| Age | Commit message (Collapse) | Author |
|---|
|
|
|
|
|
torch.cuda.empty_cache() defaults to cuda:0 device unless explicitly …
|
|
|
|
|
|
add an option to choose a different temporary directory in the UI
add an option to cleanup the selected temporary directory at startup
|
|
otherwise first. Updating torch_gc() to use the device set by --device-id if specified to avoid OOM edge cases on multi-GPU systems.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Enable override_settings to take effect for hypernetworks
|
|
|
|
|
|
|
|
|
|
|
|
Add --server-name to the list of arguments considered insecure
|
|
feat: add http basic authentication for api
|
|
|
|
|
|
[API][Feature] Add Skip endpoint
|
|
Hide Gradio progress again
|
|
alternative solution to #4765
|
|
Add interrupt button to preprocessing
|
|
Cleanly undo circular hijack to fix tiling getting stuck on #4818
|
|
negative prompts in a batch
|
|
Fix unbounded prompt growth/determinism in scripts that loop
|
|
only appear if using inpainting model, made it possible to read the setting from it using the blue arrow button
|
|
Add 'Inpainting strength' to the 'generation_params' of 'infotext' (params.txt or png chunks)
|
|
Fix: `error: Your local changes to the following files would be overwritten by merge` when trying to update extensions in WSL2 Docker
|
|
Remove no longer necessary code from VAE selector, fix #4651
|
|
sampler index
|
|
|
|
|
|
Option to use selected VAE as default fallback instead of primary option
|
|
Misc
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
