<h1 id="introduction-from-alimama-1hppk1thb">Introduction from <a target="_blank" rel="ugc" href="https://huggingface.co/alimama-creative/FLUX.1-Turbo-Alpha">Alimama</a></h1>【This checkpoint is a 8-step distilled Lora, trained based on FLUX.1-dev model. We use a multi-head discriminator to improve the distill quality. Our model can be used for T2I, inpainting controlnet and other FLUX related models. The recommended guidance_scale=3.5 and lora_scale=1. Our Lower steps version will release later.】<h2 id="and-this-is-paseer-optimazed-version-rktvk36f6">And this is PAseer-Optimazed Version</h2><ol><li>Less influnce of Asian character trend than Alimama.</li><li>Avoiding adding extra things which not in prompts.</li><li>Less Storage Volume Usage-- 150 MB</li></ol>

Files with SHA256: 199b0b65ca22a5553ab6a3d768486b7aeee2d1c0ca68ebb8054e2d1ef29b9a6d