xinyun/ComfyUI-CogVideoXWrapper
1
0
Fork 0
mirror of https://git.datalinker.icu/kijai/ComfyUI-CogVideoXWrapper.git synced 2025-12-09 04:44:22 +08:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'main' of https://github.com/kijai/ComfyUI-CogVideoXWrapper

Browse Source
This commit is contained in:
kijai 2024-08-27 18:01:43 +03:00
commit a30037feb1
1 changed files with 8 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
readme.md
View File

@ -1,11 +1,19 @@
# WORK IN PROGRESS
## Update
5b model is now also supported for basic text2vid: https://huggingface.co/THUDM/CogVideoX-5b
It is also autodownloaded to `ComfyUI/models/CogVideo/CogVideoX-5b`, text encoder is not needed as we use the ComfyUI T5.
https://github.com/user-attachments/assets/991205cc-826e-4f93-831a-c10441f0f2ce
Requires diffusers 0.30.1 (this is specified in requirements.txt)
Uses same T5 model than SD3 and Flux, fp8 works fine too. Memory requirements depend mostly on the video length.
VAE decoding seems to be the only big that takes a lot of VRAM when everything is offloaded, peaks at around 13-14GB momentarily at that stage.
Sampling itself takes only maybe 5-6GB.
Hacked in img2img to attempt vid2vid workflow, works interestingly with some inputs, highly experimental.
https://github.com/user-attachments/assets/e6951ef4-ea7a-4752-94f6-cf24f2503d83