How to compute the FID of text-image models?

CompVis / stable-diffusion

A latent text-to-image diffusion model

https://ommer-lab.com/research/latent-diffusion-models/

Other

68.43k stars 10.18k forks source link

How to compute the FID of text-image models? #583

Open jsttlgdkycy opened 1 year ago

jsttlgdkycy commented 1 year ago

I'm curious about what dataset does FIDs shown in CLIP-FID curve computed with? And are the text-image FIDs reported in https://arxiv.org/abs/2112.10752 be computed use one of these four models? I would be very grateful if someone can tell me~

sir-zengqi commented 1 month ago

Have you solved this problem? I also want to know how this FID is calculated and how to reproduce it.