| Commit message (Collapse) | Author | Age | Files | Lines | |
|---|---|---|---|---|---|
| * | return the dropdown that mysteriously disappeared | AUTOMATIC | 2022-09-30 | 1 | -1/+1 |
| | | |||||
| * | remove unwanted formatting/functionality from the PR | AUTOMATIC | 2022-09-30 | 1 | -7/+1 |
| | | |||||
| * | Merge remote-tracking branch 'upstream/master' into ModelLoader | d8ahazard | 2022-09-30 | 1 | -6/+7 |
| |\ | |||||
| | * | new implementation for attention/emphasis | AUTOMATIC | 2022-09-29 | 1 | -1/+2 |
| | | | |||||
| | * | update lists of models after merging them in checkpoints tab | AUTOMATIC | 2022-09-28 | 1 | -1/+1 |
| | | | | | | | | | support saving as half | ||||
| | * | added support for automatically installing latest k-diffusion | AUTOMATIC | 2022-09-28 | 1 | -2/+3 |
| | | | | | | | | | | | added eta parameter to parameters output for generated images split eta settings into ancestral and ddim (because they have different default values) | ||||
| | * | save parameters for images when using the Save button. | AUTOMATIC | 2022-09-28 | 1 | -1/+1 |
| | | | |||||
| | * | Update shared.py | C43H66N12O12S2 | 2022-09-28 | 1 | -1/+1 |
| | | | |||||
| | * | Fix downssample typo in options | Dave Bauman | 2022-09-27 | 1 | -1/+1 |
| | | | | | | | Updated `downssample` to `down-sample`, matching spelling in other places. | ||||
| * | | Holy $hit. | d8ahazard | 2022-09-29 | 1 | -9/+9 |
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | 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. | ||||
| * | | Merge remote-tracking branch 'upstream/master' into ModelLoader | d8ahazard | 2022-09-27 | 1 | -1/+9 |
| |\| | |||||
| | * | rename DDIM eta label | DepFA | 2022-09-27 | 1 | -2/+2 |
| | | | |||||
| | * | Add extra kdiffusion parameters | DepFA | 2022-09-27 | 1 | -0/+3 |
| | | | |||||
| | * | Add options for exposed ddim sampler params | DepFA | 2022-09-27 | 1 | -0/+4 |
| | | | | | | | ddim_eta & ddim_discretize | ||||
| | * | job_timestamp initialization change | DepFA | 2022-09-27 | 1 | -1/+2 |
| | | | |||||
| * | | Use model loader with stable-diffusion too. | d8ahazard | 2022-09-27 | 1 | -11/+17 |
| | | | | | | | | | | | | | | | | | | | | | Hook the model loader into the SD_models file. Add default url/download if checkpoint is not found. Add matching stablediffusion-models-path argument. Add message that --ckpt-dir will be removed in the future, but have it pipe to stablediffusion-models-path for now. Update help strings for models-path args so they're more or less uniform. Move sd_model "setup" call to webUI with the others. Ensure "cleanup_models" method moves existing models to the new locations, including SD, and that we aren't deleting folders that still have stuff in them. | ||||
| * | | Re-implement universal model loading | d8ahazard | 2022-09-26 | 1 | -4/+8 |
| |/ | |||||
| * | Changed job_id to timestamp | Eyrie | 2022-09-25 | 1 | -5/+4 |
| | | |||||
| * | fix formatting | Eyrie | 2022-09-25 | 1 | -1/+1 |
| | | |||||
| * | fix formatting | Eyrie | 2022-09-25 | 1 | -0/+1 |
| | | |||||
| * | Added job_id pattern for directories | Eyrie | 2022-09-25 | 1 | -1/+5 |
| | | |||||
| * | Disable 'batch img2img' when launched with --hide-ui-dir-config | EyeDeck | 2022-09-24 | 1 | -1/+1 |
| | | | | | Prevent writing to arbitrary directories, as usual | ||||
| * | Fix to XY_Grid script console progress bar and other progress bar ↵ | RnDMonkey | 2022-09-24 | 1 | -0/+7 |
| | | | | | | improvements (#890) Fix to XY_Grid script console progress bar and other progress bar improvements #890 | ||||
| * | Option to use advanced upscalers with normal img2img | AUTOMATIC | 2022-09-23 | 1 | -1/+1 |
| | | |||||
