5154 Commits

This Branch

This Branch

All Branches

Author	SHA1	Message	Date
Alexander Piskun	6917bce128	[Partner Nodes] add Gpt 5.5 and 5.5-pro LLM models (#13673) ... * feat(api-nodes): add Gpt 5.5 and 5.5-pro LLM models Signed-off-by: bigcat88 <bigcat88@icloud.com>	2026-05-05 16:53:19 +03:00
Alexander Piskun	c55ff85243	feat(api-nodes): add Luma UNI-1 models (#13614) ... Signed-off-by: bigcat88 <bigcat88@icloud.com> Co-authored-by: Alexis Rolland <alexisrolland@hotmail.com>	2026-05-05 16:49:07 +03:00
Alvin Tang	8d75211300	fix: SplitImageToTileList and ImageMergeTileList to use tile_height for vertical stride minimum (#12882)	2026-05-05 20:29:11 +08:00
Talmaj	fed8d5efa6	feat: Auto-regressive video generation (CORE-25) (#13082)	2026-05-04 21:01:22 -07:00
comfyanonymous	9aef025fb0	Document core release frequency is now ~2 weeks. (#13710)	2026-05-04 20:45:48 -07:00
Jedrzej Kosinski	e758594e3b	Add deploy environment header (Comfy-Env) to partner node API calls (#13425)	2026-05-04 20:17:56 -07:00
Jedrzej Kosinski	ae457da84b	feat: add generic --feature-flag CLI arg and --list-feature-flags registry (#13685)	2026-05-04 19:50:26 -07:00
Matt Miller	413e250ccd	spec: add workflow_id / workflow_version_id to PromptRequest with x-runtime tag (#13709) ... Adds two optional, nullable UUID fields to PromptRequest for runtimes that wrap workflow execution in a workflow-version entity (the hosted-cloud runtime does this; local ComfyUI does not). Both fields are tagged `x-runtime: [cloud]` to mark them as runtime-specific — local ComfyUI returns `null` (or omits them entirely) and that's correct behavior, not drift. ## Why these fields belong in the OSS spec Hosted-cloud's frontend and backend share `openapi.yaml` as their single source of truth via auto-generated client types. Without the fields declared in the spec, the cloud runtime has to either: 1. Hand-edit a vendored copy of openapi.yaml (drift between vendor and upstream — unsustainable). 2. Maintain a separate cloud-only spec file (forks the contract, defeats the point of a shared OSS spec). Both options have been tried and both produce maintenance pain. The shape that scales is: cloud-only fields live in OSS spec under their intended path, declared nullable, with an explicit `x-runtime` tag so local-only readers can ignore them programmatically and human readers can see what each runtime populates. ## About the `x-runtime` extension This is the first use of `x-runtime` in this spec. Convention: - `x-runtime: [cloud]` — only the hosted-cloud runtime populates the field; local returns null or omits. - `x-runtime: [local]` — only local populates; cloud returns null. - Tag absent — both runtimes populate the field (the default). This is a vendor extension (`x-` prefix) and is ignored by spec validators that don't recognize it, including `kin-openapi`. Local clients reading the spec see two extra optional nullable fields, which is forward-compatible with all existing readers. ## What this does not change - No Python code changes. `PromptRequest` already accepts arbitrary optional fields (`extra_data: additionalProperties: true` on the same schema is a stronger guarantee). The Python server already silently accepts and ignores both fields today. - No required-fields change. Both fields stay outside `required`, so older clients that don't know about them keep validating. - No nullability widening on existing fields. ## Verification - YAML parses (`yaml.safe_load`). - `kin-openapi` `loader.LoadFromFile` accepts the modified spec. - `openapi3filter.ValidateRequest` on a PromptRequest with both fields set to `null`, set to a valid UUID, or omitted — all pass.	2026-05-04 18:59:48 -07:00
