aboutsummaryrefslogtreecommitdiffstats
path: root/modules/sd_models.py
Commit message (Collapse)AuthorAgeFilesLines
* put refiner into main UI, into the new accordions sectionAUTOMATIC11112023-08-121-0/+3
| | | | | | add VAE from main model into infotext, not from refiner model option to make scripts UI without gr.Group fix inconsistencies with refiner when usings samplers that do more denoising than steps
* resolve merge issuesAUTOMATIC11112023-08-101-2/+5
|
* Merge branch 'dev' into refinerAUTOMATIC11112023-08-101-11/+12
|\
| * fix checkpoint name jumping around in the list of checkpoints for no good reasonAUTOMATIC11112023-08-091-3/+9
| |
| * Merge pull request #12426 from AUTOMATIC1111/split_sharedAUTOMATIC11112023-08-091-8/+1
| |\ | | | | | | Split shared.py into multiple files
| | * split shared.py into multiple files; should resolve all circular reference ↵AUTOMATIC11112023-08-091-8/+1
| | | | | | | | | | | | import errors related to shared.py
| * | Fix mismatch between shared.sd_model & shared.optsUminosachi2023-08-081-0/+2
| |/
* | Merge branch 'dev' into refinerAUTOMATIC11112023-08-081-1/+2
|\|
| * apply unet overrides after switching modelAUTOMATIC11112023-08-071-0/+1
| |
| * SD VAE rework 2AUTOMATIC11112023-08-071-1/+1
| | | | | | | | | | | | | | - the setting for preferring opts.sd_vae has been inverted and reworded - resolve_vae function made easier to read and now returns an object rather than a tuple - if the checkbox for overriding per-model preferences is checked, opts.sd_vae overrides checkpoint user metadata - changing VAE in user metadata for currently loaded model immediately applies the selection
* | initial refiner supportAUTOMATIC11112023-08-061-1/+17
|/
* Merge branch 'dev' into multiple_loaded_modelsAUTOMATIC11112023-08-051-12/+17
|\
| * Merge pull request #12181 from AUTOMATIC1111/hires_checkpointAUTOMATIC11112023-08-051-10/+17
| |\ | | | | | | Hires fix change checkpoint
| | * additional memory improvements when switching between models of different typesAUTOMATIC11112023-07-311-1/+4
| | |
| | * hires fix checkpoint selectionAUTOMATIC11112023-07-301-9/+13
| | |
| * | fix: prevent cache model.state_dict() after model hijackAnyISalIn2023-08-041-2/+3
| | | | | | | | | | | | Signed-off-by: AnyISalIn <anyisalin@gmail.com>
| * | add style editor dialogAUTOMATIC11112023-08-031-1/+1
| | | | | | | | | | | | | | | rework toprow for img2img and txt2img to use a class with fields fix the console error when editing checkpoint user metadata
* | | repair merge errorAUTOMATIC11112023-08-011-1/+0
| | |
* | | Merge branch 'dev' into multiple_loaded_modelsAUTOMATIC11112023-08-011-11/+18
|\| |
| * | add metadata to checkpoint mergerAUTOMATIC11112023-08-011-1/+1
| | |
| * | show metadata for SD checkpoints in the extra networks UIAUTOMATIC11112023-08-011-10/+16
| |/
* / option to keep multiple models in memoryAUTOMATIC11112023-07-311-24/+112
|/
* Use less RAM when creating modelsAUTOMATIC11112023-07-241-6/+10
|
* fix the issue with /sdapi/v1/options failing (this time for sure!)AUTOMATIC11112023-07-181-1/+1
| | | | fix automated tests downloading CLIP model
* Add support for `--upcast-sampling` with SD XLbrkirch2023-07-181-1/+1
|
* hide cards for networks of incompatible stable diffusion version in Lora ↵AUTOMATIC11112023-07-171-0/+3
| | | | extra networks interface
* linterAUTOMATIC11112023-07-141-1/+1
|
* initial SDXL refiner supportAUTOMATIC11112023-07-141-1/+2
|
* add support for SDXL loras with te1/te2 modulesAUTOMATIC11112023-07-131-1/+2
|
* repair --no-half for SDXLAUTOMATIC11112023-07-131-4/+5
|
* SDXL supportAUTOMATIC11112023-07-121-2/+12
|
* getting SD2.1 to run on SDXL repoAUTOMATIC11112023-07-111-2/+6
|
* Fix typo: checkpoint_alisasesAarni Koskela2023-07-081-5/+6
|
* added torch.mps.empty_cache() to torch_gc()AUTOMATIC11112023-07-081-1/+0
| | | | changed a bunch of places that use torch.cuda.empty_cache() to use torch_gc() instead
* send tensors to the correct device when loading from safetensors file with ↵AUTOMATIC2023-06-271-1/+3
| | | | memmap disabled for #11260
* Merge pull request #11260 from dhwz/devAUTOMATIC11112023-06-271-2/+5
|\ | | | | fix very slow loading speed of .safetensors files
| * fix very slow loading speed of .safetensors filesdhwz2023-06-161-2/+5
| |
* | Use os.makedirs(..., exist_ok=True)Aarni Koskela2023-06-131-2/+1
|/
* assign devices.dtype early because it's needed before the model is loadedAUTOMATIC2023-06-011-2/+0
|
* Merge pull request #10739 from linkoid/fix-ui-debug-mode-exitAUTOMATIC11112023-05-271-7/+8
|\ | | | | Fix --ui-debug-mode exit
| * Show full traceback in get_sd_model()linkoid2023-05-261-1/+1
| | | | | | | | to reveal if an error is caused by an extension
| * Remove exit() from select_checkpoint()linkoid2023-05-261-6/+7
| | | | | | | | Raising a FileNotFoundError instead.
* | custom unet supportAUTOMATIC2023-05-271-1/+3
|/
* option to pad prompt/neg prompt to be same lengthAUTOMATIC2023-05-211-0/+5
|
* Deduplicate webui.py initial-load/reload codeAarni Koskela2023-05-191-1/+0
|
* if sd_model is None, do not always try to load itAUTOMATIC2023-05-181-1/+6
|
* move some settings to the new Optimization pageAUTOMATIC2023-05-171-16/+20
| | | | | | add slider for token merging for img2img rework StableDiffusionProcessing to have the token_merging_ratio field fix a bug with applying png optimizations for live previews when they shouldn't be applied
* Merge pull request #10451 from dennissheng/masterAUTOMATIC11112023-05-171-1/+0
|\ | | | | not clear checkpoints cache when config changes
| * not clear checkpoints cache when config changesdennissheng2023-05-171-1/+0
| |
* | fix model loading twice in some situationsAUTOMATIC2023-05-141-0/+3
| |
generated by cgit v1.2.3 (git 2.25.1) at 2025-04-29 22:50:44 +0000