* [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>
* memory_management: Add direct to read GPU mode
Make destination optional (or make it optionally GPU) and use aimdo
to file_read direct to GPU.
* ops: Remove stream pin buffers and use aimdo reads
This consumed too much RAM and its better to just take the hit on
the CPU syncing back the stream on a short ring buffer. Aimdo
implements this so just rip the stream pin buffer from comfy.
* model_management: all active pin registration movement
Its better to just let the active model load past the pin limit as
pins and let the pins move around. The saves the HDD and SATA
people disk traffic while only costing a few GPU syncs.
* utils: use aimdo file handle
This opens on windows with more favourable flags
* mp: only count the model proper for loaded_ram and vram
Exclude live loras from the numbers to avoid the case where the reported
loaded memory exceeds the size of the model.
This causes me confusion in the Kijai visualizer when it looked fully
loaded but was hitting disk due to this accounding disrepency.
* utils: add bit reverse utility
useful for max scattering something ordered.
* pinned_memory: Implement offload balancing
Use a max scatter alogorithm to prioritize pins of the same size such
that when doing a little bit of offloading it gets scattered, allowing
the prefetcher to more evenly swollow the offload.
* comfy-aimdo 0.4.7
Aimdo 0.4.7 implement VRAM buffer exhaustion predection to avoid
early speculative load of weights that definately wont fix once the
inference gets further in.
* model-prefetch: consolidate pin ensures on the sync point
This could happen mid prefetch block, cause a sync of the entire
block and lose overlap. Get ahead of the problem with a free down
at the natural compute stream sync point.
* mm: Put a 2GB min on the pin ceiling
This is reasonably bad if it starts causing swap pressure, moreso than
during normal ram-cache proceedings. Clamp it.
* add --fast-disk
Use the RAM right up to the wire as the community is bit accustomed too.
This trades off headroom for the case where large chunky intermediates
arrive and potenitally hits pagefile/swap, but a lot of people have
"it just fits" workflows out there, so strike a compromise with
75->90%.
Disable the incative cache for all but the very high RAM users.
* model_management: disable non-dynamic smart memory
Disable smart memory outright for non dynamic models.
This is a minor step towards deprecation of --disable-dynamic-vram
and the legacy ModelPatcher.
This is needed for estimate-free model development, where new models
can opt-out of supplying a memory estimate and not have to worry
about hard VRAM allocations due to legacy non-dynamic model patchers
This is also a general stability increase for a lot of stray use cases
where estimates may still be off and going forward we are not going
to accurately maintain such estimates.
* pinned_memory: implement with aimdo growable buffer
Use a single growable buffer so we can do threaded pre-warming on
pinned memory.
* mm: use aimdo to do transfer from disk to pin
Aimdo implements a faster threaded loader.
* Add stream host pin buffer for AIMDO casts
Introduce per-offload-stream HostBuffer reuse for pinned staging,
include it in cast buffer reset synchronization.
Defer actual casts that go via this pin path to a separate pass
such that the buffer can be allocated monolithically (to avoid
cudaHostRegister thrash).
* remove old pin path
* Implement JIT pinned memory pressure
Replace the predictive pin pressure mechanism with JIT PIN memory
pressure.
* LowVRAMPatch: change to two-phase visit
* lora: re-implement as inplace swiss-army-knife operation
* prepare for multiple pin sets
* implement pinned loras
* requirements: comfy-aimdo 0.4.0
* ops: remove unused arg
This was defeatured in aimdo iteration
* ops: sync the CPU with only the offload stream activity
This was syncing with the offload stream which itself is synced with the
compute stream, so this was syncing CPU with compute transitively. Define
the event to sync it more gently.
* pins: implement freeing intermediate for pinned memory
Pinning is more important than inactive intermediates and the stream
pin buffer is more important than even active intermediates.
* execution: implement pin eviction on RAM presure
Add back proper pin freeing on RAM pressure
* implement pin registration swaps
Uncap the windows pins from 50% by extending the pool and have a pressure
mechanism to move the pin reservations om demand.
This unfortunately implies a GPU sync to do the freeing so significant
hysterisis needs to be added to consolidate these pressure events.
* cli_args/execution: Implement lower background cache-ram threshold
Limit the amount of RAM background intermediates can use, so that
switching workflows doesn't degrade performance too much.
