Flash Diffusion: Accelerating Any Conditional Diffusion Model for Few Steps Image Generation

Abstract

In this paper, we propose an efficient, fast, and versatile distillation method to accelerate the generation of pre-trained diffusion models. The method reaches state-of-the-art performances in terms of FID and CLIP-Score for few steps image generation on the COCO2014 and COCO2017 datasets, while requiring only several GPU hours of training and fewer trainable parameters than existing methods. In addition to its efficiency, the versatility of the method is also exposed across several tasks such as *text-to-image*, *inpainting*, *face-swapping*, *super-resolution* and using different backbones such as UNet-based denoisers (SD1.5, SDXL), DiT (Pixart) and MMDiT (SD3), as well as adapters. In all cases, the method allowed to reduce drastically the number of sampling steps while maintaining very high-quality image generation.