Commit Graph
4860 Commits
Author SHA1 Message Date
Kimbing NgandGitHub e5e70636e7 Remove single quote pattern to avoid wrong matches (#9842) 2025-09-13 16:59:19 -04:00
comfyanonymousandGitHub 29bf807b0e Cleanup. (#9838) 2025-09-12 21:57:04 -04:00
Jukka SeppänenandGitHub 2559dee492 Support wav2vec base models (#9637)
* Support wav2vec base models

* trim trailing whitespace

* Do interpolation after
2025-09-12 21:52:58 -04:00
comfyanonymousandGitHub a3b04de700 Hunyuan refiner vae now works with tiled. (#9836) 2025-09-12 19:46:46 -04:00
Jedrzej KosinskiandGitHub d7f40442f9 Enable Runtime Selection of Attention Functions (#9639)
* Looking into a @wrap_attn decorator to look for 'optimized_attention_override' entry in transformer_options

* Created logging code for this branch so that it can be used to track down all the code paths where transformer_options would need to be added

* Fix memory usage issue with inspect

* Made WAN attention receive transformer_options, test node added to wan to test out attention override later

* Added **kwargs to all attention functions so transformer_options could potentially be passed through

* Make sure wrap_attn doesn't make itself recurse infinitely, attempt to load SageAttention and FlashAttention if not enabled so that they can be marked as available or not, create registry for available attention

* Turn off attention logging for now, make AttentionOverrideTestNode have a dropdown with available attention (this is a test node only)

* Make flux work with optimized_attention_override

* Add logs to verify optimized_attention_override is passed all the way into attention function

* Make Qwen work with optimized_attention_override

* Made hidream work with optimized_attention_override

* Made wan patches_replace work with optimized_attention_override

* Made SD3 work with optimized_attention_override

* Made HunyuanVideo work with optimized_attention_override

* Made Mochi work with optimized_attention_override

* Made LTX work with optimized_attention_override

* Made StableAudio work with optimized_attention_override

* Made optimized_attention_override work with ACE Step

* Made Hunyuan3D work with optimized_attention_override

* Make CosmosPredict2 work with optimized_attention_override

* Made CosmosVideo work with optimized_attention_override

* Made Omnigen 2 work with optimized_attention_override

* Made StableCascade work with optimized_attention_override

* Made AuraFlow work with optimized_attention_override

* Made Lumina work with optimized_attention_override

* Made Chroma work with optimized_attention_override

* Made SVD work with optimized_attention_override

* Fix WanI2VCrossAttention so that it expects to receive transformer_options

* Fixed Wan2.1 Fun Camera transformer_options passthrough

* Fixed WAN 2.1 VACE transformer_options passthrough

* Add optimized to get_attention_function

* Disable attention logs for now

* Remove attention logging code

* Remove _register_core_attention_functions, as we wouldn't want someone to call that, just in case

