search

zsyOAOA / ResShift

ResShift: Efficient Diffusion Model for Image Super-resolution by Residual Shifting (NeurIPS@2023 Spotlight, TPAMI@2024)
Other
944 stars 50 forks source link

Request for Source Code Related to Autoencoder for Gray-Scale Image Training #100

Open zhangjie20231127 opened 3 weeks ago

zhangjie20231127 commented 3 weeks ago

I have been working with your excellent project,and I noticed that the pre-trained autoencoder model (autoencoder_vq_f4.pth) is designed for RGB images. However, I am currently working with gray-scale images and would like to train a new autoencoder model tailored for this task.

Could you please point me to the source code or provide guidance on how I can adapt the current autoencoder model for gray-scale image training?

zsyOAOA commented 3 weeks ago

Please refer to the following link: https://github.com/CompVis/taming-transformers

zhangjie20231127 commented 3 weeks ago

Thank you！