| Commit message (Collapse) | Author | Age | Files | Lines | |
|---|---|---|---|---|---|
| * | Remove no longer necessary parts and add vae_file safeguard | Muhammad Rizqi Nur | 2022-11-19 | 1 | -8/+2 |
| | | |||||
| * | restore #4035 behavior | cluder | 2022-11-09 | 1 | -1/+1 |
| | | | | | - if checkpoint cache is set to 1, keep 2 models in cache (current +1 more) | ||||
| * | - do not use ckpt cache, if disabled | cluder | 2022-11-09 | 1 | -10/+17 |
| | | | | | - cache model after is has been loaded from file | ||||
| * | fix one of previous merges breaking the program | AUTOMATIC | 2022-11-04 | 1 | -0/+2 |
| | | |||||
| * | Merge branch 'master' into fix-ckpt-cache | AUTOMATIC1111 | 2022-11-04 | 1 | -2/+3 |
| |\ | |||||
| | * | fix: loading models without vae from cache | digburn | 2022-11-04 | 1 | -2/+3 |
| | | | |||||
| * | | Merge branch 'master' into fix-ckpt-cache | Muhammad Rizqi Nur | 2022-11-02 | 1 | -18/+28 |
| |\| | |||||
| | * | fix #3986 breaking --no-half-vae | AUTOMATIC | 2022-11-02 | 1 | -0/+9 |
| | | | |||||
| | * | Reload VAE without reloading sd checkpoint | Muhammad Rizqi Nur | 2022-11-02 | 1 | -8/+7 |
| | | | |||||
| | * | Merge branch 'master' into vae-picker | Muhammad Rizqi Nur | 2022-11-01 | 1 | -1/+13 |
| | |\ | |||||
| | | * | Unload sd_model before loading the other | Jairo Correa | 2022-11-01 | 1 | -1/+13 |
| | | | | |||||
| | * | | Checkpoint cache by combination key of checkpoint and vae | Muhammad Rizqi Nur | 2022-10-31 | 1 | -11/+16 |
| | | | | |||||
| | * | | Settings to select VAE | Muhammad Rizqi Nur | 2022-10-30 | 1 | -21/+10 |
| | |/ | |||||
| * | | Fix #4035 for real now | Muhammad Rizqi Nur | 2022-10-31 | 1 | -6/+7 |
| | | | |||||
| * | | Fix #4035 | Muhammad Rizqi Nur | 2022-10-31 | 1 | -1/+1 |
| |/ | |||||
| * | Merge pull request #3818 from jwatzman/master | AUTOMATIC1111 | 2022-10-29 | 1 | -4/+7 |
| |\ | | | | | Reduce peak memory usage when changing models | ||||
| | * | Reduce peak memory usage when changing models | Josh Watzman | 2022-10-27 | 1 | -4/+7 |
| | | | | | | | | | | | | | | | | | | | 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. | ||||
| * | | Natural sorting for dropdown checkpoint list | Antonio | 2022-10-28 | 1 | -2/+5 |
| |/ | | | | | | | | | | | | | | | | | | | | | | | | | | | | 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 | ||||
| * | call model_loaded_callback after setting shared.sd_model in case scripts ↵ | AUTOMATIC | 2022-10-22 | 1 | -1/+2 |
| | | | | | refer to it using that | ||||
| * | fix aesthetic gradients doing nothing after loading a different model | MrCheeze | 2022-10-22 | 1 | -2/+2 |
| | | |||||
| * | removed aesthetic gradients as built-in | AUTOMATIC | 2022-10-22 | 1 | -2/+5 |
| | | | | | added support for extensions | ||||
| * | loading SD VAE, see PR #3303 | AUTOMATIC | 2022-10-21 | 1 | -1/+4 |
| | | |||||
| * | do not load aesthetic clip model until it's needed | AUTOMATIC | 2022-10-21 | 1 | -3/+0 |
| | | | | | | add refresh button for aesthetic embeddings add aesthetic params to images' infotext | ||||
| * | Merge branch 'ae' | AUTOMATIC | 2022-10-21 | 1 | -1/+4 |
| |\ | |||||
| | * | Merge branch 'master' into test_resolve_conflicts | MalumaDev | 2022-10-19 | 1 | -3/+25 |
| | |\ | |||||
