FID doesn't reward high-resolution detail. the inception feature size is 299x299! so we are forced to downsample our FFHQ-1024 samples to compute FID.
it also doesn't punish poor detail either! this advantages latent diffusion, which can claim to achieve a high resolution but without actually needing to have correct textures to get good metrics.
it also doesn't punish poor detail either! this advantages latent diffusion, which can claim to achieve a high resolution but without actually needing to have correct textures to get good metrics.