Re:Direct pixel-space megapixel image generation with diffus...
by Birch-san on Tuesday January 23, 2024 @07:17PM
(#39111900)
the FFHQ-1024 examples shouldn't be blurry. you can download the originals from the project page[0] — click any image in the teaser, or download our 50k samples.
the ImageNet-256 examples also aren't typically blurry (but they are 256x256 so your viewer may be bicubic scaling them or something). the ImageNet dataset _can_ have blurry, compressed or low resolution training samples, which can afflict some classes more than others, and we learn to produce samples like the training set.
the ImageNet-256 examples also aren't typically blurry (but they are 256x256 so your viewer may be bicubic scaling them or something). the ImageNet dataset _can_ have blurry, compressed or low resolution training samples, which can afflict some classes more than others, and we learn to produce samples like the training set.
[0] https://crowsonkb.github.io/hourglass-diffusion-transformers...