Commit Graph

4552 Commits

Author SHA1 Message Date
12918a5f78 chore: update workflow templates to v0.8.7 (#11896) 2026-01-15 11:08:21 -08:00
8f40b43e02 ComfyUI v0.9.2 v0.9.2 2026-01-15 10:57:35 -05:00
3b832231bb Flux2 Klein support. (#11890) 2026-01-15 10:33:15 -05:00
be518db5a7 Remove extraneous clip missing warnings when loading LTX2 embeddings_connector weights (#11874) 2026-01-14 17:54:04 -05:00
80441eb15e utils: fix lanczos grayscale upscaling (#11873) 2026-01-14 17:53:16 -05:00
07f2462eae feat(api-nodes): add Meshy 3D nodes (#11843)
* feat(api-nodes): add Meshy 3D nodes

* rebased, added JSONata price badges
2026-01-14 11:25:38 -08:00
d150440466 Fix VAELoader (#11880) 2026-01-14 10:54:50 -08:00
6165c38cb5 Optimize nvfp4 lora applying. (#11866)
This changes results a bit but it also speeds up things a lot.
2026-01-14 00:49:38 -05:00
712cca36a1 feat: throttle ProgressBar updates to reduce WebSocket flooding (#11504) 2026-01-13 22:41:44 -05:00
ac4d8ea9b3 feat: add CI container version bump automation (#11692)
* feat: add CI container version bump automation

Adds a workflow that triggers on releases to create PRs in the
comfyui-ci-container repo, updating the ComfyUI version in the Dockerfile.

Supports both release events and manual workflow dispatch for testing.

* feat: add CI container version bump automation

Adds a workflow that triggers on releases to create PRs in the
comfyui-ci-container repo, updating the ComfyUI version in the Dockerfile.

Supports both release events and manual workflow dispatch for testing.

* ci: update CI container repository owner

* refactor: rename `update-ci-container.yaml` workflow to `update-ci-container.yml`

* Remove post-merge instructions from the CI container update workflow.
2026-01-13 22:39:22 -05:00
c9196f355e Fix scale_shorter_dimension portrait check (#11862) 2026-01-13 18:25:09 -08:00
7eb959ce93 fix: update ComfyUI repo reference to Comfy-Org/ComfyUI (#11858) 2026-01-13 21:03:16 -05:00
469dd9c16a Adds crop to multiple mode to ResizeImageMaskNode. (#11838)
* Add crop-to-multiple resize mode

* Make scale-to-multiple shape handling explicit
2026-01-13 16:48:10 -08:00
eff2b9d412 Optimize nvfp4 lora applying. (#11856) 2026-01-13 19:37:19 -05:00
15b312de7a Optimize nvfp4 lora applying. (#11854) 2026-01-13 19:23:58 -05:00
1419047fdb [Api Nodes]: Improve Price Badge Declarations (#11582)
* api nodes: price badges moved to nodes code

* added price badges for 4 more node-packs

* added price badges for 10 more node-packs

* added new price badges for Omni STD mode

* add support for autogrow groups

* use full names for "widgets", "inputs" and "groups"

* add strict typing for JSONata rules

* add price badge for WanReferenceVideoApi node

* add support for DynamicCombo

* sync price badges changes (https://github.com/Comfy-Org/ComfyUI_frontend/pull/7900)

