| Age | Commit message (Collapse) | Author |
|---|
|
Implement API get-memory
|
|
|
|
Move PR template so github could use it
|
|
Tests fixes and additions
|
|
|
|
|
|
|
|
Allow mixed image sizes in TI/HN training
|
|
|
|
|
|
CI: Use native actions/setup-python caching
|
|
instances of Protocol in code
add some whitespace between functions to be in line with other code in the repo
|
|
Add fallback for Protocol import
|
|
|
|
Add support for loading VAEs from safetensors files
|
|
|
|
Update hints.js
|
|
add a visual effect to inactive hires fix elements
|
|
|
|
|
|
|
|
|
|
Fix quicksetting name overlapping with its controls.
|
|
Fix training for newer PyTorch builds
|
|
Use an actual label for feature requests.
|
|
remove calls to locals()
add a test for img2img with script
|
|
Run scripts from API
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Partial revert
|
|
|
|
|
|
increase upscale api validation limit
|
|
|
|
Add Birch-san's sub-quadratic attention implementation
|
|
|
|
Small touch up to hints
|
|
make it actually account for all relevant sliders and calculate dimensions correctly
|
