 kijai
|
71d02ee0bb
|
smarter zero init
|
2025-03-26 10:56:41 +02:00 |
|
|
kijai
|
b52e5b92bd
|
Update nodes.py
|
2025-03-26 00:14:59 +02:00 |
|
|
kijai
|
d67c96e4b5
|
Update nodes.py
|
2025-03-25 21:30:44 +02:00 |
|
|
kijai
|
d40b28bad6
|
Add CFG-Zero-star
https://github.com/WeichenFan/CFG-Zero-star/
|
2025-03-25 21:19:37 +02:00 |
|
|
kijai
|
a1938107cd
|
Allow splitting self attention as well when using multiple prompts
|
2025-03-25 21:05:08 +02:00 |
|
|
kijai
|
376d4e4557
|
Allow loading comfy-org T5 in the wrapper text encoder loading
|
2025-03-25 19:10:27 +02:00 |
|
|
kijai
|
12eef5bb83
|
Disable enhance-a-video when sampling single image
|
2025-03-25 11:08:47 +02:00 |
|
|
kijai
|
16bf0a0763
|
Clearer error when wrong model selected
|
2025-03-25 09:44:39 +02:00 |
|
|
kijai
|
b0eda236be
|
Update nodes.py
|
2025-03-25 00:27:41 +02:00 |
|
|
kijai
|
b4dc58fd9f
|
Split cross attention when using multiple prompts and/or clip image embeds
Allows for (pretty weak) prompt travel and may help with the endframe workflow.
|
2025-03-25 00:07:41 +02:00 |
|
|
kijai
|
cfea58d831
|
Add WanVideoSetBlockSwap -node to set block swap args without reloading the model
|
2025-03-24 10:33:51 +02:00 |
|
|
kijai
|
4b8672ac3b
|
Update model.py
|
2025-03-23 02:39:34 +02:00 |
|
|
kijai
|
8fbf92ae93
|
Improved loop stitching on decode
|
2025-03-22 23:05:32 +02:00 |
|
|
kijai
|
2dea8f7360
|
Update pyproject.toml
|
2025-03-22 22:18:33 +02:00 |
|
|
kijai
|
11d12f7f07
|
version bump
|
2025-03-22 22:17:25 +02:00 |
|
|
kijai
|
1e2afdbaa2
|
Update nodes.py
|
2025-03-22 16:15:28 +02:00 |
|
|
kijai
|
8d6e823d7e
|
Update nodes.py
|
2025-03-22 16:07:10 +02:00 |
|
|
kijai
|
59cda88ad1
|
Add WanVideoImageResizeToClosest
|
2025-03-22 16:02:23 +02:00 |
|
|
kijai
|
309240c0f4
|
fix T2V (again)
|
2025-03-22 10:14:07 +02:00 |
|
|
kijai
|
2863956da7
|
workflow updates
|
2025-03-22 02:45:11 +02:00 |
|
|
kijai
|
b415fe78f1
|
fix T2V
|
2025-03-21 20:44:54 +02:00 |
|
|
kijai
|
c3e96fd6f9
|
Experimental clip embed enhancement through tiling
Allows more detail in the clip embeds as well as details from non square images without stretching
Idea and most of the code is from Matteo:
https://github.com/cubiq/ComfyUI_IPAdapter_plus/blob/9d076a3df0d2763cef5510ec5ab807f6632c39f5/utils.py#L181
|
2025-03-21 19:41:49 +02:00 |
|
|
kijai
|
5a2383621a
|
Update wanvideo_480p_I2V_endframe_example_01.json
|
2025-03-20 17:59:09 +02:00 |
|
|
kijai
|
e902e4a4ba
|
Create wanvideo_480p_I2V_endframe_example_01.json
|
2025-03-20 17:58:14 +02:00 |
|
|
kijai
|
91592949de
|
Fix latent2rgb scale
|
2025-03-20 17:56:28 +02:00 |
|
|
kijaiandraindrop313
|
