jd-opensource / jd-opensource/JoyAI-Image

Any distilled weights for fewer-step inference?

Open
#2 2 comments 0 reactions 0 assignees View on GitHub
Dominant language
Python
Stars
2.2k
Forks
165
PR merge metrics
No merged PRs in 30d

Description

I'm wondering if there are any plans to release 4-step distillation weights that could replace the current [lightx2v/Qwen-Image-Edit-2511-Lightning](https://huggingface.co/lightx2v/Qwen-Image-Edit-2511-Lightning) model I'm using? A more aggressively distilled version would be really helpful for faster inference.

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.