The question about different size images to compress

[AlbertLin0]

The 'elic' model could deal with different size of images, because the arch is not sensitive to different size inputs. But diffusion model has a definite input/output size based on pixel level.

The question is how to compress different size images?

[tongdaxu]

Currently the image size is determined by your base diffusion model. This repo use pretrained ADM with image size 256^2. So we can only work with 256^2 image for one pass