Haoming02/sd-webui-old-photo-restoration
1
0
Fork 0
mirror of https://github.com/Haoming02/sd-webui-old-photo-restoration.git synced 2026-11-05 00:28:04 +00:00
Code Issues Projects Packages Wiki Activity
An Extension for Automatic1111 Webui for Bringing Old Photo Back to Life
32 commits 1 branch 1 tag 1,003 KiB
  • Python 100%
Find a file
Exact
Haoming 99c5f47f37 bump
2025-06-30 12:28:39 +08:00
.github Support Me 🤗 2024-03-24 21:30:36 +08:00
lib_bopb2l@bfe2d3f480 bump 2025-06-30 12:28:39 +08:00
scripts bump 2025-06-30 12:28:39 +08:00
.gitignore submodule 2024-11-04 15:53:34 +08:00
.gitmodules shallow 2024-11-05 10:14:30 +08:00
install.py bump 2025-06-30 12:28:39 +08:00
LICENSE clean ups 2024-03-25 12:37:54 +08:00
preload.py submodule 2024-11-04 15:53:34 +08:00
README.md submodule 2024-11-04 15:53:34 +08:00
requirements.txt submodule 2024-11-04 15:53:34 +08:00
UI.png clean ups 2024-03-25 12:37:54 +08:00

README.md

SD Webui Old Photo Restoration

This is an Extension for the Automatic1111 Webui, which allows you to perform Bringing-Old-Photos-Back-to-Life natively.

Compatible with Forge

Original Paper: https://arxiv.org/abs/2004.09484

Original Repo: https://github.com/microsoft/Bringing-Old-Photos-Back-to-Life (includes some example images)

Requirements

  1. Install this Extension
  2. Download global_checkpoints.zip from Releases
  3. Extract and put the checkpoints folder (not just the files) into ~webui/extensions/sd-webui-old-photo-restoration/lib_bopb2l/Global
  4. Download face_checkpoints.zip from Releases
  5. Extract and put the checkpoints folder (not just the files) into ~webui/extensions/sd-webui-old-photo-restoration/lib_bopb2l/Face_Enhancement
  6. Download shape_predictor_68_face_landmarks.zip from Releases
  7. Extract the .dat file into ~webui/extensions/sd-webui-old-photo-restoration/lib_bopb2l/Face_Detection

The Releases page includes the original links, as well as the backups mirrored by myself

Another mirror: Google Drive

How to Use

After installing this Extension, there will be an Old Photo Restoration section in the Extras tab

  1. Expand the dropdown to enable the features
  2. Upload the image(s) to be processed
  3. Adjust the settings as needed
  4. Click Generate
  5. The result(s) will show up on the right once the process finishes

Settings

  • Processing Order: Choose between upscaling the image first or perform the restoration first
  • Process Scratch: Remove scratches from the image
  • Face Restore: Use a pre-trained model to improve the faces
    • (This is different from the Webui built-in ones)
  • High Resolution: Use higher parameters to do the processing
    • (Only has an effect when either Process Scratch or Face Restore is also enabled)
  • Use CPU: Enable this if you do not have a Nvidia GPU or are getting Out of Memory Error