@madebyollin
Thanks for pointing this out, unfortunately that's a limitation on current method and one has to construct separate reference batches for different conditions. But please try STF if you can maintain these batches! (naive DSM is STF with batch size=1)
Get ready to upgrade your diffusion models😻! Our
#iclr2023
paper reduces variance in denoising score-matching, improving image quality, stability, and training speed. Experience the best image generation with current SOTA FID of 1.90 on CIFAR-10
@xuyilun2
Clever! Is there a path to adapt this technique for conditional diffusion? Naively, it seems like STF on class-conditioned ImageNet would need 1000 separate reference batches :(