Matt Miller	35819e35a8	fix(spec): mark DeviceStats.index and NodeInfo.essentials_category as nullable (#13706) ... * fix(spec): mark DeviceStats.index and NodeInfo.essentials_category as nullable Two fields in openapi.yaml are declared as required/non-nullable but the Python implementation legitimately returns `null` for them, so any client that response-validates against the spec will fail. `DeviceStats.index` (used by GET /api/system_stats): - server.py emits `"index": device.index` unconditionally - For the CPU device (--cpu mode), `torch.device("cpu").index` is `None` - → JSON response includes `"index": null` for CPU devices `NodeInfo.essentials_category` (used by GET /api/object_info): - The V3 schema-based path (comfy_api/latest/_io.py:1654) unconditionally passes `essentials_category=self.essentials_category` into NodeInfoV1 and serializes via dataclasses.asdict(), so the key is always present - Schema's `essentials_category` defaults to `None` for nodes that don't set it in `define_schema` (e.g. the APG node) - → JSON response includes `"essentials_category": null` for those nodes - (The V1 path in server.py uses `hasattr` and so omits the key entirely when not set, but the V3 path is the one that produces nulls) Both fields keep their existing `required` status — they're always present in the response, the value is just nullable. Descriptions expanded to spell out when `null` is expected. * docs(spec): clarify essentials_category presence rules The previous description said "null for nodes that don't set ESSENTIALS_CATEGORY (V1)" — that's wrong. server.py:739-740 uses `hasattr` and OMITS the key when the V1 attribute isn't defined; null only happens if the attribute is explicitly set to None. Spell out all three legal shapes (string / null / absent) and which path produces which.	2026-05-04 18:28:21 -07:00
Alexis Rolland	15a4494a4e	chore: Update display names and categories (CORE-151) (#13693) ... * Standardize DEPRECATED label in node display name * Promote category image/video to root level video/ * Update images and masks names and categories	2026-05-04 17:37:25 -07:00
rattus	1265955b34	ops: handle multi-compute of the same weight (#13705) ... If the same weight is used multiple times within the same prefetch window, it should only apply compute state mutations once. Mark the weight as fully resident on the first pass accordingly.	2026-05-04 16:40:57 -07:00
rattus	1ac78180b3	make control-net load order deterministic (#13701) ... Make this deterministic so speeds dont change base of load order. Load them in reverse order so whatever the caller lists first is the top priority.	2026-05-04 12:58:06 -07:00
rattus	c47633f3be	prefetch: guard against no offload (#13703) ... cast_ will return no stream if there is no work to do. guard against this is the consume logic.	2026-05-04 12:56:05 -07:00
Jukka Seppänen	c33d26c283	fix: Proper memory estimation for frame interpolation when not using dynamic VRAM (#13698)	2026-05-04 20:20:40 +03:00
Soof Golan	f3ea976cba	Fix a1111 typo in extra_model_paths.yaml (#2720)	2026-05-04 16:01:46 +08:00
Alexis Rolland	5538f62b0b	fix: Update ColorTransfer node ref_image to be mandatory (#13691)	2026-05-04 12:33:11 +08:00
Jedrzej Kosinski	2806163f6e	Default control_after_generate to fixed in PrimitiveInt node (#13690)	2026-05-04 07:21:34 +08:00
