Preprint
Aug 2026
An Empirical Study of Training Pixel-Space Text-to-Image Diffusion Models
This paper investigates an increasingly important topic in generative modeling: pixel-space diffusion models. Although numerous studies have explored this topic, most focus on small-scale or class-conditional settings. Consequently, a practical recipe for training pixel-space models that rival or exceed well-establishe...
Deng-Yang Jiang, Ruoyi Du, Zhen-Nan Chen et al.
· 3 citations