doctorpangloss
ffbb2f7cd3
Fix bug in model_downloader
2025-09-18 14:47:28 -07:00
doctorpangloss
e6762bb82a
Use pylint dynamic member correctly
2025-09-18 13:42:05 -07:00
doctorpangloss
bc201cea4d
Improve tests, fix issues with alternate filenames, improve group offloading support for transformers models
2025-09-18 13:25:08 -07:00
doctorpangloss
79b8723f61
Various fixes
...
- Fix 16 bit exif saving for PNGs
- Validate alternative filenames correctly
- Improve speed of test workflows by setting steps to 1
2025-09-17 16:04:05 -07:00
Benjamin Berman
db546c4826
Sometimes progress messages of images with metadata are not valid. Need to investigate why.
2025-09-16 22:04:39 -07:00
doctorpangloss
7cd6383110
Fix distributed previews, add sageattention to the docker container
2025-09-12 11:48:25 -07:00
doctorpangloss
421c9b88ae
Fix import order
2025-09-10 16:36:03 -07:00
doctorpangloss
67432bee6c
Fix model measurements to call
2025-09-09 18:29:56 -07:00
doctorpangloss
537e34358f
Improve compatibility with custom nodes that want to support both LTS and vanilla ComfyUI
2025-09-09 17:54:49 -07:00
doctorpangloss
4f6f3e9197
Fix linting issues, improve HooksSupport dummy implementation
2025-09-09 13:26:46 -07:00
doctorpangloss
f5e29f0e61
Fix sage attention for qwen-image, fix Qwen Image VAE memory usage, improve compatibility with hooks when using KSampler based workflows and non-ModelPatcher model manageable-stuff
2025-09-09 12:58:23 -07:00
doctorpangloss
b62d4f05e1
more type documentation, fix installation with dependency group
2025-09-08 11:35:19 -07:00
doctorpangloss
a31e5f216d
Merge branch 'master' of github.com:comfyanonymous/ComfyUI
2025-09-04 14:31:14 -07:00
doctorpangloss
58622c7e91
Move validation back to where it is supposed to be relative to upstream
2025-09-04 14:05:19 -07:00
comfyanonymous
72855db715
Fix potential rope issue. ( #9710 )
2025-09-03 22:20:13 -04:00
doctorpangloss
6cffd4c4c2
Fix linting issue
2025-09-03 15:08:16 -07:00
doctorpangloss
0e5348b9a9
Fixes issues with running from a vanilla ComfyUI workspace and having this package installed ( fixes #30 )
2025-09-03 14:57:34 -07:00
doctorpangloss
8052d070de
Fix pylint issues
2025-09-03 12:13:35 -07:00
doctorpangloss
179c2d35c8
Merge branch 'master' of github.com:comfyanonymous/ComfyUI
2025-09-03 12:04:32 -07:00
comfyanonymous
e3018c2a5a
uso -> uxo/uno as requested. ( #9688 )
2025-09-02 16:12:07 -04:00
comfyanonymous
3412d53b1d
USO style reference. ( #9677 )
...
Load the projector.safetensors file with the ModelPatchLoader node and use
the siglip_vision_patch14_384.safetensors "clip vision" model and the
USOStyleReferenceNode.
2025-09-02 15:36:22 -04:00
contentis
e2d1e5dad9
Enable Convolution AutoTuning ( #9301 )
2025-09-01 20:33:50 -04:00
comfyanonymous
27e067ce50
Implement the USO subject identity lora. ( #9674 )
...
Use the lora with FluxContextMultiReferenceLatentMethod node set to "uso"
and a ReferenceLatent node with the reference image.
2025-09-01 18:54:02 -04:00
chaObserv
32a627bf1f
SEEDS: update noise decomposition and refactor ( #9633 )
...
- Update the decomposition to reflect interval dependency
- Extract phi computations into functions
- Use torch.lerp for interpolation
2025-08-31 00:01:45 -04:00
comfyanonymous
e80a14ad50
Support wan2.2 5B fun control model. ( #9611 )
...
Use the Wan22FunControlToVideo node.
