comfyanonymous
8691037bcc
Lowvram fix.
2025-11-20 22:12:56 -05:00
comfyanonymous
726ca6c97e
Better VAE encode mem estimation.
2025-11-20 22:12:56 -05:00
comfyanonymous
8ccd4ca886
Allow any number of input frames in VAE.
2025-11-20 22:12:56 -05:00
Rattus
023036ef9d
vae_refiner: roll the convolution through temporal II
...
Roll the convolution through time using 2-latent-frame chunks and a
FIFO queue for the convolution seams.
Added support for encoder, lowered to 1 latent frame to save more
VRAM, made work for Hunyuan Image 3.0 (as code shared).
Fixed names, cleaned up code.
2025-11-20 22:12:56 -05:00
kijai
d8858cb58b
Bugfix for the HunyuanVideo15 SR model
2025-11-20 22:12:56 -05:00
kijai
87256acf20
Fix TokenRefiner for fp16
...
Otherwise x.sum has infs, just in case only casting if input is fp16, I don't know if necessary.
2025-11-20 22:12:56 -05:00
kijai
b1652790d2
Proper hyvid15 I2V channels
...
Co-Authored-By: comfyanonymous <121283862+comfyanonymous@users.noreply.github.com>
2025-11-20 22:12:56 -05:00
kijai
11061d3ecc
Some cleanup
...
Co-Authored-By: comfyanonymous <121283862+comfyanonymous@users.noreply.github.com>
2025-11-20 22:12:56 -05:00
Rattus
d423272754
fix
2025-11-20 22:12:56 -05:00
kijai
18ae40065a
Support HunyuanVideo15 latent resampler
2025-11-20 22:12:56 -05:00
Rattus
dc2e308422
vae_refiner: roll the convolution through temporal
...
Work in progress.
Roll the convolution through time using 2-latent-frame chunks and a
FIFO queue for the convolution seams.
2025-11-20 22:12:56 -05:00
kijai
0aa6eb2edc
SR model fixes
...
This also still needs timesteps scheduling based on the noise scale, can be used with two samplers too already
2025-11-20 22:12:56 -05:00
kijai
8a45f558a9
Proper latent channel count
2025-11-20 22:12:56 -05:00
kijai
fcd3a00d91
whitespaces...
2025-11-20 22:12:56 -05:00
kijai
fb4739f2f5
Support HunyuanVideo1.5 SR model
2025-11-20 22:12:56 -05:00
kijai
5d640eb407
Use the correct sigclip output...
2025-11-20 22:12:56 -05:00
kijai
5ffcc184fe
Better latent rgb factors
2025-11-20 22:12:56 -05:00
kijai
1ae17f4d57
Update nodes_hunyuan.py
2025-11-20 22:12:56 -05:00
kijai
f8fd20a2f3
Update model_base.py
2025-11-20 22:12:56 -05:00
kijai
5fe386157a
I2V
2025-11-20 22:12:56 -05:00
kijai
dc736b62a2
fp16 works
2025-11-20 22:12:56 -05:00
kijai
521cc1d38d
Prevent empty negative prompt
...
Really doesn't work otherwise
2025-11-20 22:12:56 -05:00
kijai
eaef7b764e
Fix text encoding
2025-11-20 22:12:56 -05:00
kijai
ed3d1942d0
remove print
2025-11-20 22:12:56 -05:00
kijai
7378bf6a27
Update model.py
2025-11-20 22:12:56 -05:00
kijai
24d1b6b88a
Update model.py
2025-11-20 22:12:56 -05:00
kijai
4f242de56f
update
2025-11-20 22:12:56 -05:00
kijai
cadd00226b
init
2025-11-20 22:12:56 -05:00
Christian Byrne
10e90a5757
bump comfyui-workflow-templates for nano banana 2 ( #10818 )
...
* bump templates
* bump templates
2025-11-20 18:20:52 -08:00
Alexander Piskun
b75d349f25
fix(KlingLipSyncAudioToVideoNode): convert audio to mp3 format ( #10811 )
2025-11-20 16:33:54 -08:00
Alexander Piskun
7b8389578e
feat(api-nodes): add Nano Banana Pro ( #10814 )
...
* feat(api-nodes): add Nano Banana Pro
* frontend bump to 1.28.9
2025-11-20 16:17:47 -08:00
Jedrzej Kosinski
9e00ce5b76
Make Batch Images node add alpha channel when one of the inputs has it ( #10816 )
...
* When one Batch Image input has alpha and one does not, add empty alpha channel
* Use torch.nn.functional.pad
2025-11-20 17:42:46 -05:00
comfyanonymous
f5e66d5e47
Fix ImageBatch with different channel count. ( #10815 )
2025-11-20 15:08:03 -05:00
Christian Byrne
87b0359392
Update server templates handler to use new multi-package distribution (comfyui-workflow-templates versions >=0.3) ( #10791 )
...
* update templates for monorepo
* refactor
2025-11-19 22:36:56 -08:00
comfyanonymous
cb96d4d18c
Disable workaround on newer cudnn. ( #10807 )
2025-11-19 23:56:23 -05:00
Alexander Piskun
394348f5ca
feat(api-nodes): add Topaz API nodes ( #10755 )
2025-11-19 17:44:04 -08:00
comfyanonymous
7601e89255
Fix workflow name. ( #10806 )
2025-11-19 20:17:15 -05:00
Alexander Piskun
6a1d3a1ae1
convert hunyuan3d.py to V3 schema ( #10664 )
2025-11-19 14:49:01 -08:00
Alexander Piskun
65ee24c978
change display name of PreviewAny node to "Preview as Text" ( #10796 )
2025-11-19 01:25:28 -08:00
comfyanonymous
17027f2a6a
Add a way to disable the final norm in the llama based TE models. ( #10794 )
2025-11-18 22:36:03 -05:00
comfyanonymous
b5c8be8b1d
ComfyUI 0.3.70
2025-11-18 19:37:20 -05:00
Alexander Piskun
24fdb92edf
feat(api-nodes): add new Gemini model ( #10789 )
2025-11-18 14:26:44 -08:00
comfyanonymous
d526974576
Fix hunyuan 3d 2.0 ( #10792 )
2025-11-18 16:46:19 -05:00
Jukka Seppänen
e1ab6bb394
EasyCache: Fix for mismatch in input/output channels with some models ( #10788 )
...
Slices model input with output channels so the caching tracks only the noise channels, resolves channel mismatch with models like WanVideo I2V
Also fix for slicing deprecation in pytorch 2.9
2025-11-18 07:00:21 -08:00
Alexander Piskun
048f49adbd
chore(api-nodes): adjusted PR template; set min python version for pylint to 3.10 ( #10787 )
2025-11-18 03:59:27 -08:00
comfyanonymous
47bfd5a33f
Native block swap custom nodes considered harmful. ( #10783 )
2025-11-18 00:26:44 -05:00
ComfyUI Wiki
fdf49a2861
Fix the portable download link for CUDA 12.6 ( #10780 )
2025-11-17 22:04:06 -05:00
comfyanonymous
f41e5f398d
Update README with new portable download link ( #10778 )
2025-11-17 19:59:19 -05:00
comfyanonymous
27cbac865e
Add release workflow for NVIDIA cu126 ( #10777 )
2025-11-17 19:04:04 -05:00
comfyanonymous
3d0003c24c
ComfyUI version 0.3.69
2025-11-17 17:17:24 -05:00
