Changrz
6ec1cfe101
[Rodin3d api nodes] Updated the name of the save file path (changed from timestamp to UUID). ( #10011 )
...
* Update savepath name from time to uuid
* delete lib
2025-09-29 11:59:12 -07:00
comfyanonymous
b60dc31627
Update command to install latest nighly pytorch. ( #10085 )
2025-09-28 13:41:32 -04:00
comfyanonymous
555f902fc1
Fix stable workflow creating multiple draft releases. ( #10067 )
2025-09-27 22:43:25 -04:00
Rui Wang (王瑞)
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
2dadb34860
convert nodes_hypertile.py to V3 schema ( #10061 )
2025-09-27 19:16:22 -07:00
Alexander Piskun
1cf86f5ae5
convert nodes_lumina2.py to V3 schema ( #10058 )
2025-09-27 19:12:51 -07:00
Alexander Piskun
a1127b232d
convert nodes_lotus.py to V3 schema ( #10057 )
2025-09-27 19:11:36 -07:00
comfyanonymous
896f2e653c
Fix typo in release workflow. ( #10066 )
2025-09-27 21:30:35 -04:00
comfyanonymous
40ae495ddc
Improvements to the stable release workflow. ( #10065 )
2025-09-27 20:28:49 -04:00
rattus128
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
Alexander Piskun
160698eb41
convert nodes_qwen.py to V3 schema ( #10049 )
2025-09-27 12:25:35 -07:00
Alexander Piskun
7eca95657c
convert nodes_photomaker.py to V3 schema ( #10017 )
2025-09-27 02:36:43 -07:00
Alexander Piskun
ad5aef2d0c
convert nodes_pixart.py to V3 schema ( #10019 )
2025-09-27 02:34:32 -07:00
Alexander Piskun
bcfd80dd79
convert nodes_luma.py to V3 schema ( #10030 )
2025-09-27 02:28:11 -07:00
Alexander Piskun
6b4b671ce7
convert nodes_bfl.py to V3 schema ( #10033 )
2025-09-27 02:27:01 -07:00
Alexander Piskun
a9cf1cd249
convert nodes_hidream.py to V3 schema ( #9946 )
2025-09-26 23:13:05 -07:00
Christian Byrne
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
0572029fee
Update template to 0.1.88 ( #10046 )
2025-09-26 21:18:16 -07:00
Jedrzej Kosinski
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
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
cd66d72b46
convert CLIPTextEncodeSDXL nodes to V3 schema ( #9716 )
2025-09-26 14:15:44 -07:00
Alexander Piskun
2103e39335
convert nodes_post_processing to V3 schema ( #9491 )
2025-09-26 14:14:42 -07:00
Alexander Piskun
d20576e6a3
convert nodes_sag.py to V3 schema ( #9940 )
2025-09-26 14:13:52 -07:00
Alexander Piskun
a061b06321
convert nodes_tcfg.py to V3 schema ( #9942 )
2025-09-26 14:13:05 -07:00
Alexander Piskun
80718908a9
convert nodes_sdupscale.py to V3 schema ( #9943 )
2025-09-26 14:12:38 -07:00
Alexander Piskun
7ea173c187
convert nodes_fresca.py to V3 schema ( #9951 )
2025-09-26 14:12:04 -07:00
Alexander Piskun
76eb1d72c3
convert nodes_rebatch.py to V3 schema ( #9945 )
2025-09-26 14:10:49 -07:00
Yoland Yan
c4a46e943c
Add @kosinkadink as code owner ( #10041 )
...
Updated CODEOWNERS to include @kosinkadink as a code owner.
2025-09-26 17:08:16 -04:00
doctorpangloss
dcba4847ab
Fix linting issues
2025-09-26 13:22:04 -07:00
doctorpangloss
8ab28996fb
Merge branch 'master' of github.com:comfyanonymous/ComfyUI
2025-09-26 13:18:23 -07:00
Benjamin Berman
e62df3a881
Fix issue finding approx vae taesdxl when used in a workflow
2025-09-26 12:29:00 -07:00
comfyanonymous
2b7f9a8196
Fix the failing unit test. ( #10037 )
2025-09-26 14:12:43 -04:00
doctorpangloss
6bba743d62
Fix exec info issues
2025-09-26 10:54:30 -07:00
comfyanonymous
ce4cb2389c
Make LatentCompositeMasked work with basic video latents. ( #10023 )
2025-09-25 17:20:13 -04:00
Guy Niv
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
fccab99ec0
Fix issue with .view() in HuMo. ( #10014 )
2025-09-24 20:09:42 -04:00
Jukka Seppänen
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
doctorpangloss
3de77f6e24
ROCm support
2025-09-24 14:40:28 -07:00
doctorpangloss
85474cee78
Python 3.10 unit tests pass on NVIDIA containers and older torch
2025-09-24 14:39:52 -07:00
Changrz
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
doctorpangloss
06a5766dd7
Update logging to logger everywhere
2025-09-23 16:07:54 -07:00
doctorpangloss
74d77a3757
Fix container image for rocm
2025-09-23 15:33:23 -07:00
doctorpangloss
1d3dd20b67
Workaround for potential issue loading loras on windows
2025-09-23 15:13:46 -07:00
doctorpangloss
ff494713fb
Fix linting error
2025-09-23 15:06:34 -07:00
doctorpangloss
6e98a0c478
Fix linting errors, preliminary rocm 7 support
2025-09-23 15:02:21 -07:00
doctorpangloss
ac0694a7bd
Fix #46 enable node blacklisting using --blacklist-custom-nodes ComfyUI-Manager / config.blacklist_custom_nodes = ["ComfyUI-Manager"]
2025-09-23 13:50:05 -07:00
doctorpangloss
2a881a768e
Fix #45 now test 3.10 and 3.12 images. NVIDIA doesn't support 3.11 at all!
2025-09-23 13:22:54 -07:00
doctorpangloss
f6d3962c77
Fix tests
...
Merge branch 'master' of github.com:comfyanonymous/ComfyUI
2025-09-23 12:42:12 -07:00
doctorpangloss
6a48fc1c40
Pass all tests. Add Qwen-Edit and other Qwen checkpoints for testing
2025-09-23 12:15:41 -07:00
doctorpangloss
6af812f9a8
Fix custom model paths config paths, tweak tests
2025-09-23 11:01:48 -07:00
