xinyun/ComfyUI-CogVideoXWrapper
1
0
Fork 0
mirror of https://git.datalinker.icu/kijai/ComfyUI-CogVideoXWrapper.git synced 2025-12-08 20:34:23 +08:00
Code Issues Packages Projects Releases Wiki Activity
338 Commits 7 Branches 0 Tags
Commit Graph

338 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
kijai
dbc63f622d some tweaks to test I2V with context windows, add context window preview 2025-01-28 22:40:58 +02:00
kijai
fed499e971 Update pyproject.toml 2025-01-28 16:39:21 +02:00
Jukka Seppänen
f3dda43cdf
Update readme.md 2025-01-23 11:18:57 +02:00
kijai
126322139f teacache tweaks 2025-01-20 22:22:45 +02:00
kijai
90e8367f5e Better sampling preview and support VHS live latent preview 2025-01-20 21:53:00 +02:00
kijai
76f7930d07 Add TeaCache 2025-01-20 17:06:06 +02:00
kijai
3d2ee02d83 delete LoRAs if fused to save memory 2025-01-20 17:04:42 +02:00
kijai
51daeef1b7 sageattn fp8/GGUF fix 2025-01-20 11:23:02 +02:00
Jukka Seppänen
5bca0548d9
Update readme.md 2025-01-18 21:27:57 +02:00
kijai
97b7b18f35 Create cut_and_drag_for_noisewarp_01.json 2025-01-18 21:20:24 +02:00
kijai
f5454aa806 rename workflows folder, add NoiseWarp example 2025-01-18 21:14:04 +02:00
kijai
3a38d01414 Allow using precalculated noise 
only when denoise is 1.0 for now
 2025-01-18 17:02:41 +02:00
kijai
8c5e4f812d support other tora model 2025-01-14 14:39:44 +02:00
Jukka Seppänen
eaaa0f6e1a
Create LICENSE 2024-12-24 02:09:15 +02:00
kijai
25d0ede406 fix 2024-12-22 18:12:07 +02:00
kijai
f16d38a5d2 Add Enhance-A-Video 
https://github.com/NUS-HPC-AI-Lab/Enhance-A-Video
 2024-12-22 01:26:18 +02:00
kijai
fcc0f3e65a Update pipeline_cogvideox.py 2024-12-20 17:00:42 +02:00
kijai
0758d2d016 fix 2024-12-17 09:10:03 +02:00
kijai
b5eefbf4d4 Initial support for Fun 1.5 
I2V works, interpolation doesn't seem to (not sure if it should)
 2024-12-17 01:16:11 +02:00
Jukka Seppänen
795f8b0565
Merge pull request #311 from glide-the/fix_pos_embedding 
Add cogvideox-2b-img2vid CogVideoXModelLoader support
 2024-12-08 11:52:12 +02:00
glide-the
d9d30f24bb Add cogvideox-2b-img2vid CogVideoXModelLoader support 
fix for transformer model patch_embed.pos_embedding dtype
or at add line ComfyUI-CogVideoXWrapper/embeddings.py:129 code
pos_embedding = pos_embedding.to(embeds.device, dtype=embeds.dtype)
 2024-12-06 15:58:52 +08:00
kijai
729a6485ea expose sageattn 2.0.0 functions 
_cuda versions seem to be required on RTX 30xx -series GPUs for sageattn + CogVideoX 1.5
 2024-12-01 18:45:10 +02:00
kijai
411791c748 Update model_loading.py 2024-11-27 20:36:21 +02:00
kijai
7a10e732bb update cogvideox_Fun_180_orbit -example 2024-11-27 12:14:15 +02:00
Jukka Seppänen
1ade29084e Merge branch 'main' of https://github.com/kijai/ComfyUI-CogVideoXWrapper 2024-11-24 22:27:27 +02:00
Jukka Seppänen
f1b3bc0abf error earlier if sageattention fails to import 2024-11-24 22:27:26 +02:00
kijai
c71bca9350 Update pipeline_cogvideox.py 2024-11-24 18:34:00 +02:00
Jukka Seppänen
8d6e53b556 Allow compiling VAE as well 2024-11-23 17:08:57 +02:00
kijai
9baf100366 fix 2b image2vid 2024-11-22 23:13:14 +02:00
Jukka Seppänen
6c7068b5bc
Update nodes.py 2024-11-22 22:38:51 +02:00
kijai
895d3b83a4 Update model_loading.py 2024-11-21 03:05:51 +02:00
kijai
276a045a57 use selected load device as LoRA load device too 2024-11-21 02:46:07 +02:00
kijai
e52dc36bc5 Update model_loading.py 2024-11-20 21:28:53 +02:00
kijai
e5fc7c1bf3 Allow mixing Fun and not fun loras 2024-11-20 21:24:51 +02:00
kijai
e187cfe22f Allow loading the "Rewards" LoRAs into 1.5 as well (for what it's worth) 2024-11-20 19:18:40 +02:00
kijai
573150de28 fix Tora when no autocast 2024-11-20 16:41:34 +02:00
kijai
b74aa75026 Don't use autocast with fp/bf16 2024-11-20 14:22:10 +02:00
Jukka Seppänen
b9f7b6e338
Merge pull request #261 from Dango233/Dango233-patch-1 
Fix fused sdpa
 2024-11-20 12:37:26 +02:00
Dango233
b31a025673
Fix fused sdpa 2024-11-20 17:40:28 +08:00
kijai
ce329e0dce fix T2V 2024-11-20 10:17:11 +02:00
kijai
de7e069286 fix noise augment 2024-11-20 02:12:56 +02:00
kijai
5cc570a467 Add start/end percent to image_conds 2024-11-20 02:07:29 +02:00
kijai
b9688f3cd2 Add strength parameter for image encode 2024-11-20 01:32:05 +02:00
kijai
ecd067260c Add CogVideoX-Fun-V1.1-5b-Control 
https://huggingface.co/alibaba-pai/CogVideoX-Fun-V1.1-5b-Control
 2024-11-20 01:23:54 +02:00
kijai
c9efefe736 Update cogvideox_1_5_5b_I2V_01.json 2024-11-19 20:33:58 +02:00
kijai
f7afa7d3be Update cogvideox_1_5_5b_I2V_01.json 2024-11-19 20:33:15 +02:00
kijai
ebd6a3a4e8 update workflows to save_output enabled by default 2024-11-19 20:32:30 +02:00
kijai
41a0f33381 Update model_loading.py 2024-11-19 20:27:31 +02:00
kijai
1cfe0835f5 fix GGUF loader 2024-11-19 20:23:47 +02:00
kijai
b0eabeba24 fix comfy attention output shape 2024-11-19 20:18:13 +02:00