68 Commits (ac085628540d0ec6a988fad93f5b8f2154209571)

Author SHA1 Message Date
AUTOMATIC 99043f3360 fix one of previous merges breaking the program 3 years ago
AUTOMATIC1111 24fc05cf57
Merge branch 'master' into fix-ckpt-cache 3 years ago
digburn 3780ad3ad8 fix: loading models without vae from cache 3 years ago
Muhammad Rizqi Nur fb3b564801 Merge branch 'master' into fix-ckpt-cache 3 years ago
AUTOMATIC f2a5cbe6f5 fix #3986 breaking --no-half-vae 3 years ago
Muhammad Rizqi Nur 056f06d373 Reload VAE without reloading sd checkpoint 3 years ago
Muhammad Rizqi Nur f8c6468d42
Merge branch 'master' into vae-picker 3 years ago
Jairo Correa af758e97fa Unload sd_model before loading the other 3 years ago
Muhammad Rizqi Nur bf7a699845 Fix #4035 for real now 3 years ago
Muhammad Rizqi Nur 36966e3200 Fix #4035 3 years ago
Muhammad Rizqi Nur 726769da35 Checkpoint cache by combination key of checkpoint and vae 3 years ago
Muhammad Rizqi Nur cb31abcf58 Settings to select VAE 3 years ago
AUTOMATIC1111 9553a7e071
Merge pull request #3818 from jwatzman/master
Reduce peak memory usage when changing models
3 years ago
Antonio 5d5dc64064
Natural sorting for dropdown checkpoint list
Example:

Before					After

11.ckpt					11.ckpt
ab.ckpt					ab.ckpt
ade_pablo_step_1000.ckpt	ade_pablo_step_500.ckpt			
ade_pablo_step_500.ckpt	ade_pablo_step_1000.ckpt	
ade_step_1000.ckpt		ade_step_500.ckpt
ade_step_1500.ckpt		ade_step_1000.ckpt
ade_step_2000.ckpt		ade_step_1500.ckpt
ade_step_2500.ckpt		ade_step_2000.ckpt
ade_step_3000.ckpt		ade_step_2500.ckpt
ade_step_500.ckpt			ade_step_3000.ckpt
atp_step_5500.ckpt			atp_step_5500.ckpt
model1.ckpt				model1.ckpt
model10.ckpt				model10.ckpt
model1000.ckpt			model33.ckpt
model33.ckpt				model50.ckpt
model400.ckpt			model400.ckpt
model50.ckpt				model1000.ckpt
moo44.ckpt				moo44.ckpt
v1-4-pruned-emaonly.ckpt	v1-4-pruned-emaonly.ckpt
v1-5-pruned-emaonly.ckpt	v1-5-pruned-emaonly.ckpt
v1-5-pruned.ckpt			v1-5-pruned.ckpt
v1-5-vae.ckpt				v1-5-vae.ckpt
3 years ago
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.
3 years ago
AUTOMATIC 321bacc6a9 call model_loaded_callback after setting shared.sd_model in case scripts refer to it using that 3 years ago
MrCheeze 0df94d3fcf fix aesthetic gradients doing nothing after loading a different model 3 years ago
AUTOMATIC 2b91251637 removed aesthetic gradients as built-in
added support for extensions
3 years ago
AUTOMATIC ac0aa2b18e loading SD VAE, see PR #3303 3 years ago
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
AUTOMATIC 7d6b388d71 Merge branch 'ae' 3 years ago
random_thoughtss 49533eed9e XY grid correctly re-assignes model when config changes 3 years ago
random_thoughtss 708c3a7bd8 Added PLMS hijack and made sure to always replace methods 3 years ago
random_thoughtss 8e7097d06a Added support for RunwayML inpainting model 3 years ago
AUTOMATIC f894dd552f fix for broken checkpoint merger 3 years ago
MalumaDev 2362d5f00e
Merge branch 'master' into test_resolve_conflicts 3 years ago
AUTOMATIC 10aca1ca3e more careful loading of model weights (eliminates some issues with checkpoints that have weird cond_stage_model layer names) 3 years ago
MalumaDev 9324cdaa31 ui fix, re organization of the code 3 years ago
AUTOMATIC1111 af144ebdc7
Merge branch 'master' into ckpt-cache 3 years ago
Rae Fu e21f01f645 add checkpoint cache option to UI for faster model switching
switching time reduced from ~1500ms to ~280ms
3 years ago
AUTOMATIC bb295f5478 rework the code for lowram a bit 3 years ago
Ljzd-PRO 4a216ded43 load models to VRAM when using `--lowram` param
load models to VRM instead of RAM (for machines which have bigger VRM than RAM such as free Google Colab server)
3 years ago
AUTOMATIC 727e4d1086 no to different messages plus fix using != to compare to None 3 years ago
AUTOMATIC1111 b3d3b335cf
Merge pull request #2131 from ssysm/upstream-master
Add VAE Path Arguments
3 years ago
ssysm af62ad4d25 change vae loading method 3 years ago
AUTOMATIC 7349088d32 --no-half-vae 3 years ago
ssysm 6fdad291bd Merge branch 'master' of https://github.com/AUTOMATIC1111/stable-diffusion-webui into upstream-master 3 years ago
ssysm cc92dc1f8d add vae path args 3 years ago
AUTOMATIC e6e8cabe0c change up #2056 to make it work how i want it to plus make xy plot write correct values to images 3 years ago
William Moorehouse d6d10a37bf Added extended model details to infotext 3 years ago
AUTOMATIC f4578b343d fix model switching not working properly if there is a different yaml config 3 years ago
AUTOMATIC 4e569fd888 fixed incorrect message about loading config; thanks anon! 3 years ago
AUTOMATIC c77c89cc83 make main model loading and model merger use the same code 3 years ago
AUTOMATIC 050a6a798c support loading .yaml config with same name as model
support EMA weights in processing (????)
3 years ago
Aidan Holland 432782163a chore: Fix typos 3 years ago
leko 616b7218f7 fix: handles when state_dict does not exist 3 years ago
AUTOMATIC d15b3ec001 support loading VAE 3 years ago
AUTOMATIC 852fd90c0d emergency fix for disabling SD model download after multiple complaints 3 years ago
AUTOMATIC a1cde7e646 disabled SD model download after multiple complaints 3 years ago
AUTOMATIC 0758f6e641 fix --ckpt option breaking model selection 3 years ago