this post was submitted on 15 Dec 2025
2 points (100.0% liked)

Stable Diffusion

5225 readers
4 users here now

Discuss matters related to our favourite AI Art generation technology

Also see

Other communities

founded 2 years ago
MODERATORS
 

This model is a LoRA designed to repair the acceleration capability of Z-Image Turbo LoRA.

LoRAs directly trained on Z-Image Turbo lose their acceleration ability, resulting in blurry images when generated under accelerated settings (steps=8, cfg=1), while the images generated under non-accelerated settings (steps=30, cfg=2) are normal.

Github: https://github.com/modelscope/DiffSynth-Studio/blob/main/docs/en/Model_Details/Z-Image.md

no comments (yet)
sorted by: hot top controversial new old
there doesn't seem to be anything here