- 12 Jan, 2023 2 commits
-
-
AUTOMATIC1111 authored
add textinfo to progress api response
-
AUTOMATIC1111 authored
Set TQDM progress bar and state textinfo description
-
- 11 Jan, 2023 23 commits
-
-
AUTOMATIC1111 authored
Fix prompt parser default step transformer
-
AUTOMATIC authored
fix for an error caused by skipping initialization, for realsies this time: TypeError: expected str, bytes or os.PathLike object, not NoneType
-
Vladimir Mandic authored
-
Vladimir Mandic authored
-
catboxanon authored
-
catboxanon authored
-
catboxanon authored
-
AUTOMATIC1111 authored
Fix keyboard navigation in modal image viewer
-
Alexey Shirokov authored
-
AUTOMATIC authored
-
AUTOMATIC authored
-
AUTOMATIC authored
-
AUTOMATIC1111 authored
Support loading textual inversion embeddings from safetensors files
-
AUTOMATIC1111 authored
Expose XY Grid module to extensions
-
space-nuko authored
-
catboxanon authored
-
catboxanon authored
-
Lee Bousfield authored
-
AUTOMATIC authored
-
AUTOMATIC authored
-
AUTOMATIC1111 authored
Make VENV environment variable accept absolute path instead of relative path.
-
Vladimir Repin authored
-
AUTOMATIC authored
-
- 10 Jan, 2023 15 commits
-
-
AUTOMATIC authored
add fallback for when quick model creation fails
-
AUTOMATIC authored
prevent .vae.safetensors files from being listed as stable diffusion models
-
AUTOMATIC1111 authored
Fix issues with testing process
-
AUTOMATIC authored
disable torch weight initialization and CLIP downloading/reading checkpoint to speedup creating sd model from config
-
Vladimir Repin authored
-
AUTOMATIC authored
-
Andrey authored
-
Andrey authored
-
Andrey authored
-
Andrey authored
-
AUTOMATIC1111 authored
Variable dropout rate
-
aria1th authored
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
-
AUTOMATIC1111 authored
allow model load if previous model failed
-
AUTOMATIC1111 authored
follow-up for pr #6466 to relax response type check enforcement in get_memory
-
Vladimir Mandic authored
-