: models/checkpoints
Put your VAE in: models/vae
AMD GPUs (Linux)
AMD users can install rocm and pytorch with pip if you don't have it already installed, this is the command to install the stable version:
pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/rocm7.2
This is the command to install the nightly with ROCm 7.2 which might have some performance improvements:
pip install --pre torch torchvision torchaudio --index-url https://download.pytorch.org/whl/nightly/rocm7.2
AMD GPUs (Experimental: Windows and Linux), RDNA 3, 3.5 and 4 only.
These have less hardware support than the builds above but they work on windows. You also need to install the pytorch version specific to your hardware.
RDNA 3 (RX 7000 series):
pip install --pre torch torchvision torchaudio --index-url https://rocm.nightlies.amd.com/v2/gfx110X-all/
RDNA 3.5 (Strix halo/Ryzen AI Max+ 365):
pip install --pre torch torchvision torchaudio --index-url https://rocm.nightlies.amd.com/v2/gfx1151/
RDNA 4 (RX 9000 series):
pip install --pre torch torchvision torchaudio --index-url https://rocm.nightlies.amd.com/v2/gfx120X-all/
Intel GPUs (Windows and Linux)
Intel Arc GPU users can install native PyTorch with torch.xpu support using pip. More information can be found here
- To install PyTorch xpu, use the following command:
pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/xpu
This is the command to install the Pytorch xpu nightly which might have some performance improvements:
pip install --pre torch torchvision torchaudio --index-url https://download.pytorch.org/whl/nightly/xpu
NVIDIA
Nvidia users should install stable pytorch using this command:
pip install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cu130
This is the command to install pytorch nightly instead which might have performance improvements.
pip install --pre torch torchvision torchaudio --index-url https://download.pytorch.org/whl/nightly/cu132
Troubleshooting
If you get the "Torch not compiled with CUDA enabled" error, uninstall torch with:
pip uninstall torch
And install it again with the command above.
Dependencies
Install the dependencies by opening your terminal inside the ComfyUI folder and:
pip install -r requirements.txt
After this you should have everything installed and can proceed to running ComfyUI.
Others:
Apple Mac silicon
You can install ComfyUI in Apple Mac silicon (M1 or M2) with any recent macOS version.
- Install pytorch nightly. For instructions, read the Accelerated PyTorch training on Mac Apple Developer guide (make sure to install the latest pytorch nightly).
- Follow the ComfyUI manual installation instructions for Windows and Linux.
- Install the ComfyUI dependencies. If you have another Stable Diffusion UI you might be able to reuse the dependencies.
- Launch ComfyUI by running
python main.py
Note
: Remember to add your models, VAE, LoRAs etc. to the corresponding Comfy folders, as discussed in ComfyUI manual installation.
Ascend NPUs
For models compatible with Ascend Extension for PyTorch (torch_npu). To get started, ensure your environment meets the prerequisites outlined on the installation page. Here's a step-by-step guide tailored to your platform and installation method:
- Begin by installing the recommended or newer kernel version for Linux as specified in the Installation page of torch-npu, if necessary.
- Proceed with the installation of Ascend Basekit, which includes the driver, firmware, and CANN, following the instructions provided for your specific platform.
- Next, install the necessary packages for torch-npu by adhering to the platform-specific instructions on the Installation page.
- Finally, adhere to the ComfyUI manual installation guide for Linux. Once all components are installed, you can run ComfyUI as described earlier.
Cambricon MLUs
For models compatible with Cambricon Extension for PyTorch (torch_mlu). Here's a step-by-step guide tailored to your platform and installation method:
- Install the Cambricon CNToolkit by adhering to the platform-specific instructions on the Installation
- Next, install the PyTorch(torch_mlu) following the instructions on the Installation
- Launch ComfyUI by running
python main.py
Iluvatar Corex
For models compatible with Iluvatar Extension for PyTorch. Here's a step-by-step guide tailored to your platform and installation method:
- Install the Iluvatar Corex Toolkit by adhering to the platform-specific instructions on the Installation
- Launch ComfyUI by running
python main.py
ComfyUI-Manager
ComfyUI-Manager is an extension that allows you to easily install, update, and manage custom nodes for ComfyUI.
