Extracted from: https://huggingface.co/GuangyuanSD/Z-Image-Distilled
Basic workflow: please refer to the Z-Image-Turbo official workflow (fully compatible with the official Z-Image-Turbo workflow)
Recommended inference parameters:
inference cfg: 1.0–2.5 (recommended range: 1.0~1.8; higher values enhance prompt adherence)
inference steps: 10–20 (10 steps for quick previews, 15–20 steps for more stable quality)
sampler / scheduler: Euler / simple, or res_m, or any other compatible sampler
LoRA compatibility is good; recommended weight: 0.6~1.0, adjust as needed.
Description
FAQ
Comments (4)
Hello 🙌 I'm sorry sir but, what is this LoRA for exactly? Thank you
It's a distilled z-image (from the non-turbo) allowing you to 1) save space 2) inference faster in ~10 - 20 steps instead of the usual 25 - 50. I extracted it from the checkpoint in the description below.
@anyMODE Thank you
And it's best combined with https://civitai.com/models/958009?modelVersionId=2642177 ... Together you will get the best results in less time.