Viewing profile — stefanbaumann

The models presented in the paper are trained on class-conditional ImageNet (where the input is Gaussian noise and one of 1000 classes, e.g., "car") and unconditional FFHQ (where t…

Not yet, we focused on the architecture for this paper. I totally agree with you though - pixel space is generally less limiting than a latent space for diffusion, so we would expe…

Both Latent Consistency Models and Adversarial Diffusion Distillation (the method behind SDXL Turbo) are methods that do not depend on any specific properties of the backbone. So, …

The "input image" is just the noisy sample from the previous timestep, yes. The overall architecture diagram does not explicitly show the conditioning mechanism, which is a small s…

Thanks a lot! Yeah, the main motivation was trying to find a way to enable transformers to do high-resolution image synthesis: transformers are known to scale well to extreme, mult…

It's already a thing [1]. They also have a project website [2] with some nice videos, although the code hasn't yet been released. [1] https://arxiv.org/abs/2308.09713 [2] https://d…