You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

AUTOMATIC 600cc0342d added support for setting hires fix from pasted prompts ... added more robust detection of last line with parameters for pasted prompts		3 years ago
..
codeformer	clarification for settings; another comment about copied files	3 years ago
artists.py	added random artist button	3 years ago
codeformer_model.py	Removed stray references to shared.device_codeformer.	3 years ago
devices.py	first attempt to produce crrect seeds in batch	3 years ago
errors.py	Allow TF32 in CUDA for increased performance #279	3 years ago
esrgam_model_arch.py	ESRGAN support	3 years ago
esrgan_model.py	Fix/Revert opts name from GAN to ESRGAN	3 years ago
extras.py	add the bitton to paste parameters into UI for txt2img, img2img, and pnginfo tabs	3 years ago
face_restoration.py	codeformer support	3 years ago
generation_parameters_copypaste.py	added support for setting hires fix from pasted prompts	3 years ago
gfpgan_model.py	gfpgan: just download the damn model	3 years ago
images.py	added [styles] filename pattern	3 years ago
img2img.py	Disable 'batch img2img' when launched with --hide-ui-dir-config	3 years ago
interrogate.py	fix for Error Interrogating when user has garbage in text files #479	3 years ago
ldsr_model.py	Add LDSR and "GoLatent?" Upscaling (#763)	3 years ago
lowvram.py	memory optimization for CLIP interrogator	3 years ago
masking.py	make inpaint at full resolution option not discard useful pixels from the image	3 years ago
memmon.py	Add some error handling for VRAM monitor	3 years ago
paths.py	Add LDSR and "GoLatent?" Upscaling (#763)	3 years ago
processing.py	Reformat some changes from the previous commit.	3 years ago
prompt_parser.py	use model's dtype for #707	3 years ago
realesrgan_model.py	reworking #775	3 years ago
safety.py	put safety checker into a separate file because it's already crowded in processing	3 years ago
scripts.py	A big rework, just what you were secretly hoping for!	3 years ago
sd_hijack.py	--opt-split-attention now on by default for torch.cuda, off for others (cpu and MPS; because the option does not work there according to reports)	3 years ago
sd_models.py	display a more informative message when a checkpoint is not found	3 years ago
sd_samplers.py	added highres fix feature	3 years ago
shared.py	Disable 'batch img2img' when launched with --hide-ui-dir-config	3 years ago
styles.py	added a second style field	3 years ago
swinir.py	Update swinir.py	3 years ago
swinir_arch.py	Rename swinir_arch.py to modules/swinir_arch.py	3 years ago
txt2img.py	prevent saving settings with bogus values	3 years ago
ui.py	added support for setting hires fix from pasted prompts	3 years ago