A step and cfg distill lora for Z-Image Base by alibaba-pai.
Sampler: Euler/Simple
CFG: 1.1 (to use negatives when needed)
Steps: 8 (8 steps), 4 (4 steps)
Don't use sageattention, Z-Image feels bad with it.
Original creator's notes:
A Distill LoRA for Z-Image that distills both steps and CFG. Compared to Z-Image-Fun-Lora-Distill-8-Steps.safetensors, its colors are more consistent with the original model, and the skin texture is better.
This is a Distill LoRA for Z-Image that distills both steps and CFG. It does not use any Z-Image-Turbo related weights and is trained from scratch. It is compatible with other Z-Image LoRAs and Controls.
This model will slightly reduce the output quality and change the output composition of the model. For specific comparisons, please refer to the Results section.
The purpose of this model is to provide fast generation compatibility for Z-Image derivative models, not to replace Z-Image-Turbo.