f8f423ecee
|
Experimental end frame feature, refactor image to vid encoding
VAE modification code from:
https: //github.com/raindrop313/ComfyUI-WanVideoStartEndFrames/
Co-Authored-By: raindrop313 <87897973+raindrop313@users.noreply.github.com>
|
2025-03-20 16:48:04 +02:00 |
|
|
Jukka Seppänen
|
56bd434abc
|
Allow filtering control lora blocks too
|
2025-03-20 00:39:42 +02:00 |
|
|
kijai
|
635001f3e8
|
Fix torch.compile with lora reloading in control workflows
|
2025-03-19 22:47:53 +02:00 |
|
|
kijai
|
e5fbe79872
|
Update nodes.py
|
2025-03-18 23:07:11 +02:00 |
|
|
kijai
|
a53de321c5
|
Bump version
|
2025-03-18 21:35:37 +02:00 |
|
|
kijai
|
34f5258891
|
Update nodes.py
|
2025-03-18 21:35:05 +02:00 |
|
|
kijai
|
778765ba2a
|
Update nodes.py
|
2025-03-18 09:12:47 +02:00 |
|
|
kijai
|
557fe5c875
|
Fix up temporal masking
|
2025-03-18 09:09:41 +02:00 |
|
|
kijai
|
c4ed468967
|
Update nodes.py
|
2025-03-17 22:03:12 +02:00 |
|
|
kijai
|
7c8b4d09ae
|
Update nodes.py
|
2025-03-17 20:18:46 +02:00 |
|
|
kijai
|
71737192fc
|
Update nodes.py
|
2025-03-17 19:50:00 +02:00 |
|
|
kijai
|
6cd7f2296f
|
Add Moebius latent shift looping
https://github.com/YisuiTT/Mobius/
|
2025-03-17 19:45:52 +02:00 |
|
|
kijai
|
8262973402
|
Merge branch 'main' of https://github.com/kijai/ComfyUI-WanVideoWrapper
|
2025-03-17 17:49:42 +02:00 |
|
|
kijai
|
b827a43905
|
Create wanvideo_flowedit_I2V_example_01.json
|
2025-03-17 17:49:41 +02:00 |
|
|
Jukka Seppänen
|
7ea5e4e213
|
Merge pull request #249 from james-banks/patch-1
Update nodes.py to remove references to Hunyuan
|
2025-03-16 20:28:27 +02:00 |
|
|
James Banks
|
f109df75c2
|
Update nodes.py to remove references to Hunyuan
|
2025-03-16 18:27:29 +00:00 |
|
|
kijai
|
173aff2367
|
fix I2V flowedit and maybe allow compile with vram management
|
2025-03-16 03:00:14 +02:00 |
|
|
kijai
|
b18fafce2b
|
Update nodes.py
|
2025-03-16 01:52:02 +02:00 |
|
|
kijai
|
81a08d0e59
|
Make non_blocking offloading optional for low RAM usecases
|
2025-03-16 01:48:45 +02:00 |
|
|
kijai
|
f28d3f4225
|
somewhat working tiny vae previews
|
2025-03-15 23:12:38 +02:00 |
|
|
kijai
|
d455cc89a3
|
vram management fix
|
2025-03-15 16:40:39 +02:00 |
|
|
kijai
|
3aa573a74f
|
Update nodes.py
|
2025-03-15 16:25:19 +02:00 |
|
|
kijai
|
58e5737032
|
Add option to use comfy native RoPE calculations
comfy rope doesn't use complex numbers and can be torch.compiled, then it's faster and uses less memory
|
2025-03-15 15:45:53 +02:00 |
|
|
kijai
|
66893bf39b
|
taehv experiments
|
2025-03-15 13:06:29 +02:00 |
|
|
kijai
|
976ae48a13
|
Update wanvideo_1_3B_control_example_01.json
|
2025-03-15 11:14:44 +02:00 |
|