Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

batch luminance calculation fix for non-8bit RGB source images | vae cache fix for SDXL / legacy SD training | epoch / resume step fix for a corner case where the path to the training data includes the dataset name #377

Merged
merged 6 commits into from
May 3, 2024

Commits on May 2, 2024

  1. vae: fix encode via prepare_sample

    bghira committed May 2, 2024
    Configuration menu
    Copy the full SHA
    75bd2d9 View commit details
    Browse the repository at this point in the history
  2. vaecache: add training sample factory

    bghira committed May 2, 2024
    Configuration menu
    Copy the full SHA
    5de3517 View commit details
    Browse the repository at this point in the history
  3. follow-up vae cache fixes for sd/xl models

    bghira committed May 2, 2024
    Configuration menu
    Copy the full SHA
    ef7ee9d View commit details
    Browse the repository at this point in the history

Commits on May 3, 2024

  1. correct an issue where resumption might not step from last epoch when…

    … the dataset name is in a parent folder node
    bghira committed May 3, 2024
    Configuration menu
    Copy the full SHA
    b6e670f View commit details
    Browse the repository at this point in the history
  2. Configuration menu
    Copy the full SHA
    c47949b View commit details
    Browse the repository at this point in the history
  3. Merge pull request #376 from Beinsezii/calc_lum_rgb

    Convert image to accepted format for calculate_luminance
    bghira authored May 3, 2024
    Configuration menu
    Copy the full SHA
    d2a96cc View commit details
    Browse the repository at this point in the history