* Satisfy ruff

* Remove AttentionOverrideTest node, that's something to cook up for later
2025-09-12 18:07:38 -04:00
doctorpangloss 10448e67ef Tweak torch compile 2025-09-12 14:58:26 -07:00
doctorpangloss 112017f2d2 Group offloading support 2025-09-12 14:58:21 -07:00
comfyanonymousandGitHub b149e2e1e3 Better way of doing the generator for the hunyuan image noise aug. (#9834) 2025-09-12 17:53:15 -04:00
Alexander PiskunandGitHub 581bae2af3 convert Moonvalley API nodes to the V3 schema (#9698) 2025-09-12 17:41:26 -04:00
Alexander PiskunandGitHub af99928f22 convert Canny node to V3 schema (#9743) 2025-09-12 17:40:34 -04:00
Alexander PiskunandGitHub 53c9c7d39a convert CFG nodes to V3 schema (#9717) 2025-09-12 17:39:55 -04:00
Alexander PiskunandGitHub ba68e83f1c convert nodes_cond.py to V3 schema (#9719) 2025-09-12 17:39:30 -04:00
Alexander PiskunandGitHub dcb8834983 convert Cosmos nodes to V3 schema (#9721) 2025-09-12 17:38:46 -04:00
Alexander PiskunandGitHub f9d2e4b742 convert WanCameraEmbedding node to V3 schema (#9714) 2025-09-12 17:38:12 -04:00
Alexander PiskunandGitHub 45bc1f5c00 convert Minimax API nodes to the V3 schema (#9693) 2025-09-12 17:37:31 -04:00
Alexander PiskunandGitHub 0aa074a420 add kling-v2-1 model to the KlingStartEndFrame node (#9630) 2025-09-12 17:29:03 -04:00
comfyanonymousandGitHub 7757d5a657 Set default hunyuan refiner shift to 4.0 (#9833) 2025-09-12 16:40:12 -04:00
comfyanonymousandGitHub e600520f8a Fix hunyuan refiner blownout colors at noise aug less than 0.25 (#9832) 2025-09-12 16:35:34 -04:00
comfyanonymousandGitHub fd2b820ec2 Add noise augmentation to hunyuan image refiner. (#9831)
This was missing and should help with colors being blown out.
2025-09-12 16:03:08 -04:00
doctorpangloss 7179ed44bd Update compose file to use tagged image 2025-09-12 12:08:46 -07:00
doctorpangloss 7cd6383110 Fix distributed previews, add sageattention to the docker container 2025-09-12 11:48:25 -07:00
Benjamin LuandGitHub d6b977b2e6 Bump frontend to 1.26.11 (#9809) 2025-09-12 00:46:01 -04:00
Jedrzej KosinskiandGitHub 15ec9ea958 Add Output to V3 Combo type to match what is possible with V1 (#9813) 2025-09-12 00:44:20 -04:00
comfyanonymousandGitHub 33bd9ed9cb Implement hunyuan image refiner model. (#9817) 2025-09-12 00:43:20 -04:00
comfyanonymousandGitHub 18de0b2830 Fast preview for hunyuan image. (#9814) 2025-09-11 19:33:02 -04:00
ComfyUI WikiandGitHub df6850fae8 Update template to 0.1.81 (#9811) 2025-09-11 14:59:26 -04:00
comfyanonymousandGitHub e01e99d075 Support hunyuan image distilled model. (#9807) 2025-09-10 23:17:34 -04:00
doctorpangloss 421c9b88ae Fix import order 2025-09-10 16:36:03 -07:00
comfyanonymous 72212fef66 ComfyUI version 0.3.59 v0.3.59 2025-09-10 17:25:41 -04:00
ComfyUI WikiandGitHub df34f1549a Update template to 0.1.78 (#9806)
* Update template to 0.1.77

* Update template to 0.1.78
2025-09-10 14:16:41 -07:00
Alexander PiskunandGitHub 9b0553809c add new ByteDanceSeedream (4.0) node (#9802) 2025-09-10 14:13:18 -07:00
doctorpangloss 292f43c127 Do not overwrite comfy.nodes 2025-09-10 09:32:07 -07:00
comfyanonymous 8d7c930246 ComfyUI version v0.3.58 v0.3.58 2025-09-10 10:51:02 -04:00
Alexander PiskunandGitHub de44b95db6 add StabilityAudio API nodes (#9749) 2025-09-10 05:06:47 -04:00
comfyanonymousandGitHub 543888d3d8 Fix lowvram issue with hunyuan image vae. (#9794) 2025-09-10 02:15:34 -04:00
ComfyUI WikiandGitHub 70fc0425b3 Update template to 0.1.76 (#9793) 2025-09-10 02:09:16 -04:00
comfyanonymousandGitHub 85e34643f8 Support hunyuan image 2.1 regular model. (#9792) 2025-09-10 02:05:07 -04:00
comfyanonymousandGitHub 5c33872e2f Fix issue on old torch. (#9791) 2025-09-10 00:23:47 -04:00
doctorpangloss c10f746bef fix output tensor return 2025-09-09 18:41:12 -07:00
Jedrzej KosinskiandGitHub 206595f854 Change validate_inputs' output typehint to 'bool | str' and update docstrings (#9786) 2025-09-09 21:33:36 -04:00
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
comfyanonymousandGitHub b288fb0db8 Small refactor of some vae code. (#9787) 2025-09-09 18:09:56 -04:00
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
Alexander PiskunandGitHub f73b176abd add ByteDance video API nodes (#9712) 2025-09-09 14:40:29 -04:00
comfyanonymousandGitHub 103a12cb66 Support qwen inpaint controlnet. (#9772) 2025-09-08 17:30:26 -04:00
contentisandGitHub 97652d26b8 Add explicit casting in apply_rope for Qwen VL (#9759) 2025-09-08 15:08:18 -04:00
Jedrzej KosinskiandGitHub bd1d9bcd5f Add ZeroDivisionError catch for EasyCache logging statement (#9768) 2025-09-08 15:07:04 -04:00
doctorpangloss b62d4f05e1 more type documentation, fix installation with dependency group 2025-09-08 11:35:19 -07:00