Rando717 and GitHub
e4ee6ae301
Update cfz_vae_loader.py (moved node to CFZ/category)
2025-09-28 21:05:00 +02:00
Rando717 and GitHub
2e4f550d66
Update cfz_patcher.py (moved CFZ nodes to CFZ/category)
2025-09-28 21:03:27 +02:00
Rando717 and GitHub
2e1b189c97
Update cfz_cudnn.toggle.py (moved to CFZ/category)
2025-09-28 20:55:26 +02:00
Rando717 and GitHub
165f17aece
cfz_caching_condition.py (moved CFZ nodes to CFZ/category)
...
moving all CFZ nodes into CFZ category, more organized
2025-09-28 20:54:01 +02:00
comfyanonymous and GitHub
b60dc31627
Update command to install latest nighly pytorch. ( #10085 )
2025-09-28 13:41:32 -04:00
patientx and GitHub
5e79de6a73
Merge branch 'comfyanonymous:master' into master
2025-09-28 12:23:05 +03:00
comfyanonymous and GitHub
555f902fc1
Fix stable workflow creating multiple draft releases. ( #10067 )
2025-09-27 22:43:25 -04:00
1364548c72
feat: ComfyUI can be run on the specified Ascend NPU ( #9663 )
...
* feature: Set the Ascend NPU to use a single one
* Enable the `--cuda-device` parameter to support both CUDA and Ascend NPUs simultaneously.
* Make the code just set the ASCENT_RT_VISIBLE_DEVICES environment variable without any other edits to master branch
---------
Co-authored-by: Jedrzej Kosinski <kosinkadink1@gmail.com >
2025-09-27 22:36:02 -04:00
Alexander Piskun and GitHub
2dadb34860
convert nodes_hypertile.py to V3 schema ( #10061 )
2025-09-27 19:16:22 -07:00
Alexander Piskun and GitHub
1cf86f5ae5
convert nodes_lumina2.py to V3 schema ( #10058 )
2025-09-27 19:12:51 -07:00
Alexander Piskun and GitHub
a1127b232d
convert nodes_lotus.py to V3 schema ( #10057 )
2025-09-27 19:11:36 -07:00
patientx and GitHub
21dc67a0b9
Merge branch 'comfyanonymous:master' into master
2025-09-28 04:38:19 +03:00
comfyanonymous and GitHub
896f2e653c
Fix typo in release workflow. ( #10066 )
2025-09-27 21:30:35 -04:00
comfyanonymous and GitHub
40ae495ddc
Improvements to the stable release workflow. ( #10065 )
2025-09-27 20:28:49 -04:00
rattus128 and GitHub
653ceab414
Reduce Peak WAN inference VRAM usage - part II ( #10062 )
...
* flux: math: Use _addcmul to avoid expensive VRAM intermediate
The rope process can be the VRAM peak and this intermediate
for the addition result before releasing the original can OOM.
addcmul_ it.
* wan: Delete the self attention before cross attention
This saves VRAM when the cross attention and FFN are in play as the
VRAM peak.
2025-09-27 18:14:16 -04:00
patientx and GitHub
da3d19833e
Merge branch 'comfyanonymous:master' into master
2025-09-28 01:08:36 +03:00
Alexander Piskun and GitHub
160698eb41
convert nodes_qwen.py to V3 schema ( #10049 )
2025-09-27 12:25:35 -07:00
patientx and GitHub
7e6b077cd7
Merge branch 'comfyanonymous:master' into master
2025-09-27 14:25:54 +03:00
Alexander Piskun and GitHub
7eca95657c
convert nodes_photomaker.py to V3 schema ( #10017 )
2025-09-27 02:36:43 -07:00
Alexander Piskun and GitHub
ad5aef2d0c
convert nodes_pixart.py to V3 schema ( #10019 )
2025-09-27 02:34:32 -07:00
Alexander Piskun and GitHub
bcfd80dd79
convert nodes_luma.py to V3 schema ( #10030 )
2025-09-27 02:28:11 -07:00
Alexander Piskun and GitHub
6b4b671ce7
convert nodes_bfl.py to V3 schema ( #10033 )
2025-09-27 02:27:01 -07:00
Alexander Piskun and GitHub
a9cf1cd249
convert nodes_hidream.py to V3 schema ( #9946 )
2025-09-26 23:13:05 -07:00
Christian Byrne and GitHub
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 Wiki and GitHub
0572029fee
Update template to 0.1.88 ( #10046 )
2025-09-26 21:18:16 -07:00
Jedrzej Kosinski and GitHub
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
comfyanonymous and GitHub
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 Piskun and GitHub
cd66d72b46
convert CLIPTextEncodeSDXL nodes to V3 schema ( #9716 )
2025-09-26 14:15:44 -07:00
Alexander Piskun and GitHub
2103e39335
convert nodes_post_processing to V3 schema ( #9491 )
2025-09-26 14:14:42 -07:00
Alexander Piskun and GitHub
d20576e6a3
convert nodes_sag.py to V3 schema ( #9940 )
2025-09-26 14:13:52 -07:00
Alexander Piskun and GitHub
a061b06321
convert nodes_tcfg.py to V3 schema ( #9942 )
2025-09-26 14:13:05 -07:00
Alexander Piskun and GitHub
80718908a9
convert nodes_sdupscale.py to V3 schema ( #9943 )
2025-09-26 14:12:38 -07:00
Alexander Piskun and GitHub
7ea173c187
convert nodes_fresca.py to V3 schema ( #9951 )
2025-09-26 14:12:04 -07:00
Alexander Piskun and GitHub
76eb1d72c3
convert nodes_rebatch.py to V3 schema ( #9945 )
2025-09-26 14:10:49 -07:00
Yoland Yan and GitHub
c4a46e943c
Add @kosinkadink as code owner ( #10041 )
...
Updated CODEOWNERS to include @kosinkadink as a code owner.
2025-09-26 17:08:16 -04:00
patientx and GitHub
85c88fbdf7
Merge branch 'comfyanonymous:master' into master
2025-09-26 22:14:47 +03:00
comfyanonymous and GitHub
2b7f9a8196
Fix the failing unit test. ( #10037 )
2025-09-26 14:12:43 -04:00
patientx and GitHub
e2985f3935
Merge branch 'comfyanonymous:master' into master
2025-09-26 13:46:28 +03:00
patientx and GitHub
ebe156ccbe
Update install-n.bat
2025-09-26 12:55:38 +03:00
comfyanonymous and GitHub
ce4cb2389c
Make LatentCompositeMasked work with basic video latents. ( #10023 )
2025-09-25 17:20:13 -04:00
patientx and GitHub
258da26c98
Merge branch 'comfyanonymous:master' into master
2025-09-25 15:08:16 +03:00
Guy Niv and GitHub
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
comfyanonymous and GitHub
fccab99ec0
Fix issue with .view() in HuMo. ( #10014 )
2025-09-24 20:09:42 -04:00
Jukka Seppänen and GitHub
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
patientx and GitHub
e687d57150
Merge branch 'comfyanonymous:master' into master
2025-09-24 22:51:44 +03:00
Changrz and GitHub
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
patientx and GitHub
65fdf11559
Merge branch 'comfyanonymous:master' into master
2025-09-23 22:29:25 +03:00
comfyanonymous
b8730510db
ComfyUI version 0.3.60
v0.3.60
2025-09-23 11:50:33 -04:00
Alexander Piskun and GitHub
e808790799
feat(api-nodes): add wan t2i, t2v, i2v nodes ( #9996 )
2025-09-23 11:36:47 -04:00
ComfyUI Wiki and GitHub
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