PixArt-\Sigma: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation

arXiv:2403.04692v1 Announce Type: new
Abstract: In this paper, we introduce PixArt-\Sigma, a Diffusion Transformer model~(DiT) capable of directly generating images at 4K resolution. PixArt-\Sigma represents a significant advancement over its predecessor, PixArt-\alpha, offering images of markedly higher fidelity and improved alignment with text prompts. A key feature of PixArt-\Sigma is its training efficiency. Leveraging the foundational pre-training of PixArt-\alpha, it evolves from the `weaker' baseline to a `stronger' model via incorporating higher quality data, a process we term "weak-to-strong training". …

abstract advancement alignment alpha arxiv cs.cv diffusion feature fidelity image image generation images key paper pixart prompts text text-to-image training transformer transformer model type