wangbo/ComfyUI
1
0
Fork 0
mirror of https://github.com/comfyanonymous/ComfyUI.git synced 2026-07-21 23:41:28 +08:00
Code Issues Actions 10 Packages Projects Releases Wiki Activity
4,324 Commits 305 Branches 166 Tags
c36323fe53a63ec77fca365d2788e247e6fad388
Commit Graph
4324 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
Alexander PiskunandGitHub 7eca95657c convert nodes_photomaker.py to V3 schema (#10017) 2025-09-27 02:36:43 -07:00
Alexander PiskunandGitHub ad5aef2d0c convert nodes_pixart.py to V3 schema (#10019) 2025-09-27 02:34:32 -07:00
Alexander PiskunandGitHub bcfd80dd79 convert nodes_luma.py to V3 schema (#10030) 2025-09-27 02:28:11 -07:00
Alexander PiskunandGitHub 6b4b671ce7 convert nodes_bfl.py to V3 schema (#10033) 2025-09-27 02:27:01 -07:00
Alexander PiskunandGitHub a9cf1cd249 convert nodes_hidream.py to V3 schema (#9946) 2025-09-26 23:13:05 -07:00
Christian ByrneandGitHub 255572188f Add workflow templates version tracking to system_stats (#9089) 
Adds installed and required workflow templates version information to the
/system_stats endpoint, allowing the frontend to detect and notify users
when their templates package is outdated.

- Add get_installed_templates_version() and get_required_templates_version()
  methods to FrontendManager
- Include templates version info in system_stats response
- Add comprehensive unit tests for the new functionality
 2025-09-26 21:29:13 -07:00
ComfyUI WikiandGitHub 0572029fee Update template to 0.1.88 (#10046) 2025-09-26 21:18:16 -07:00
Jedrzej KosinskiandGitHub 196954ab8c Add 'input_cond' and 'input_uncond' to the args dictionary passed into sampler_cfg_function (#10044) 2025-09-26 19:55:03 -07:00
comfyanonymousandGitHub 1e098d6132 Don't add template to qwen2.5vl when template is in prompt. (#10043) 
Make the hunyuan image refiner template_end 36.
 2025-09-26 18:34:17 -04:00
Alexander PiskunandGitHub cd66d72b46 convert CLIPTextEncodeSDXL nodes to V3 schema (#9716) 2025-09-26 14:15:44 -07:00
Alexander PiskunandGitHub 2103e39335 convert nodes_post_processing to V3 schema (#9491) 2025-09-26 14:14:42 -07:00
Alexander PiskunandGitHub d20576e6a3 convert nodes_sag.py to V3 schema (#9940) 2025-09-26 14:13:52 -07:00
Alexander PiskunandGitHub a061b06321 convert nodes_tcfg.py to V3 schema (#9942) 2025-09-26 14:13:05 -07:00
Alexander PiskunandGitHub 80718908a9 convert nodes_sdupscale.py to V3 schema (#9943) 2025-09-26 14:12:38 -07:00
Alexander PiskunandGitHub 7ea173c187 convert nodes_fresca.py to V3 schema (#9951) 2025-09-26 14:12:04 -07:00
Alexander PiskunandGitHub 76eb1d72c3 convert nodes_rebatch.py to V3 schema (#9945) 2025-09-26 14:10:49 -07:00
Yoland YanandGitHub c4a46e943c Add @kosinkadink as code owner (#10041) 
Updated CODEOWNERS to include @kosinkadink as a code owner.
 2025-09-26 17:08:16 -04:00
comfyanonymousandGitHub 2b7f9a8196 Fix the failing unit test. (#10037) 2025-09-26 14:12:43 -04:00
comfyanonymousandGitHub ce4cb2389c Make LatentCompositeMasked work with basic video latents. (#10023) 2025-09-25 17:20:13 -04:00
Guy NivandGitHub c8d2117f02 Fix memory leak by properly detaching model finalizer (#9979) 
When unloading models in load_models_gpu(), the model finalizer was not
being explicitly detached, leading to a memory leak. This caused
linear memory consumption increase over time as models are repeatedly
loaded and unloaded.

This change prevents orphaned finalizer references from accumulating in
memory during model switching operations.
 2025-09-24 22:35:12 -04:00
comfyanonymousandGitHub fccab99ec0 Fix issue with .view() in HuMo. (#10014) 2025-09-24 20:09:42 -04:00
Jukka SeppänenandGitHub fd79d32f38 Add new audio nodes (#9908) 
* Add new audio nodes

- TrimAudioDuration
- SplitAudioChannels
- AudioConcat
- AudioMerge
- AudioAdjustVolume

* Update nodes_audio.py

* Add EmptyAudio -node

* Change duration to Float (allows sub seconds)
 2025-09-24 18:59:29 -04:00
ChangrzandGitHub 341b4adefd Rodin3D - add [Rodin3D Gen-2 generate] api-node (#9994) 
* update Rodin api node

* update rodin3d gen2 api node

* fix images limited bug
 2025-09-24 14:05:37 -04:00
comfyanonymous b8730510db ComfyUI version 0.3.60 v0.3.60 2025-09-23 11:50:33 -04:00
Alexander PiskunandGitHub e808790799 feat(api-nodes): add wan t2i, t2v, i2v nodes (#9996) 2025-09-23 11:36:47 -04:00
ComfyUI WikiandGitHub 145b0e4f79 update template to 0.1.86 (#9998) 
* update template to 0.1.84

