xinyun/ComfyUI-CogVideoXWrapper
1
0
Fork 0
mirror of https://git.datalinker.icu/kijai/ComfyUI-CogVideoXWrapper.git synced 2026-01-23 12:24:23 +08:00
Code Issues Packages Projects Releases Wiki Activity

Update readme.md

Browse Source
This commit is contained in:
Jukka Seppänen 2024-10-07 02:36:21 +03:00 committed by GitHub
parent f657e0d56e
commit a2200c47ba
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 17 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

17
readme.md
View File

@ -1,4 +1,21 @@
# WORK IN PROGRESS
## Update5
This week there's been some bigger updates that will most likely affect some old workflows, sampler node especially probably need to be refreshed (re-created) if it errors out!
New features:
- Initial context windowing with FreeNoise noise shuffling mainly for vid2vid and pose2vid pipelines for longer generations, haven't figured it out for img2vid yet
- GGUF models and tiled encoding for I2V and pose pipelines (thanks to MinusZoneAI)
- [sageattention](https://github.com/thu-ml/SageAttention) support (Linux only) for a speed boost, I experienced ~20-30% increase with it, stacks with fp8 fast mode, doesn't need compiling
- Support CogVideoX-Fun 1.1 and it's pose models with additional control strenght and application step settings, this model's input does NOT have to be just dwpose skeletons, just about anything can work
- Support LoRAs
https://github.com/user-attachments/assets/ddeb8f38-a647-42b3-a4b1-c6936f961deb
https://github.com/user-attachments/assets/c78b2832-9571-4941-8c97-fbcc1a4cc23d
https://github.com/user-attachments/assets/d9ed98b1-f917-432b-a16e-e01e87efb1f9
## Update4
Initial support for the official I2V version of CogVideoX: https://huggingface.co/THUDM/CogVideoX-5b-I2V