comfyanonymous	cea8d0925f	Refactor LoadImageMask to use LoadImage code. (#13687)	2026-05-03 16:18:27 -04:00
Silver	b138133ffa	Enable triton comfy kitchen via cli-arg (#12730)	2026-05-03 14:07:21 -04:00
Jukka Seppänen	025e6792ee	Batch broadcasting in JoinImageWithAlpha node (#13686) ... * Batch broadcasting in JoinImageWithAlpha node	2026-05-03 16:30:00 +03:00
Luke Mino-Altherr	867b8d2408	fix: gracefully handle port-in-use error on server startup (#13001) ... Catch EADDRINUSE OSError when binding the TCP site and exit with a clear error message instead of an unhandled traceback.	2026-05-03 20:44:20 +08:00
Alexis Rolland	d0f0b15cf5	Update ComfyUI screenshot in README (#13683) ... Update ComfyUI screenshot to showcase a more modern workflow	2026-05-03 18:48:58 +08:00
Alexis Rolland	b5bb83c964	Fix issue blend images with alpha (#13615) ... Make ImageBlend and ImageCompositeMasked nodes handle images with different channel counts	2026-05-03 18:17:08 +08:00
Alexis Rolland	f6d5068ac0	Update README (#13679) ... Updated the README to include a new screenshot, improved description and add Ernie Image to supported models.	2026-05-03 12:20:17 +08:00
Jukka Seppänen	be95871adc	feat: Gemma4 text generation support (CORE-30) (#13376) ... * initial gemma4 support * parity with reference implementation outputs can 100% match transformers with same sdpa flags, checkpoint this and then optimize * Cleanup, video fixes * cleanup, enable fused rms norm by default * update comment * Cleanup * Update sd.py * Various fixes * Add fp8 scaled embedding support * small fixes * Translate think tokens * Fix image encoder attention mask type So it works with basic attention * Handle thinking tokens different only for Gemma4 * Code cleanup * Update nodes_textgen.py * Use embed scale class instead of buffer Slight difference to HF, but technically more accurate and simpler code * Default to fused rms_norm * Update gemma4.py	2026-05-02 22:46:15 -04:00
Alexander Piskun	f756d801a1	[Partner Nodes] Topaz Astra 2 model (#13672) ... * feat(api-nodes): add Topaz Astra 2 model Signed-off-by: bigcat88 <bigcat88@icloud.com> * feat(api-nodes): make Astra 2 the default Topaz upscaler model Reorder UPSCALER_MODELS_MAP and the upscaler_model dynamic combo so "Astra 2" appears first, surfacing it as the default selection. --------- Signed-off-by: bigcat88 <bigcat88@icloud.com> Co-authored-by: Marwan Mostafa <marawan206@gmail.com>	2026-05-02 19:29:00 -07:00
Daxiong (Lin)	1d23a875ed	chore: update workflow templates to v0.9.68 (#13678)	2026-05-03 10:06:55 +08:00
comfyanonymous	ef6722f6be	Some cleanups to the load image node. (#13677)	2026-05-02 20:34:27 -04:00
rattus	783782d5d7	Implement block prefetch + Lora Async load + and adopt in LTX (Speedup!) (CORE-111) (#13618) ... * mm: Use Aimdo raw allocator for cast buffers pytorch manages allocation of growing buffers on streams poorly. Pyt has no windows support for the expandable segments allocator (which is the right tool for this job), while also segmenting the memory by stream such that it can be generally re-used. So kick the problem to aimdo which can just grow a virtual region thats freed per stream. * plan * ops: move cpu handler up to the caller * ops: split up prefetch from weight prep block prefetching API Split up the casting and weight formating/lora stuff in prep for arbitrary prefetch support. * ops: implement block prefetching API allow a model to construct a prefetch list and operate it for increased async offload. * ltxv2: Implement block prefetching * Implement lora async offload Implement async offload of loras.	2026-05-02 19:23:24 -04:00