* make default
* bump aimdo
* model-patcher: force-cast tiny weights
Flux 2 gets crazy stalls due to a mix of tiny and giant weights
creating lopsided steam buffer rotations which creates stalls.
* ops: refactor in prep for chunking
* mm: delegate pin-on-the-way to aimdo
Aimdo is able to chunk and slice this on the way for better CPU->GPU
overlap. The main advantage is the ability to shorten the bus contention
window between previous weight transfer and the next weights vbar
fault.
* bump aimdo
* pinning updates
* specify hostbuf max allocation size
There a signs of virtual memory exhaustion on some linux systems when
throwing 128GB for every little piece. Pass the actual to save aimdo
from over-estimates
* tests: update execution tests for caching
The default caching changed to ram-cache so update these tests
accordingly.
Remove the LRU 0 test as this also falls through to RAM cache.
This is an experimental WIP option that might not work in your workflow but
should lower memory usage if it does.
Currently only the VAE and the load image node will output in fp16 when
this option is turned on.
This was previously considering the pool of dynamic models as one giant
entity for the sake of smart memory, but that isnt really the useful
or what a user would reasonably expect. Make Dynamic VRAM properly purge
its models just like the old --disable-smart-memory but conditioning
the dynamic-for-dynamic bypass on smart memory.
Re-enable dynamic smart memory.
* Brought over minimal elements from PR 10045 to reproduce seed_assets and register_assets_system without adding anything to the DB or server routes yet, for now making everything sync (can introduce async once everything is cleaned up and brought over)
* Added db script to insert assets stuff, cleaned up some code; assets (models) now get added/rescanned
* Added support for 5 http endpoints for assets
* Replaced Optional with | None in schemas_in.py and schemas_out.py
* Remove two routes that will not be relevant yet in this PR: HEAD /api/assets/hash/<hash> and PUT /api/assets/<id>/preview
* Remove some functions the two deleted endpoints were using
* Don't show assets scan message upon calling /object_info endpoint
* removed unsued import to satisfy ruff
* Simplified hashing function tpye hint and _hash_file_obj
* Satisfied ruff
* execution: Roll the UI cache into the outputs
Currently the UI cache is parallel to the output cache with
expectations of being a content superset of the output cache.
At the same time the UI and output cache are maintained completely
seperately, making it awkward to free the output cache content without
changing the behaviour of the UI cache.
There are two actual users (getters) of the UI cache. The first is
the case of a direct content hit on the output cache when executing a
node. This case is very naturally handled by merging the UI and outputs
cache.
The second case is the history JSON generation at the end of the prompt.
This currently works by asking the cache for all_node_ids and then
pulling the cache contents for those nodes. all_node_ids is the nodes
of the dynamic prompt.
So fold the UI cache into the output cache. The current UI cache setter
now writes to a prompt-scope dict. When the output cache is set, just
get this value from the dict and tuple up with the outputs.
When generating the history, simply iterate prompt-scope dict.
This prepares support for more complex caching strategies (like RAM
pressure caching) where less than 1 workflow will be cached and it
will be desirable to keep the UI cache and output cache in sync.
* sd: Implement RAM getter for VAE
* model_patcher: Implement RAM getter for ModelPatcher
* sd: Implement RAM getter for CLIP
* Implement RAM Pressure cache
Implement a cache sensitive to RAM pressure. When RAM headroom drops
down below a certain threshold, evict RAM-expensive nodes from the
cache.
Models and tensors are measured directly for RAM usage. An OOM score
is then computed based on the RAM usage of the node.
Note the due to indirection through shared objects (like a model
patcher), multiple nodes can account the same RAM as their individual
usage. The intent is this will free chains of nodes particularly
model loaders and associate loras as they all score similar and are
sorted in close to each other.
Has a bias towards unloading model nodes mid flow while being able
to keep results like text encodings and VAE.
* execution: Convert the cache entry to NamedTuple
As commented in review.
Convert this to a named tuple and abstract away the tuple type
completely from graph.py.
* Change bf16 check and switch non-blocking to off default with option to force to regain speed on certain classes of iGPUs and refactor xpu check.
* Turn non_blocking off by default for xpu.
