DiffBIR icon indicating copy to clipboard operation
DiffBIR copied to clipboard

Official codes of DiffBIR: Towards Blind Image Restoration with Generative Diffusion Prior

Results 86 DiffBIR issues
Sort by recently updated
recently updated
newest added

I started training with about 2000 images with a batch size of 10. 1. How long does traning take for 2000 images set? Currently, it is at about 800 Epoch...

Hello, I wanted to ask if there are any plans regards using other stable diffusion models. I can imagine that stable diffusion models which are fine-tuned on higher resolution images...

I noticed that you've removed the DDIM option in the current version of the code, even though it didn't seem to work in the initial version. Sampling efficiency is one...

**1**. When I try to run ━ _conda install xformers==0.0.16 -c xformers_ , I receive the following message: ``` Collecting package metadata (current_repodata.json): done Solving environment: failed with initial frozen...

I see that OpenXLab has issues every day, is it possible that you hot DIffBIR on hugging face or replicate? They're more reliable

Team, When I try to run this code, I get the following error when pressing run after uploading a photo: RuntimeError: CUDA out of memory. Tried to allocate 20.00 MiB...

HuggingFace -> Hugging Face