bc8418f55a
Merge branch 'master' into dr-support-pip-cm
2025-09-26 07:00:43 +09:00
ce4cb2389c
Make LatentCompositeMasked work with basic video latents. ( #10023 )
2025-09-25 17:20:13 -04:00
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
fccab99ec0
Fix issue with .view() in HuMo. ( #10014 )
2025-09-24 20:09:42 -04:00
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
42f69b1ffd
Merge branch 'master' into dr-support-pip-cm
2025-09-25 07:25:27 +09:00
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
581059a83d
Merge branch 'master' into dr-support-pip-cm
2025-09-24 07:24:19 +09:00
b8730510db
ComfyUI version 0.3.60
2025-09-23 11:50:33 -04:00
e808790799
feat(api-nodes): add wan t2i, t2v, i2v nodes ( #9996 )
2025-09-23 11:36:47 -04:00
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
74c1a58566
Merge branch 'master' into dr-support-pip-cm
2025-09-23 07:28:52 +09:00
707b2638ec
Fix bug with WanAnimateToVideo. ( #9990 )
2025-09-22 17:34:33 -04:00
8a5ac527e6
Fix bug with WanAnimateToVideo node. ( #9988 )
2025-09-22 17:26:58 -04:00
e3206351b0
add offset param ( #9977 )
2025-09-22 17:12:32 -04:00
1fee8827cb
Support for qwen edit plus model. Use the new TextEncodeQwenImageEditPlus. ( #9986 )
2025-09-22 16:49:48 -04:00
316aa125c9
Merge branch 'master' into dr-support-pip-cm
2025-09-22 12:33:09 +09:00
27bc181c49
Set some wan nodes as no longer experimental. ( #9976 )
2025-09-21 19:48:31 -04:00
7b1ed9b2b8
Merge branch 'master' into dr-support-pip-cm
2025-09-21 11:24:37 +09:00
d1d9eb94b1
Lower wan memory estimation value a bit. ( #9964 )
...
Previous pr reduced the peak memory requirement.
2025-09-20 22:09:35 -04:00
4ea946778b
Merge branch 'master' into dr-support-pip-cm
2025-09-21 10:45:28 +09:00
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
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
309c92d6c9
Merge branch 'master' into dr-support-pip-cm
2025-09-21 09:33:38 +09:00
66241cef31
Add inputs for character replacement to the WanAnimateToVideo node. ( #9960 )
2025-09-20 02:24:10 -04:00
e8df53b764
Update WanAnimateToVideo to more easily extend videos. ( #9959 )
2025-09-19 18:48:56 -04:00
ca7492c9d4
Merge branch 'master' into dr-support-pip-cm
2025-09-20 07:13:36 +09:00
852704c81a
fix(seedream4): add flag to ignore error on partial success ( #9952 )
2025-09-19 16:04:51 -04:00
9fdf8c25ab
api_nodes: reduce default timeout from 7 days to 2 hours ( #9918 )
2025-09-19 16:02:43 -04:00
dc95b6acc0
Basic WIP support for the wan animate model. ( #9939 )
2025-09-19 03:07:17 -04:00
711bcf33ee
Bump frontend to 1.26.13 ( #9933 )
2025-09-19 03:03:30 -04:00
267c54eaae
Updated comfyui_manager to version 4.0.2 in requirements.txt
2025-09-19 12:00:17 +09:00
fa51f0c60a
Merge branch 'master' into dr-support-pip-cm
2025-09-19 12:00:10 +09:00
24b0fce099
Do padding of audio embed in model for humo for more flexibility. ( #9935 )
2025-09-18 19:54:16 -04:00
1ea8c54064
make kernel of same type as image to avoid mismatch issues ( #9932 )
2025-09-18 19:51:16 -04:00
8d6653fca6
Enable fp8 ops by default on gfx1200 ( #9926 )
2025-09-18 19:50:37 -04:00
0a084a88a2
Merge branch 'master' into dr-support-pip-cm
2025-09-19 08:16:58 +09:00
036aa3efa8
fixed: Even if --enable-manager is applied, it should switch to a disabled state if comfyui_manager is not installed.
2025-09-19 07:38:10 +09:00
e7ff647d02
--disable-manager -> --enable-manager
2025-09-17 20:58:42 -04:00
dd611a7700
Support the HuMo 17B model. ( #9912 )
2025-09-17 18:39:24 -04:00
77e10752fe
Merge branch 'master' into dr-support-pip-cm
2025-09-18 07:32:23 +09:00
9288c78fc5
Support the HuMo model. ( #9903 )
2025-09-17 00:12:48 -04:00
2c30881d9c
Merge branch 'master' into dr-support-pip-cm
2025-09-17 11:56:35 +09:00
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
7fa5990dbc
Merge branch 'master' into dr-support-pip-cm
2025-09-17 06:09:40 +09:00
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
07212a2466
Merge branch 'master' into dr-support-pip-cm
2025-09-16 12:39:43 +09:00
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
47a9cde5d3
Support the omnigen2 umo lora. ( #9886 )
2025-09-15 18:10:55 -04:00
f4d7a32cd8
Merge branch 'master' into dr-support-pip-cm
2025-09-15 12:16:00 +09:00