* Update README.md for Intel GPUs.
* feat: “--whitelist-custom-nodes” args for comfy core to go with “--disable-all-custom-nodes” for development purposes
* feat: Simplify custom nodes whitelist logic to use consistent code paths
* Add Ideogram generate node.
* Add staging api.
* Add API_NODE and common error for missing auth token (#5)
* Add Minimax Video Generation + Async Task queue polling example (#6)
* [Minimax] Show video preview and embed workflow in ouput (#7)
* Remove uv.lock
* Remove polling operations.
* Revert "Remove polling operations."
* Update stubs.
* Added Ideogram and Minimax back in.
* Added initial BFL Flux 1.1 [pro] Ultra node (#11)
* Add --comfy-api-base launch arg (#13)
* Add instructions for staging development. (#14)
* remove validation to make it easier to run against LAN copies of the API
* Manually add BFL polling status response schema (#15)
* Add function for uploading files. (#18)
* Add Luma nodes (#16)
* Refactor util functions (#20)
* Add VIDEO type (#21)
* Add rest of Luma node functionality (#19)
* Fix image_luma_ref not working (#28)
* [Bug] Remove duplicated option T2V-01 in MinimaxTextToVideoNode (#31)
* Add utils to map from pydantic model fields to comfy node inputs (#30)
* add veo2, bump av req (#32)
* Add Recraft nodes (#29)
* Add Kling Nodes (#12)
* Add Camera Concepts (luma_concepts) to Luma Video nodes (#33)
* Add Runway nodes (#17)
* Convert Minimax node to use VIDEO output type (#34)
* Standard `CATEGORY` system for api nodes (#35)
* Set `Content-Type` header when uploading files (#36)
* add better error propagation to veo2 (#37)
* Add Realistic Image and Logo Raster styles for Recraft v3 (#38)
* Fix runway image upload and progress polling (#39)
* Fix image upload for Luma: only include `Content-Type` header field if it's set explicitly (#40)
* Moved Luma nodes to nodes_luma.py (#47)
* Moved Recraft nodes to nodes_recraft.py (#48)
* Add Pixverse nodes (#46)
* Move and fix BFL nodes to node_bfl.py (#49)
* Move and edit Minimax node to nodes_minimax.py (#50)
* Add Minimax Image to Video node + Cleanup (#51)
* Add Recraft Text to Vector node, add Save SVG node to handle its output (#53)
* Added pixverse_template support to Pixverse Text to Video node (#54)
* Added Recraft Controls + Recraft Color RGB nodes (#57)
* split remaining nodes out of nodes_api, make utility lib, refactor ideogram (#61)
* Add types and doctstrings to utils file (#64)
* Fix: `PollingOperation` progress bar update progress by absolute value (#65)
* Use common download function in kling nodes module (#67)
* Fix: Luma video nodes in `api nodes/image` category (#68)
* Set request type explicitly (#66)
* Add `control_after_generate` to all seed inputs (#69)
* Fix bug: deleting `Content-Type` when property does not exist (#73)
* Add preview to Save SVG node (#74)
* change default poll interval (#76), rework veo2
* Add Pixverse and updated Kling types (#75)
* Added Pixverse Image to VIdeo node (#77)
* Add Pixverse Transition Video node (#79)
* Proper ray-1-6 support as fix has been applied in backend (#80)
* Added Recraft Style - Infinite Style Library node (#82)
* add ideogram v3 (#83)
* [Kling] Split Camera Control config to its own node (#81)
* Add Pika i2v and t2v nodes (#52)
* Temporary Fix for Runway (#87)
* Added Stability Stable Image Ultra node (#86)
* Remove Runway nodes (#88)
* Fix: Prompt text can't be validated in Kling nodes when using primitive nodes (#90)
* Fix: typo in node name "Stabiliy" => "Stability" (#91)
* Add String (Multiline) node (#93)
* Update Pika Duration and Resolution options (#94)
* Change base branch to master. Not main. (#95)
* Fix UploadRequest file_name param (#98)
* Removed Infinite Style Library until later (#99)
* fix ideogram style types (#100)
* fix multi image return (#101)
* add metadata saving to SVG (#102)
* Bump templates version to include API node template workflows (#104)
* Fix: `download_url_to_video_output` return type (#103)
* fix 4o generation bug (#106)
* Serve SVG files directly (#107)
* Add a bunch of nodes, 3 ready to use, the rest waiting for endpoint support (#108)
