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.

innovaciones 3e4b7fb869 Remove double loading message		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	add the bitton to paste parameters into UI for txt2img, img2img, and pnginfo tabs	3 years ago
gfpgan_model.py	gfpgan: just download the damn model	3 years ago
images.py	fix for inpaint at full resolution breaking if you have an NN upscaler.	3 years ago
img2img.py	Add option to always log generation info	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	Clear no longer needed VRAM during a 'highres fix' generation created during the first sampling before doing the second (img2img) sampling. Makes it possible to use the feature on an 8GB card.	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	Option to use advanced upscalers with normal img2img	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	Remove double loading message	3 years ago