Setup
-
Install the manager dependencies:
pip install -r manager_requirements.txt -
Enable the manager with the
--enable-managerflag when running ComfyUI:python main.py --enable-manager
Command Line Options
| Flag | Description |
|---|---|
--enable-manager |
Enable ComfyUI-Manager |
--enable-manager-legacy-ui |
Use the legacy manager UI instead of the new UI (requires --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) |
Running
python main.py
For AMD cards not officially supported by ROCm
Try running it with this command if you have issues:
For 6700, 6600 and maybe other RDNA2 or older: HSA_OVERRIDE_GFX_VERSION=10.3.0 python main.py
For AMD 7600 and maybe other RDNA3 cards: HSA_OVERRIDE_GFX_VERSION=11.0.0 python main.py
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.
Notes
Only parts of the graph that have an output with all the correct inputs will be executed.
Only parts of the graph that change from each execution to the next will be executed, if you submit the same graph twice only the first will be executed. If you change the last part of the graph only the part you changed and the part that depends on it will be executed.
Dragging a generated png on the webpage or loading one will give you the full workflow including seeds that were used to create it.
You can use () to change emphasis of a word or phrase like: (good code:1.2) or (bad code:0.8). The default emphasis for () is 1.1. To use () characters in your actual prompt escape them like \( or \).
You can use {day|night}, for wildcard/dynamic prompts. With this syntax "{wild|card|test}" will be randomly replaced by either "wild", "card" or "test" by the frontend every time you queue the prompt. To use {} characters in your actual prompt escape them like: \{ or \}.
Dynamic prompts also support C-style comments, like // comment or /* comment */.
To use a textual inversion concepts/embeddings in a text prompt put them in the models/embeddings directory and use them in the CLIPTextEncode node like this (you can omit the .pt extension):
embedding:embedding_filename.pt
How to show high-quality previews?
Use --preview-method auto to enable previews.
The default installation includes a fast latent preview method that's low-resolution. To enable higher-quality previews with TAESD, download the taesd_decoder.pth, taesdxl_decoder.pth, taesd3_decoder.pth and taef1_decoder.pth and place them in the models/vae_approx folder. Once they're installed, restart ComfyUI and launch it with --preview-method taesd to enable high-quality previews.
How to use TLS/SSL?
Generate a self-signed certificate (not appropriate for shared/production use) and key by running the command: openssl req -x509 -newkey rsa:4096 -keyout key.pem -out cert.pem -sha256 -days 3650 -nodes -subj "/C=XX/ST=StateName/L=CityName/O=CompanyName/OU=CompanySectionName/CN=CommonNameOrHostname"
Use --tls-keyfile key.pem --tls-certfile cert.pem to enable TLS/SSL, the app will now be accessible with https://... instead of http://....
Note: Windows users can use alexisrolland/docker-openssl or one of the 3rd party binary distributions to run the command example above.
If you use a container, note that the volume mount-vcan be a relative path so... -v ".\:/openssl-certs" ...would create the key & cert files in the current directory of your command prompt or powershell terminal.
Support and dev channel
Discord: Try the #help or #feedback channels.
Matrix space: #comfyui_space:matrix.org (it's like discord but open source).
See also: https://www.comfy.org/
psst — we're hiring! Help build ComfyUI: comfy.org/careers
Frontend Development
As of August 15, 2024, we have transitioned to a new frontend, which is now hosted in a separate repository: ComfyUI Frontend. The compiled JS files (from TS/Vue) are published to pypi and installed as a dependency in ComfyUI.
Reporting Issues and Requesting Features
For any bugs, issues, or feature requests related to the frontend, please use the ComfyUI Frontend repository. This will help us manage and address frontend-specific concerns more efficiently.
Using the Latest Frontend
The new frontend is now the default for ComfyUI. However, please note:
- The frontend in the main ComfyUI repository is updated fortnightly.
- Daily releases are available in the separate frontend repository.
To use the most up-to-date frontend version:
-
For the latest daily release, launch ComfyUI with this command line argument:
--front-end-version Comfy-Org/ComfyUI_frontend@latest -
For a specific version, replace
latestwith the desired version number:--front-end-version Comfy-Org/ComfyUI_frontend@1.2.2
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.