Extracted from: <a target="_blank" rel="ugc" href="https://huggingface.co/GuangyuanSD/Z-Image-Distilled">https://huggingface.co/GuangyuanSD/Z-Image-Distilled</a> Basic workflow: please refer to the Z-Image-Turbo official workflow (fully compatible with the official Z-Image-Turbo workflow)Recommended inference parameters:<ul><li>inference cfg: 1.0–2.5 (recommended range: 1.0~1.8; higher values enhance prompt adherence)</li><li>inference steps: 10–20 (10 steps for quick previews, 15–20 steps for more stable quality)</li><li>sampler / scheduler: Euler / simple, or res_m, or any other compatible sampler</li></ul>LoRA compatibility is good; recommended weight: 0.6~1.0, adjust as needed.

Z-Image (base) Distilled Lora | Extracted

RedZDX_ZI_Turbo_r128.safetensors

RedZDX R128

Files with SHA256: cf6b5c6f30ead33d6bc1f36df4035d3813fca995af76081e54a667b9c836a1d0