Age | Commit message (Collapse) | Author |
|
add textinfo to progress api response
|
|
Set TQDM progress bar and state textinfo description
|
|
Fix prompt parser default step transformer
|
|
TypeError: expected str, bytes or os.PathLike object, not NoneType
|
|
|
|
|
|
|
|
|
|
|
|
Fix keyboard navigation in modal image viewer
|
|
|
|
|
|
|
|
|
|
Support loading textual inversion embeddings from safetensors files
|
|
Expose XY Grid module to extensions
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Make VENV environment variable accept absolute path instead of relative path.
|
|
|
|
|
|
add fallback for when quick model creation fails
|
|
prevent .vae.safetensors files from being listed as stable diffusion models
|
|
Fix issues with testing process
|
|
to speedup creating sd model from config
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Variable dropout rate
|
|
Implements variable dropout rate from #4549
Fixes hypernetwork multiplier being able to modified during training, also fixes user-errors by setting multiplier value to lower values for training.
Changes function name to match torch.nn.module standard
Fixes RNG reset issue when generating previews by restoring RNG state
|
|
allow model load if previous model failed
|
|
follow-up for pr #6466 to relax response type check enforcement in get_memory
|
|
|
|
|
|
enabled
|
|
Implement API get-memory
|
|
|
|
Move PR template so github could use it
|
|
Tests fixes and additions
|
|
|
|
|
|
|
|
Allow mixed image sizes in TI/HN training
|