FineDiffusion: Scaling up Diffusion Models for Fine-grained Image Generation with 10,000 Classes

arXiv:2402.18331v1 Announce Type: new
Abstract: The class-conditional image generation based on diffusion models is renowned for generating high-quality and diverse images. However, most prior efforts focus on generating images for general categories, e.g., 1000 classes in ImageNet-1k. A more challenging task, large-scale fine-grained image generation, remains the boundary to explore. In this work, we present a parameter-efficient strategy, called FineDiffusion, to fine-tune large pre-trained diffusion models scaling to large-scale fine-grained image generation with 10,000 categories. FineDiffusion significantly accelerates training and …

arxiv cs.cv diffusion diffusion models fine-grained image image generation scaling scaling up type