Kevin Cheung

Quality-Aware Modulation for Diffusion Transformers

Luke Budny, Yuhong Guo, Kevin Cheung

Modern text-to-image diffusion models, such as diffusion transformers (DiT), rely on timestep or prompt embeddings to modulate the strength of the denoising process in each timestep. While this modulation communicates the current noise level, it does not provide any quality-aware…Read more