mirror of
https://git.datalinker.icu/kijai/ComfyUI-CogVideoXWrapper.git
synced 2025-12-09 21:04:23 +08:00
Update readme.md
This commit is contained in:
parent
e98c428e1e
commit
1561834955
@ -1,11 +1,19 @@
|
|||||||
# WORK IN PROGRESS
|
# 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)
|
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.
|
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.
|
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.
|
Sampling itself takes only maybe 5-6GB.
|
||||||
|
|
||||||
|
|
||||||
Hacked in img2img to attempt vid2vid workflow, works interestingly with some inputs, highly experimental.
|
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
|
https://github.com/user-attachments/assets/e6951ef4-ea7a-4752-94f6-cf24f2503d83
|
||||||
|
|||||||
Loading…
x
Reference in New Issue
Block a user