2025-08-28 22:13:07 -04:00
comfyanonymous
4aa79dbf2c
Adjust flux mem usage factor a bit. ( #9588 )
2025-08-27 23:08:17 -04:00
Gangin Park
3aad339b63
Add DPM++ 2M SDE Heun (RES) sampler ( #9542 )
2025-08-27 19:07:31 -04:00
comfyanonymous
491755325c
Better s2v memory estimation. ( #9584 )
2025-08-27 19:02:42 -04:00
comfyanonymous
496888fd68
Improve s2v performance when generating videos longer than 120 frames. ( #9582 )
2025-08-27 16:06:40 -04:00
comfyanonymous
b5ac6ed7ce
Fixes to make controlnet type models work on qwen edit and kontext. ( #9581 )
2025-08-27 15:26:28 -04:00
Kohaku-Blueleaf
b20ba1f27c
Fix #9537 ( #9576 )
2025-08-27 12:45:02 -04:00
comfyanonymous
88aee596a3
WIP Wan 2.2 S2V model. ( #9568 )
2025-08-27 01:10:34 -04:00
doctorpangloss
1b7d04b2e7
Add types for PreviewImageWithMetadataMessage
2025-08-26 17:19:46 -07:00
doctorpangloss
726804ca63
Improve the way the execution context is initialized
2025-08-26 16:55:41 -07:00
doctorpangloss
479e20d233
Fix attention dispatch bug
2025-08-26 16:40:45 -07:00
doctorpangloss
173b1ce0ae
Add support for intuitive progress notifications when using comfyui as a library
2025-08-26 16:31:39 -07:00
doctorpangloss
35d890eafe
fix logging in extra_config
2025-08-26 15:11:49 -07:00
doctorpangloss
1e938f5feb
fix sdpa priorities
2025-08-26 14:33:00 -07:00
doctorpangloss
306fcbaa0e
audio_encoders now a package correctly, make imports relative
2025-08-26 14:12:40 -07:00
doctorpangloss
752caf013c
fix model upscaler, fix list iteration linting issue, fix samplers
2025-08-26 14:09:07 -07:00
doctorpangloss
443bb45eaf
Merge branch 'master' of github.com:comfyanonymous/ComfyUI
2025-08-26 13:59:45 -07:00
comfyanonymous
914c2a2973
Implement wav2vec2 as an audio encoder model. ( #9549 )
...
This is useless on its own but there are multiple models that use it.
2025-08-25 23:26:47 -04:00
comfyanonymous
41048c69b4
Fix Conditioning masks on 3d latents. ( #9506 )
2025-08-22 23:15:44 -04:00
Jedrzej Kosinski
fc247150fe
Implement EasyCache and Invent LazyCache ( #9496 )
...
* Attempting a universal implementation of EasyCache, starting with flux as test; I screwed up the math a bit, but when I set it just right it works.
* Fixed math to make threshold work as expected, refactored code to use EasyCacheHolder instead of a dict wrapped by object
* Use sigmas from transformer_options instead of timesteps to be compatible with a greater amount of models, make end_percent work
* Make log statement when not skipping useful, preparing for per-cond caching
* Added DIFFUSION_MODEL wrapper around forward function for wan model
* Add subsampling for heuristic inputs
* Add subsampling to output_prev (output_prev_subsampled now)
* Properly consider conds in EasyCache logic
* Created SuperEasyCache to test what happens if caching and reuse is moved outside the scope of conds, added PREDICT_NOISE wrapper to facilitate this test
* Change max reuse_threshold to 3.0
* Mark EasyCache/SuperEasyCache as experimental (beta)
* Make Lumina2 compatible with EasyCache
* Add EasyCache support for Qwen Image
* Fix missing comma, curse you Cursor
* Add EasyCache support to AceStep
* Add EasyCache support to Chroma
* Added EasyCache support to Cosmos Predict t2i
* Make EasyCache not crash with Cosmos Predict ImagToVideo latents, but does not work well at all
* Add EasyCache support to hidream
* Added EasyCache support to hunyuan video
* Added EasyCache support to hunyuan3d
* Added EasyCache support to LTXV (not very good, but does not crash)
* Implemented EasyCache for aura_flow
* Renamed SuperEasyCache to LazyCache, hardcoded subsample_factor to 8 on nodes
* Eatra logging when verbose is true for EasyCache
2025-08-22 22:41:08 -04:00
doctorpangloss
9fcc597e1f
Merge branch 'master' of github.com:comfyanonymous/ComfyUI
2025-08-22 18:29:55 -07:00
doctorpangloss
e84bf5f025
Fix downloads and tests on Linux
2025-08-22 18:29:12 -07:00
doctorpangloss
7ce781b0fd
Fix torch compile
2025-08-22 17:43:12 -07:00
doctorpangloss
735a133ad4
Update to 0.3.51
2025-08-22 17:29:18 -07:00
contentis
fe31ad0276
Add elementwise fusions ( #9495 )
...
* Add elementwise fusions
* Add addcmul pattern to Qwen
2025-08-22 19:39:15 -04:00
doctorpangloss
dfc47e0611
Merge branch 'master' of github.com:comfyanonymous/ComfyUI
2025-08-22 13:24:52 -07:00
