https://openreview.net/forum?id=SRWs2wxNs7&referrer=%5Bthe%20profile%20of%20Zhijun%20Tu%5D(%2Fprofile%3Fid%3D~Zhijun_Tu1)
Diffusion Transformers (DiTs) introduce the transformer architecture to diffusion tasks for latent-space image generation. With an isotropic architecture that...
uditsdownsampletokensshaped