huggingface / huggingface/open-muse
Maybe also do asymmetric timesteps
Open
- Dominant language
- Python
- Stars
- 359
- Forks
- 30
- PR merge metrics
- No merged PRs in 30d
Description
Since you mentioned using self-conditioning from Bit Diffusion [here](https://github.com/huggingface/muse#conduct-text2image-experiments-on-cc12m), maybe it also makes sense to use asymmetric timesteps as explored in the Bit Diffusion paper?
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.