| | * | | ui fix, re organization of the code | MalumaDev | 2022-10-16 | 1 | -1/+4 |
| | | | | |||||
| * | | | XY grid correctly re-assignes model when config changes | random_thoughtss | 2022-10-20 | 1 | -3/+3 |
| | | | | |||||
| * | | | Added PLMS hijack and made sure to always replace methods | random_thoughtss | 2022-10-20 | 1 | -2/+1 |
| | | | | |||||
| * | | | Added support for RunwayML inpainting model | random_thoughtss | 2022-10-19 | 1 | -1/+15 |
| | | | | |||||
| * | | | fix for broken checkpoint merger | AUTOMATIC | 2022-10-19 | 1 | -1/+4 |
| | |/ |/| | |||||
| * | | more careful loading of model weights (eliminates some issues with ↵ | AUTOMATIC | 2022-10-19 | 1 | -3/+25 |
| |/ | | | | checkpoints that have weird cond_stage_model layer names) | ||||
| * | Merge branch 'master' into ckpt-cache | AUTOMATIC1111 | 2022-10-15 | 1 | -3/+2 |
| |\ | |||||
| | * | rework the code for lowram a bit | AUTOMATIC | 2022-10-14 | 1 | -10/+2 |
| | | | |||||
| | * | load models to VRAM when using `--lowram` param | Ljzd-PRO | 2022-10-14 | 1 | -2/+13 |
| | | | | | | | load models to VRM instead of RAM (for machines which have bigger VRM than RAM such as free Google Colab server) | ||||
| * | | add checkpoint cache option to UI for faster model switching | Rae Fu | 2022-10-14 | 1 | -22/+32 |
| |/ | | | | switching time reduced from ~1500ms to ~280ms | ||||
| * | no to different messages plus fix using != to compare to None | AUTOMATIC | 2022-10-10 | 1 | -6/+3 |
| | | |||||
| * | Merge pull request #2131 from ssysm/upstream-master | AUTOMATIC1111 | 2022-10-10 | 1 | -1/+8 |
| |\ | | | | | Add VAE Path Arguments | ||||
| | * | change vae loading method | ssysm | 2022-10-10 | 1 | -2/+9 |
| | | | |||||
| | * | Merge branch 'master' of ↵ | ssysm | 2022-10-10 | 1 | -8/+12 |
| | |\ | | | | | | | | | | https://github.com/AUTOMATIC1111/stable-diffusion-webui into upstream-master | ||||
| | * | | add vae path args | ssysm | 2022-10-10 | 1 | -1/+1 |
| | | | | |||||
| * | | | --no-half-vae | AUTOMATIC | 2022-10-10 | 1 | -0/+3 |
| | |/ |/| | |||||
| * | | change up #2056 to make it work how i want it to plus make xy plot write ↵ | AUTOMATIC | 2022-10-09 | 1 | -2/+0 |
| | | | | | | | | | correct values to images | ||||
| * | | Added extended model details to infotext | William Moorehouse | 2022-10-09 | 1 | -1/+2 |
| | | | |||||
| * | | fix model switching not working properly if there is a different yaml config | AUTOMATIC | 2022-10-09 | 1 | -1/+2 |
| | | | |||||
| * | | fixed incorrect message about loading config; thanks anon! | AUTOMATIC | 2022-10-09 | 1 | -1/+1 |
| | | | |||||
| * | | make main model loading and model merger use the same code | AUTOMATIC | 2022-10-09 | 1 | -5/+9 |
| |/ | |||||
| * | support loading .yaml config with same name as model | AUTOMATIC | 2022-10-08 | 1 | -7/+23 |
| | | | | | support EMA weights in processing (????) | ||||
| * | chore: Fix typos | Aidan Holland | 2022-10-08 | 1 | -2/+2 |
| | | |||||
| * | fix: handles when state_dict does not exist | leko | 2022-10-08 | 1 | -1/+5 |
| | | |||||
| * | support loading VAE | AUTOMATIC | 2022-10-07 | 1 | -0/+8 |
| | | |||||
 |
index : stable-diffusion-webui-gfx803.git | |
| stable-diffusion-webui by AUTOMATIC1111 with patches for gfx803 GPU and Dockerfile |
| aboutsummaryrefslogtreecommitdiffstats |