training decoder during Stage 2

csslc / CCSR

Official codes of CCSR: Improving the Stability of Diffusion Models for Content Consistent Super-Resolution

https://csslc.github.io/project-CCSR/

390 stars 30 forks source link

training decoder during Stage 2 #27

Open zhpenli opened 1 month ago

zhpenli commented 1 month ago

Thanks for the wonderful work! I noticed you only train 100 iterations for decoder, while 25k iterations for SD. Is it enough to train decoder for only 100 iterations? BTW, did you use combination of L1 loss, perceptual loss, and GAN loss to train decoder?

Thanks in advance!