
This model is an 8-step distilled lora version based on the FLUX.1 dev model. We use a specially designed discriminator to improve the quality of distillation. The model can be used for T2I, Inpainting controlnet, and other FLUX-related models. Recommended guidance_scale=3.5 and lora_scale=1.
This model is an 8-step distilled lora version based on the FLUX.1 dev model. We use a specially designed discriminator to improve the quality of distillation. The model can be used for T2I, Inpainting controlnet, and other FLUX-related models. Recommended guidance_scale=3.5 and lora_scale=1.