* Revert "Serve SVG files directly" (#111)
* Expose 4 remaining Recraft nodes (#112)
* [Kling] Add `Duration` and `Video ID` outputs (#105)
* Fix: datamodel-codegen sets string#binary type to non-existent `bytes_aliased` variable (#114)
* Fix: Dall-e 2 not setting request content-type dynamically (#113)
* Default request timeout: one hour. (#116)
* Add Kling nodes: camera control, start-end frame, lip-sync, video extend (#115)
* Add 8 nodes - 4 BFL, 4 Stability (#117)
* Fix error for Recraft ImageToImage error for nonexistent random_seed param (#118)
* Add remaining Pika nodes (#119)
* Make controls input work for Recraft Image to Image node (#120)
* Use upstream PR: Support saving Comfy VIDEO type to buffer (#123)
* Use Upstream PR: "Fix: Error creating video when sliced audio tensor chunks are non-c-contiguous" (#127)
* Improve audio upload utils (#128)
* Fix: Nested `AnyUrl` in request model cannot be serialized (Kling, Runway) (#129)
* Show errors and API output URLs to the user (change log levels) (#131)
* Fix: Luma I2I fails when weight is <=0.01 (#132)
* Change category of `LumaConcepts` node from image to video (#133)
* Fix: `image.shape` accessed before `image` is null-checked (#134)
* Apply small fixes and most prompt validation (if needed to avoid API error) (#135)
* Node name/category modifications (#140)
* Add back Recraft Style - Infinite Style Library node (#141)
* Fixed Kling: Check attributes of pydantic types. (#144)
* Bump `comfyui-workflow-templates` version (#142)
* [Kling] Print response data when error validating response (#146)
* Fix: error validating Kling image response, trying to use `"key" in` on Pydantic class instance (#147)
* [Kling] Fix: Correct/verify supported subset of input combos in Kling nodes (#149)
* [Kling] Fix typo in node description (#150)
* [Kling] Fix: CFG min/max not being enforced (#151)
* Rebase launch-rebase (private) on prep-branch (public copy of master) (#153)
* Bump templates version (#154)
* Fix: Kling image gen nodes don't return entire batch when `n` > 1 (#152)
* Remove pixverse_template from PixVerse Transition Video node (#155)
* Invert image_weight value on Luma Image to Image node (#156)
* Invert and resize mask for Ideogram V3 node to match masking conventions (#158)
* [Kling] Fix: image generation nodes not returning Tuple (#159)
* [Bug] [Kling] Fix Kling camera control (#161)
* Kling Image Gen v2 + improve node descriptions for Flux/OpenAI (#160)
* [Kling] Don't return video_id from dual effect video (#162)
* Bump frontend to 1.18.8 (#163)
* Use 3.9 compat syntax (#164)
* Use Python 3.10
* add example env var
* Update templates to 0.1.11
* Bump frontend to 1.18.9
---------
Co-authored-by: Robin Huang <robin.j.huang@gmail.com>
Co-authored-by: Christian Byrne <cbyrne@comfy.org>
Co-authored-by: thot experiment <94414189+thot-experiment@users.noreply.github.com>
This should speed up the lowvram mode a bit. It currently is only enabled when --async-offload is used but it will be enabled by default in the future if there are no problems.
* add dependency aware cache that removed a cached node as soon as all of its decendents have executed. This allows users with lower RAM to run workflows they would otherwise not be able to run. The downside is that every workflow will fully run each time even if no nodes have changed.
* remove test code
* tidy code
* Better argument handling of front-end-root
Improves handling of front-end-root launch argument. Several instances where users have set it and ComfyUI launches as normal and completely disregards the launch arg which doesn't make sense. Better to indicate to user that something is incorrect.
* Removed unused import
There was no real reason to use "Optional" typing in ther front-end-root argument.
The idea is that you can indicate how much quality vs speed you want.
At the moment:
--fast 2 enables fp16 accumulation if your pytorch supports it.
--fast 5 enables fp8 matrix mult on fp8 models and the optimization above.
--fast without a number enables all optimizations.