* sync badges for Vidu2 nodes

* fixed incorrect price for RecraftCrispUpscaleNode

* fixed incorrect price badges for LTXV nodes

* fixed price badge for MinimaxHailuoVideoNode

* fixed price badges for PixVerse nodes
2026-01-13 16:18:28 -08:00
79f6bb5e4f add blueprints dir for built-in blueprints (#11853) 2026-01-13 16:14:40 -08:00
e4b4fb3479 Load metadata on VAELoader (#11846)
Needed to load the proper LTX2 VAE if separated from checkpoint
2026-01-13 17:37:21 -05:00
d9dc02a7d6 Support "lite" version of alibaba-pai Z-Image Controlnet (#11849)
* reduced number of control layers (3) compared to full model
2026-01-13 15:03:53 -05:00
c543ad81c3 fix(api-nodes-gemini): raise exception when no candidates due to safety block (#11848) 2026-01-13 08:30:13 -08:00
5ac1372533 ComfyUI v0.9.1 v0.9.1 2026-01-13 01:44:06 -05:00
1dcbd9efaf Bump ltxav mem estimation a bit. (#11842) 2026-01-13 01:42:07 -05:00
db9e6edfa1 ComfyUI v0.9.0 v0.9.0 2026-01-13 01:23:31 -05:00
8af13b439b Update requirements.txt (#11841) 2026-01-13 01:22:25 -05:00
acd0e53653 Make bulk_ops not use .returning to be compatible with python 3.10 and 3.11 sqlalchemy (#11839) 2026-01-13 00:15:24 -05:00
117e7a5853 Refactor to try to lower mem usage. (#11840) 2026-01-12 21:01:52 -08:00
b3c0e4de57 Make loras work on nvfp4 models. (#11837)
The initial applying is a bit slow but will probably be sped up in the
future.
2026-01-12 22:33:54 -05:00
ecaeeb990d chore: update workflow templates to v0.8.4 (#11835) 2026-01-12 19:18:01 -08:00
c2b65e2fce Update workflow templates to v0.8.0 (#11828) 2026-01-12 17:29:25 -05:00
fd5c0755af Reduce LTX2 VRAM use by more efficient timestep embed handling (#11829) 2026-01-12 17:28:59 -05:00
c881a1d689 Support the siglip 2 naflex model as a clip vision model. (#11831)
Not useful yet.
2026-01-12 17:05:54 -05:00
a3b5d4996a Support ModelScope-Trainer DiffSynth lora for Z Image. (#11805) 2026-01-12 15:38:46 -05:00
c6238047ee Put more details about portable in readme. (#11816) 2026-01-11 21:11:53 -05:00
5cd1113236 fix(api-nodes): use a unique name for uploading audio files (#11778) 2026-01-11 03:07:11 -08:00
2f642d5d9b Fix chroma fp8 te being treated as fp16. (#11795) 2026-01-10 14:40:42 -08:00
cd912963f1 Fix issue with t5 text encoder in fp4. (#11794) 2026-01-10 17:31:31 -05:00
6e4b1f9d00 pythorch_attn_by_def_on_gfx1200 (#11793) 2026-01-10 16:51:05 -05:00
dc202a2e51 Properly save mixed ops. (#11772) 2026-01-10 02:03:57 -05:00
153bc524bf chore: update embedded docs to v0.4.0 (#11776) 2026-01-10 01:29:30 -05:00
393d2880dd feat(api-nodes): added nodes for Vidu2 (#11760) 2026-01-09 12:59:38 -08:00
4484b93d61 fix(api-nodes): do not downscale the input image for Topaz Enhance (#11768) 2026-01-09 12:25:56 -08:00
bd0e6825e8 Be less strict when loading mixed ops weights. (#11769) 2026-01-09 14:21:06 -05:00
ec0a832acb Add workaround for hacky nodepack(s) that edit folder_names_and_paths to have values with tuples of more than 2. Other things could potentially break with those nodepack(s), so I will hunt for the guilty nodepack(s) now. (#11755) 2026-01-08 22:49:12 -08:00
04c49a29b4 feat: add cancelled filter to /jobs (#11680) 2026-01-08 21:57:36 -08:00
4609fcd260 add node - image compare (#11343) 2026-01-08 21:31:19 -08:00
6207f86c18 Fix VAEEncodeForInpaint to support WAN VAE tuple downscale_ratio (#11572)
Use vae.spacial_compression_encode() instead of directly accessing
downscale_ratio to handle both standard VAEs (int) and WAN VAEs (tuple).

Addresses reviewer feedback on PR #11259.

Co-authored-by: ChrisFab16 <christopher@fabritius.dk>
2026-01-08 23:34:48 -05:00
1dc3da6314 Add most basic Asset support for models (#11315)
* 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
2026-01-08 22:21:51 -05:00
114fc73685 Bump comfyui-frontend-package to 1.36.13 (#11645) 2026-01-08 22:16:15 -05:00
b48d6a83d4 Fix csp error in frontend when forcing offline. (#11749) 2026-01-08 22:15:50 -05:00
027042db68 Add node: JoinAudioChannels (#11728) 2026-01-08 22:14:06 -05:00