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

Junsong Chen, Chongjian GE, Enze Xie*, Yue Wu, Lewei Yao, Xiaozhe Ren, Zhongdao Wang, Ping Luo, Huchuan Lu, Zhenguo Li ;

"In this paper, we introduce , a Diffusion Transformer model (DiT) capable of directly generating images at 4K resolution. represents a significant advancement over its predecessor, , offering images of markedly higher fidelity and improved alignment with text prompts. A key feature of is its training efficiency. Leveraging the foundational pre-training of , it evolves from the ‘weaker’ baseline to a ‘stronger’ model via incorporating higher quality data, a process we term “weak-to-strong training”. The advancements in are twofold: (1) High-Quality Training Data: incorporates superior-quality image data, paired with more precise and detailed image captions. (2) Efficient Token Compression: we propose a novel attention module within the DiT framework that compresses both keys and values, significantly improving efficiency and facilitating ultra-high-resolution image generation. Thanks to these improvements, achieves superior image quality and user prompt adherence capabilities with significantly smaller model size (0.6B parameters) than existing text-to-image diffusion models, such as SDXL (2.6B parameters) and SD Cascade (5.1B parameters). Moreover, ’s capability to generate 4K images supports the creation of high-resolution posters and wallpapers, efficiently bolstering the production of high-quality visual content in industries such as film and gaming. T2I Synthesis, Diffusion Transformer, Efficient Model"