aboutsummaryrefslogtreecommitdiff
path: root/modules/sd_models.py
AgeCommit message (Collapse)Author
2022-11-01Unload sd_model before loading the otherJairo Correa
2022-10-29Merge pull request #3818 from jwatzman/masterAUTOMATIC1111
Reduce peak memory usage when changing models
2022-10-28Natural sorting for dropdown checkpoint listAntonio
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
2022-10-27Reduce peak memory usage when changing modelsJosh Watzman
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.
2022-10-22call model_loaded_callback after setting shared.sd_model in case scripts ↵AUTOMATIC
refer to it using that
2022-10-22fix aesthetic gradients doing nothing after loading a different modelMrCheeze
2022-10-22removed aesthetic gradients as built-inAUTOMATIC
added support for extensions
2022-10-21loading SD VAE, see PR #3303AUTOMATIC
2022-10-21do not load aesthetic clip model until it's neededAUTOMATIC
add refresh button for aesthetic embeddings add aesthetic params to images' infotext
2022-10-21Merge branch 'ae'AUTOMATIC
2022-10-20XY grid correctly re-assignes model when config changesrandom_thoughtss
2022-10-20Added PLMS hijack and made sure to always replace methodsrandom_thoughtss
2022-10-19Added support for RunwayML inpainting modelrandom_thoughtss
2022-10-19fix for broken checkpoint mergerAUTOMATIC
2022-10-19Merge branch 'master' into test_resolve_conflictsMalumaDev
2022-10-19more careful loading of model weights (eliminates some issues with ↵AUTOMATIC
checkpoints that have weird cond_stage_model layer names)
2022-10-16ui fix, re organization of the codeMalumaDev
2022-10-15Merge branch 'master' into ckpt-cacheAUTOMATIC1111
2022-10-14add checkpoint cache option to UI for faster model switchingRae Fu
switching time reduced from ~1500ms to ~280ms
2022-10-14rework the code for lowram a bitAUTOMATIC
2022-10-14load models to VRAM when using `--lowram` paramLjzd-PRO
load models to VRM instead of RAM (for machines which have bigger VRM than RAM such as free Google Colab server)
2022-10-10no to different messages plus fix using != to compare to NoneAUTOMATIC
2022-10-10Merge pull request #2131 from ssysm/upstream-masterAUTOMATIC1111
Add VAE Path Arguments
2022-10-10change vae loading methodssysm
2022-10-10--no-half-vaeAUTOMATIC
2022-10-09Merge branch 'master' of ↵ssysm
https://github.com/AUTOMATIC1111/stable-diffusion-webui into upstream-master
2022-10-09add vae path argsssysm
2022-10-09change up #2056 to make it work how i want it to plus make xy plot write ↵AUTOMATIC
correct values to images
2022-10-09Added extended model details to infotextWilliam Moorehouse
2022-10-09fix model switching not working properly if there is a different yaml configAUTOMATIC
2022-10-09fixed incorrect message about loading config; thanks anon!AUTOMATIC
2022-10-09make main model loading and model merger use the same codeAUTOMATIC
2022-10-08support loading .yaml config with same name as modelAUTOMATIC
support EMA weights in processing (????)
2022-10-08chore: Fix typosAidan Holland
2022-10-08fix: handles when state_dict does not existleko
2022-10-07support loading VAEAUTOMATIC
2022-10-02emergency fix for disabling SD model download after multiple complaintsAUTOMATIC
2022-10-02disabled SD model download after multiple complaintsAUTOMATIC
2022-10-02fix --ckpt option breaking model selectionAUTOMATIC
2022-10-02initial support for training textual inversionAUTOMATIC
2022-09-30if --ckpt option is specified, load that modelAUTOMATIC
2022-09-30revert the annotation not supported by old pythonsAUTOMATIC
2022-09-30remove unwanted formatting/functionality from the PRAUTOMATIC
2022-09-30fix bugs in the PRAUTOMATIC
2022-09-30Merge pull request #1109 from d8ahazard/ModelLoaderAUTOMATIC1111
Model Loader, Fixes
2022-09-30return shortest checkpoint title matchDepFA
2022-09-30add get_closet_checkpoint_matchDepFA
2022-09-29Merge remote-tracking branch 'upstream/master' into ModelLoaderd8ahazard
2022-09-29Holy $hit.d8ahazard
Yep. Fix gfpgan_model_arch requirement(s). Add Upscaler base class, move from images. Add a lot of methods to Upscaler. Re-work all the child upscalers to be proper classes. Add BSRGAN scaler. Add ldsr_model_arch class, removing the dependency for another repo that just uses regular latent-diffusion stuff. Add one universal method that will always find and load new upscaler models without having to add new "setup_model" calls. Still need to add command line params, but that could probably be automated. Add a "self.scale" property to all Upscalers so the scalers themselves can do "things" in response to the requested upscaling size. Ensure LDSR doesn't get stuck in a longer loop of "upscale/downscale/upscale" as we try to reach the target upscale size. Add typehints for IDE sanity. PEP-8 improvements. Moar.
2022-09-29fix for incorrect model weight loading for #814AUTOMATIC
generated by cgit v1.2.1 (git 2.18.0) at 2024-09-20 10:34:08 +0000