comfyanonymous	3e3ed8cc2a	Add script in AMD portable to launch with dynamic vram. (#13667)	2026-05-01 20:19:46 -04:00
comfyanonymous	67f6cb3527	List all the portable downloads in the README section. (#13666)	2026-05-01 20:19:32 -04:00
Alexis Rolland	0230e0e7cc	Adding kijai (#13664) ... Co-authored-by: Jedrzej Kosinski <kosinkadink1@gmail.com>	2026-05-02 06:37:18 +08:00
Jukka Seppänen	b5921c8ac2	SDPose: resize fix (#13656)	2026-05-01 14:17:25 -07:00
Simon Lui	63103d519e	Remove IPEX and clean up checks and add missing synchronize during empty cache. (#13653)	2026-05-01 14:16:41 -07:00
Alexander Piskun	cf758bd256	chore(api-nodes): increase default timeout for partner API node tasks (#13663) ... Signed-off-by: bigcat88 <bigcat88@icloud.com> Co-authored-by: Jedrzej Kosinski <kosinkadink1@gmail.com>	2026-05-01 12:48:41 -07:00
Daxiong (Lin)	10b45a71cd	chore: update workflow templates to v0.9.66 (#13662) ... Co-authored-by: Jedrzej Kosinski <kosinkadink1@gmail.com>	2026-05-01 12:11:30 -07:00
Alexander Piskun	fa7553138e	chore(api-nodes): remove Moonvalley API nodes (#13659) ... Signed-off-by: bigcat88 <bigcat88@icloud.com>	2026-05-01 11:09:25 -07:00
Talmaj	cf9cbec596	Reformat models variable into multiline array CORE-59 (#13513) ... Co-authored-by: Talmaj Marinc <talmaj@comfy.org>	2026-05-01 17:20:11 +08:00
Alexander Piskun	96f1cee9f5	chore(api-nodes): always display the custom width and height in GPTImage2 node (#13651) ... Signed-off-by: bigcat88 <bigcat88@icloud.com>	2026-04-30 23:15:11 -07:00
Jedrzej Kosinski	97f58baaaf	Add alexisrolland and rattus128 as code owners (#13648)	2026-04-30 21:49:31 -04:00
Daxiong (Lin)	e8e8fee224	chore: update workflow templates to v0.9.65 (#13644)	2026-04-30 18:14:28 -07:00
Rainer	e9c311b245	OneTainer ERNIE LoRA support (#13640)	2026-04-30 19:33:41 -04:00
comfyanonymous	e6e0936128	Load other jpeg formats without taking so much memory. (#13642)	2026-04-30 19:33:09 -04:00
Alexander Piskun	b633244635	[Partner Nodes] ByteDance: virtual portrait library for regular images (#13638) ... * feat(api-nodes-bytedance): use the virtual portrait library for regular images Signed-off-by: bigcat88 <bigcat88@icloud.com> * fix: include shape in image dedup hash Signed-off-by: bigcat88 <bigcat88@icloud.com> --------- Signed-off-by: bigcat88 <bigcat88@icloud.com>	2026-04-30 11:49:08 -07:00
Alexander Piskun	38ecad8f8a	feat(api-nodes): allow custom resolutions for GPTImage2 node (#13631) ... Signed-off-by: bigcat88 <bigcat88@icloud.com>	2026-04-30 01:09:33 -07:00
Jedrzej Kosinski	a7d82baa06	Fix SQLAlchemy version format in requirements.txt (#13547) ... Change SQLAlchemy>=2.0 to SQLAlchemy>=2.0.0 to satisfy the X.Y.Z version format expected by install_util.is_valid_version().	2026-04-29 23:30:01 -04:00
comfyanonymous	d10fc2d652	Lower peak mem usage for 8 bit formats with pyav. (#13626)	2026-04-29 23:05:31 -04:00
blepping	a164c82913	Add high quality preview support for Flux2 latents (#13496)	2026-04-29 19:37:30 -04:00
Talmaj	5eeae3f1d8	Cogvideox (#13402) ... --------- Co-authored-by: kijai <40791699+kijai@users.noreply.github.com> Co-authored-by: Talmaj Marinc <talmaj@comfy.org>	2026-04-29 19:30:08 -04:00
Jukka Seppänen	0e25a6936e	Reduce video tiny VAE peak VRAM and decode time (CORE-127) (#13617) ... * Update taehv.py * Simplify * Simplify pixel_unshuffle dispatch	2026-04-29 12:15:10 -07:00