stable-diffusion-webui/modules
Josh Watzman b50ff4f4e4 Reduce peak memory usage when changing models
A few tweaks to reduce peak memory usage, the biggest being that if we
aren't using the checkpoint cache, we shouldn't duplicate the model
state dict just to immediately throw it away.

On my machine with 16GB of RAM, this change means I can typically change
models, whereas before it would typically OOM.
2022-10-27 22:01:06 +01:00
..
api clean 2022-10-26 09:46:17 +03:00
codeformer clarification for settings; another comment about copied files 2022-09-07 12:57:12 +03:00
hypernetworks patch bug (SeverianVoid's comment on 5245c7a) 2022-10-26 10:12:46 +03:00
textual_inversion typo: cmd_opts.embedding_dir to cmd_opts.embeddings_dir 2022-10-26 17:38:08 +03:00
artists.py added random artist button 2022-09-05 23:08:06 +03:00
codeformer_model.py send all three of GFPGAN's and codeformer's models to CPU memory instead of just one for #1283 2022-10-04 12:32:22 +03:00
deepbooru.py fix part2 2022-10-22 19:27:16 +03:00
devices.py MPS Upscalers Fix 2022-10-25 09:42:53 +03:00
errors.py Allow TF32 in CUDA for increased performance #279 2022-09-12 16:34:13 +03:00
esrgan_model_arch.py fix typo in filename for ESRGAN arch 2022-10-09 15:08:27 +03:00
esrgan_model.py MPS Upscalers Fix 2022-10-25 09:42:53 +03:00
extras.py sort file list in alphabetical ordering in extras 2022-10-21 09:00:46 +03:00
face_restoration.py codeformer support 2022-09-07 12:32:28 +03:00
generation_parameters_copypaste.py do not load aesthetic clip model until it's needed 2022-10-21 16:10:51 +03:00
gfpgan_model.py Merge branch 'master' into cpu-cmdline-opt 2022-10-04 07:42:53 -04:00
images.py add script callback for before image save and change callback for after image save to use a class with parameters 2022-10-26 13:12:44 +03:00
img2img.py img2img, use smartphone photos' EXIF orientation 2022-10-26 10:10:57 +03:00
interrogate.py interrogate: Fix CLIP-interrogation on CPU 2022-10-21 09:52:12 +03:00
ldsr_model_arch.py Remove useless print message 2022-09-30 08:56:39 -05:00
ldsr_model.py Removed duplicate definition model_path 2022-10-09 12:46:07 +03:00
localization.py localization support 2022-10-17 21:15:32 +03:00
lowvram.py remove parsing command line from devices.py 2022-10-22 14:04:14 +03:00
masking.py make inpaint at full resolution option not discard useful pixels from the image 2022-09-18 10:49:00 +03:00
memmon.py Add some error handling for VRAM monitor 2022-09-18 05:20:33 -04:00
modelloader.py Merge branch 'master' into ScuNET 2022-10-02 07:56:22 -05:00
ngrok.py Allow specifying the region of ngrok. 2022-10-16 09:56:33 +03:00
paths.py added guard for torch.load to prevent loading pickles with unknown content 2022-10-09 17:58:43 +03:00
processing.py add override_settings to API as an alternative to #3629 2022-10-26 11:47:17 +03:00
prompt_parser.py Fix typo in prompt_parser.py 2022-10-19 11:52:12 +03:00
realesrgan_model.py Removed duplicate definition model_path 2022-10-09 12:46:07 +03:00
safe.py extra message for unpicking fails 2022-10-14 16:37:36 +03:00
safety.py put safety checker into a separate file because it's already crowded in processing 2022-09-13 08:34:41 +03:00
script_callbacks.py add script callback for before image save and change callback for after image save to use a class with parameters 2022-10-26 13:12:44 +03:00
scripts.py further support for extensions 2022-10-22 13:34:49 +03:00
scunet_model_arch.py chore: Fix typos 2022-10-08 22:42:30 +03:00
scunet_model.py MPS Upscalers Fix 2022-10-25 09:42:53 +03:00
sd_hijack_inpainting.py updated readme and some small stylistic changes to code 2022-10-21 09:00:39 +03:00
sd_hijack_optimizations.py Remove wrong self reference in CUDA support for invokeai 2022-10-19 09:35:53 +03:00
sd_hijack.py removed aesthetic gradients as built-in 2022-10-22 12:23:58 +03:00
sd_models.py Reduce peak memory usage when changing models 2022-10-27 22:01:06 +01:00
sd_samplers.py fix #3145 #3093 2022-10-25 08:32:33 +03:00
shared.py add override_settings to API as an alternative to #3629 2022-10-26 11:47:17 +03:00
styles.py styles.csv encoding utf8 to utf-8-sig 2022-10-18 15:18:51 +03:00
swinir_model_arch_v2.py Add files via upload 2022-10-10 19:54:57 +03:00
swinir_model_arch.py chore: Fix typos 2022-10-08 22:42:30 +03:00
swinir_model.py MPS Upscalers Fix 2022-10-25 09:42:53 +03:00
txt2img.py removed aesthetic gradients as built-in 2022-10-22 12:23:58 +03:00
ui.py Merge pull request #3139 from captin411/focal-point-cropping 2022-10-26 09:24:21 +03:00
upscaler.py fix logic error in #1832 2022-10-09 13:48:04 +03:00