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 df57064093 do not load aesthetic clip model until it's needed ... add refresh button for aesthetic embeddings add aesthetic params to images' infotext		3 years ago
..
api	call sampler by name	3 years ago
codeformer	clarification for settings; another comment about copied files	3 years ago
hypernetworks	turns out LayerNorm also has weight and bias and needs to be pre-multiplied and trained for hypernets	3 years ago
textual_inversion	Merge branch 'ae'	3 years ago
aesthetic_clip.py	do not load aesthetic clip model until it's needed	3 years ago
artists.py	added random artist button	3 years ago
bsrgan_model.py	Removed duplicate definition model_path	3 years ago
bsrgan_model_arch.py	remove extra print from BSRGAN	3 years ago
codeformer_model.py	send all three of GFPGAN's and codeformer's models to CPU memory instead of just one for #1283	3 years ago
deepbooru.py	Oops	3 years ago
devices.py	Add 'interrogate' and 'all' choices to --use-cpu	3 years ago
errors.py	Allow TF32 in CUDA for increased performance #279	3 years ago
esrgan_model.py	fix typo in filename for ESRGAN arch	3 years ago
esrgan_model_arch.py	fix typo in filename for ESRGAN arch	3 years ago
extras.py	sort file list in alphabetical ordering in extras	3 years ago
face_restoration.py	codeformer support	3 years ago
generation_parameters_copypaste.py	do not load aesthetic clip model until it's needed	3 years ago
gfpgan_model.py	Merge branch 'master' into cpu-cmdline-opt	3 years ago
images.py	Remove redundant try/except.	3 years ago
images_history.py	fix dir_path in some path like `D:/Pic/outputs`	3 years ago
img2img.py	do not load aesthetic clip model until it's needed	3 years ago
interrogate.py	interrogate: Fix CLIP-interrogation on CPU	3 years ago
ldsr_model.py	Removed duplicate definition model_path	3 years ago
ldsr_model_arch.py	Remove useless print message	3 years ago
localization.py	localization support	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
modelloader.py	Merge branch 'master' into ScuNET	3 years ago
ngrok.py	Allow specifying the region of ngrok.	3 years ago
paths.py	added guard for torch.load to prevent loading pickles with unknown content	3 years ago
processing.py	do not load aesthetic clip model until it's needed	3 years ago
prompt_parser.py	Fix typo in prompt_parser.py	3 years ago
realesrgan_model.py	Removed duplicate definition model_path	3 years ago
safe.py	extra message for unpicking fails	3 years ago
safety.py	put safety checker into a separate file because it's already crowded in processing	3 years ago
scripts.py	update scripts.py	3 years ago
scunet_model.py	Removed duplicate definition model_path	3 years ago
scunet_model_arch.py	chore: Fix typos	3 years ago
sd_hijack.py	Merge branch 'ae'	3 years ago
sd_hijack_inpainting.py	updated readme and some small stylistic changes to code	3 years ago
sd_hijack_optimizations.py	Remove wrong self reference in CUDA support for invokeai	3 years ago
sd_models.py	do not load aesthetic clip model until it's needed	3 years ago
sd_samplers.py	Merge branch 'master' into master	3 years ago
shared.py	Merge branch 'ae'	3 years ago
styles.py	styles.csv encoding utf8 to utf-8-sig	3 years ago
swinir_model.py	add swinir v2 support	3 years ago
swinir_model_arch.py	chore: Fix typos	3 years ago
swinir_model_arch_v2.py	Add files via upload	3 years ago
txt2img.py	do not load aesthetic clip model until it's needed	3 years ago
ui.py	do not load aesthetic clip model until it's needed	3 years ago
upscaler.py	fix logic error in #1832	3 years ago