* update template to 0.1.85

* Update template to 0.1.86
 2025-09-23 11:22:35 -04:00
comfyanonymousandGitHub 707b2638ec Fix bug with WanAnimateToVideo. (#9990) 2025-09-22 17:34:33 -04:00
comfyanonymousandGitHub 8a5ac527e6 Fix bug with WanAnimateToVideo node. (#9988) 2025-09-22 17:26:58 -04:00
Christian ByrneandGitHub e3206351b0 add offset param (#9977) 2025-09-22 17:12:32 -04:00
comfyanonymousandGitHub 1fee8827cb Support for qwen edit plus model. Use the new TextEncodeQwenImageEditPlus. (#9986) 2025-09-22 16:49:48 -04:00
comfyanonymousandGitHub 27bc181c49 Set some wan nodes as no longer experimental. (#9976) 2025-09-21 19:48:31 -04:00
comfyanonymousandGitHub d1d9eb94b1 Lower wan memory estimation value a bit. (#9964) 
Previous pr reduced the peak memory requirement.
 2025-09-20 22:09:35 -04:00
Kohaku-BlueleafandGitHub 7be2b49b6b Fix LoRA Trainer bugs with FP8 models. (#9854) 
* Fix adapter weight init

* Fix fp8 model training

* Avoid inference tensor
 2025-09-20 21:24:48 -04:00
Jedrzej KosinskiGitHubThereforeGames
 		9ed3c5cc09 [Reviving #5709] Add strength input to Differential Diffusion (#9957) 
* Update nodes_differential_diffusion.py

* Update nodes_differential_diffusion.py

* Make strength optional to avoid validation errors when loading old workflows, adjust step

---------

Co-authored-by: ThereforeGames <eric@sparknight.io>
 2025-09-20 21:10:39 -04:00
comfyanonymousandGitHub 66241cef31 Add inputs for character replacement to the WanAnimateToVideo node. (#9960) 2025-09-20 02:24:10 -04:00
comfyanonymousandGitHub e8df53b764 Update WanAnimateToVideo to more easily extend videos. (#9959) 2025-09-19 18:48:56 -04:00
Alexander PiskunandGitHub 852704c81a fix(seedream4): add flag to ignore error on partial success (#9952) 2025-09-19 16:04:51 -04:00
Alexander PiskunandGitHub 9fdf8c25ab api_nodes: reduce default timeout from 7 days to 2 hours (#9918) 2025-09-19 16:02:43 -04:00
comfyanonymousandGitHub dc95b6acc0 Basic WIP support for the wan animate model. (#9939) 2025-09-19 03:07:17 -04:00
Christian ByrneandGitHub 711bcf33ee Bump frontend to 1.26.13 (#9933) 2025-09-19 03:03:30 -04:00
comfyanonymousandGitHub 24b0fce099 Do padding of audio embed in model for humo for more flexibility. (#9935) 2025-09-18 19:54:16 -04:00
Jodh SinghandGitHub 1ea8c54064 make kernel of same type as image to avoid mismatch issues (#9932) 2025-09-18 19:51:16 -04:00
DELUXAandGitHub 8d6653fca6 Enable fp8 ops by default on gfx1200 (#9926) 2025-09-18 19:50:37 -04:00
comfyanonymousandGitHub dd611a7700 Support the HuMo 17B model. (#9912) 2025-09-17 18:39:24 -04:00
comfyanonymousandGitHub 9288c78fc5 Support the HuMo model. (#9903) 2025-09-17 00:12:48 -04:00
rattus128andGitHub e42682b24e Reduce Peak WAN inference VRAM usage (#9898) 
* flux: Do the xq and xk ropes one at a time

This was doing independendent interleaved tensor math on the q and k
tensors, leading to the holding of more than the minimum intermediates
in VRAM. On a bad day, it would VRAM OOM on xk intermediates.

Do everything q and then everything k, so torch can garbage collect
all of qs intermediates before k allocates its intermediates.

This reduces peak VRAM usage for some WAN2.2 inferences (at least).

* wan: Optimize qkv intermediates on attention

As commented. The former logic computed independent pieces of QKV in
parallel which help more inference intermediates in VRAM spiking
VRAM usage. Fully roping Q and garbage collecting the intermediates
before touching K reduces the peak inference VRAM usage.
 2025-09-16 19:21:14 -04:00
comfyanonymousandGitHub a39ac59c3e Add encoder part of whisper large v3 as an audio encoder model. (#9894) 
Not useful yet but some models use it.
 2025-09-16 01:19:50 -04:00
bleppingandGitHub 1a85483da1 Fix depending on asserts to raise an exception in BatchedBrownianTree and Flash attn module (#9884) 
Correctly handle the case where w0 is passed by kwargs in BatchedBrownianTree
 2025-09-15 20:05:03 -04:00
comfyanonymousandGitHub 47a9cde5d3 Support the omnigen2 umo lora. (#9886) 2025-09-15 18:10:55 -04:00
comfyanonymousandGitHub 4f1f26ac6c Add that hunyuan image is supported to readme. (#9857) 2025-09-14 04:05:38 -04:00