huggingface / huggingface/open-muse

Maybe also do asymmetric timesteps

Open
#3 0 comments 0 reactions 0 assignees View on GitHub
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.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.