| * | prevent saving settings with bogus values | AUTOMATIC | 2022-09-23 | 1 | -12/+11 |
| | | |||||
| * | Merge pull request #847 from rewbs/rewbs-optionally-save-before-color-correction | AUTOMATIC1111 | 2022-09-23 | 1 | -0/+1 |
| |\ | | | | | Add option to save before color correction. This helps with some posterisation issues in img2img loopback. | ||||
| | * | Merge from master | Robin Fernandes | 2022-09-23 | 1 | -73/+118 |
| | |\ | |||||
| | * | | Add option to save before color correction. Add suffix param when saving ↵ | Robin Fernandes | 2022-09-22 | 1 | -0/+1 |
| | | | | | | | | | | | | | files, used for special saves without color correction and face restoration. | ||||
| * | | | gfpgan: just download the damn model | AUTOMATIC | 2022-09-23 | 1 | -2/+1 |
| | | | | |||||
| * | | | add warning for when user's settings are broken | AUTOMATIC | 2022-09-23 | 1 | -0/+21 |
| | |/ |/| | |||||
| * | | settings categories split to columns, remade categories | AUTOMATIC | 2022-09-22 | 1 | -47/+61 |
| | | | |||||
| * | | emergency fix for the settings screen breaking the program | AUTOMATIC | 2022-09-22 | 1 | -94/+103 |
| | | | |||||
| * | | Add Section keys and headers to settings | DepFA | 2022-09-22 | 1 | -31/+51 |
| | | | |||||
| * | | Fixed directory name generation process. | Prof-Cheese | 2022-09-22 | 1 | -0/+1 |
| | | | | | | | | | 'Max prompt words' has been added to config and modified to be used in the directory name generation process. | ||||
| * | | Add option to always log generation info | Johan Aires Rastén | 2022-09-22 | 1 | -0/+1 |
| |/ | |||||
| * | A big rework, just what you were secretly hoping for! | AUTOMATIC | 2022-09-22 | 1 | -2/+1 |
| | | | | | | | | SD upscale moved to scripts Batch processing script removed Batch processing added to main img2img and now works with scripts img2img page UI reworked to use tabs | ||||
| * | reworking #775 | AUTOMATIC | 2022-09-22 | 1 | -11/+9 |
| | | |||||
| * | Basic settings for realesrgan model selection. | d8ahazard | 2022-09-22 | 1 | -0/+5 |
| | | | | | I don't like that you have to restart the app, but it works. | ||||
| * | Add LDSR and "GoLatent?" Upscaling (#763) | d8ahazard | 2022-09-21 | 1 | -0/+6 |
| | | | | * Add LDSR Upscaling | ||||
| * | Merge remote-tracking branch 'origin/master' | AUTOMATIC | 2022-09-21 | 1 | -2/+4 |
| |\ | |||||
| | * | disallow no tiling as we don't support it | C43H66N12O12S2 | 2022-09-21 | 1 | -1/+1 |
| | | | |||||
| | * | breakout tile options | C43H66N12O12S2 | 2022-09-21 | 1 | -2/+4 |
| | | | |||||
| * | | --opt-split-attention now on by default for torch.cuda, off for others (cpu ↵ | AUTOMATIC | 2022-09-21 | 1 | -5/+2 |
| |/ | | | | and MPS; because the option does not work there according to reports) | ||||
| * | Update shared.py | C43H66N12O12S2 | 2022-09-20 | 1 | -2/+3 |
| | | |||||
| * | added --use-textbox-seed option to make long seeds possible from web ui | AUTOMATIC | 2022-09-20 | 1 | -0/+2 |
| | | |||||
| * | Enable neural network upscalers for highres. fix | AUTOMATIC | 2022-09-20 | 1 | -0/+1 |
| | | |||||
| * | Keep legacy behaviour wrt reuse of filename during batch processes | olivier | 2022-09-20 | 1 | -1/+1 |
| | | |||||
| * | Support reusing filename stems during batch processing in Extras tab | olivier | 2022-09-20 | 1 | -0/+1 |
| | | |||||
| * | avoid exception if empty | C43H66N12O12S2 | 2022-09-19 | 1 | -1/+1 |
| | | |||||
| * | automatically match any version gfpgan | C43H66N12O12S2 | 2022-09-19 | 1 | -2/+2 |
| | | |||||
 |
index : stable-diffusion-webui-gfx803.git | |
| stable-diffusion-webui by AUTOMATIC1111 with patches for gfx803 GPU and Dockerfile |
| aboutsummaryrefslogtreecommitdiffstats |