Junsong Chen

SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer

PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis

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

Support for miscellaneous image models. Currently supports: DiT, PixArt, HunYuanDiT, MiaoBi, and a few VAEs.