Commit Graph

3927 Commits

Author SHA1 Message Date
blepping
d1a3a5d1b7 Ensure images are multiples of 16 for Chroma Radiance
Add batch dimension and fix channels when necessary in ChromaRadianceImageToLatent node
2025-09-12 20:48:33 -06:00
blepping
0f584ea983 Increase Chroma Radiance memory usage factor once again 2025-09-12 20:48:33 -06:00
blepping
6e44dc8a9d Increase Chroma Radiance memory usage factor 2025-09-12 20:48:33 -06:00
blepping
913fe088b9 Fix Chroma Radiance memory estimation. 2025-09-12 20:48:33 -06:00
blepping
1b0b2b728f Update Radiance nodes to ensure latents/images are on the intermediate device 2025-09-12 20:48:33 -06:00
blepping
d15a96e146 Minor Chroma Radiance cleanups 2025-09-12 20:48:33 -06:00
blepping
52acaa6c19 Initial Chroma Radiance support 2025-09-12 20:48:33 -06:00
comfyanonymous
29bf807b0e
Cleanup. (#9838) 2025-09-12 21:57:04 -04:00
Jukka Seppänen
2559dee492
Support wav2vec base models (#9637)
* Support wav2vec base models

* trim trailing whitespace

* Do interpolation after
2025-09-12 21:52:58 -04:00
comfyanonymous
a3b04de700
Hunyuan refiner vae now works with tiled. (#9836) 2025-09-12 19:46:46 -04:00
Jedrzej Kosinski
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
comfyanonymous
b149e2e1e3
Better way of doing the generator for the hunyuan image noise aug. (#9834) 2025-09-12 17:53:15 -04:00
Alexander Piskun
581bae2af3
convert Moonvalley API nodes to the V3 schema (#9698) 2025-09-12 17:41:26 -04:00
Alexander Piskun
af99928f22
convert Canny node to V3 schema (#9743) 2025-09-12 17:40:34 -04:00
Alexander Piskun
53c9c7d39a
convert CFG nodes to V3 schema (#9717) 2025-09-12 17:39:55 -04:00
Alexander Piskun
ba68e83f1c
convert nodes_cond.py to V3 schema (#9719) 2025-09-12 17:39:30 -04:00
Alexander Piskun
dcb8834983
convert Cosmos nodes to V3 schema (#9721) 2025-09-12 17:38:46 -04:00
Alexander Piskun
f9d2e4b742
convert WanCameraEmbedding node to V3 schema (#9714) 2025-09-12 17:38:12 -04:00
Alexander Piskun
45bc1f5c00
convert Minimax API nodes to the V3 schema (#9693) 2025-09-12 17:37:31 -04:00
Alexander Piskun
0aa074a420
add kling-v2-1 model to the KlingStartEndFrame node (#9630) 2025-09-12 17:29:03 -04:00
comfyanonymous
7757d5a657
Set default hunyuan refiner shift to 4.0 (#9833) 2025-09-12 16:40:12 -04:00
comfyanonymous
e600520f8a
Fix hunyuan refiner blownout colors at noise aug less than 0.25 (#9832) 2025-09-12 16:35:34 -04:00
comfyanonymous
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
Benjamin Lu
d6b977b2e6
Bump frontend to 1.26.11 (#9809) 2025-09-12 00:46:01 -04:00
Jedrzej Kosinski
15ec9ea958
Add Output to V3 Combo type to match what is possible with V1 (#9813) 2025-09-12 00:44:20 -04:00
comfyanonymous
33bd9ed9cb
Implement hunyuan image refiner model. (#9817) 2025-09-12 00:43:20 -04:00
comfyanonymous
18de0b2830
Fast preview for hunyuan image. (#9814) 2025-09-11 19:33:02 -04:00
ComfyUI Wiki
df6850fae8
Update template to 0.1.81 (#9811) 2025-09-11 14:59:26 -04:00
comfyanonymous
e01e99d075
Support hunyuan image distilled model. (#9807) 2025-09-10 23:17:34 -04:00
comfyanonymous
72212fef66 ComfyUI version 0.3.59 2025-09-10 17:25:41 -04:00
ComfyUI Wiki
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 Piskun
9b0553809c
add new ByteDanceSeedream (4.0) node (#9802) 2025-09-10 14:13:18 -07:00
comfyanonymous
8d7c930246 ComfyUI version v0.3.58 2025-09-10 10:51:02 -04:00
Alexander Piskun
de44b95db6
add StabilityAudio API nodes (#9749) 2025-09-10 05:06:47 -04:00
comfyanonymous
543888d3d8
Fix lowvram issue with hunyuan image vae. (#9794) 2025-09-10 02:15:34 -04:00
ComfyUI Wiki
70fc0425b3
Update template to 0.1.76 (#9793) 2025-09-10 02:09:16 -04:00
comfyanonymous
85e34643f8
Support hunyuan image 2.1 regular model. (#9792) 2025-09-10 02:05:07 -04:00
comfyanonymous
5c33872e2f
Fix issue on old torch. (#9791) 2025-09-10 00:23:47 -04:00
Jedrzej Kosinski
206595f854
Change validate_inputs' output typehint to 'bool | str' and update docstrings (#9786) 2025-09-09 21:33:36 -04:00
comfyanonymous
b288fb0db8
Small refactor of some vae code. (#9787) 2025-09-09 18:09:56 -04:00
Alexander Piskun
f73b176abd
add ByteDance video API nodes (#9712) 2025-09-09 14:40:29 -04:00
comfyanonymous
103a12cb66
Support qwen inpaint controlnet. (#9772) 2025-09-08 17:30:26 -04:00
contentis
97652d26b8
Add explicit casting in apply_rope for Qwen VL (#9759) 2025-09-08 15:08:18 -04:00
Jedrzej Kosinski
bd1d9bcd5f
Add ZeroDivisionError catch for EasyCache logging statement (#9768) 2025-09-08 15:07:04 -04:00
comfyanonymous
fb763d4333
Fix amd_min_version crash when cpu device. (#9754) 2025-09-07 21:16:29 -04:00
comfyanonymous
bcbd7884e3
Don't enable pytorch attention on AMD if triton isn't available. (#9747) 2025-09-07 00:29:38 -04:00
comfyanonymous
27a0fcccc3
Enable bf16 VAE on RDNA4. (#9746) 2025-09-06 23:25:22 -04:00
comfyanonymous
ea6cdd2631
Print all fast options in --help (#9737) 2025-09-06 01:05:05 -04:00
comfyanonymous
2ee7879a0b
Fix lowvram issues with hunyuan3d 2.1 (#9735) 2025-09-05 14:57:35 -04:00
Arjan Singh
3493b9cb1f
fix: add cache headers for images (#9560) 2025-09-05 14:32:25 -04:00