Looped Diffusion Transformer
Improving text-to-image models has traditionally relied on increasing model size or the number of denoising steps. In this work, we explore an alternative way to scale computation by repeatedly running shared Transformer blocks within each denoising step, effectively increasing computational depth while keeping the par...
Yong Xien Chng, Tian-Yi Chen, Wen-Wen Tong et al.
· 0 citations