Commit message (Collapse) | Author | Age | Files | Lines | ||
---|---|---|---|---|---|---|
... | ||||||
* | | | Merge pull request #12515 from catboxanon/fix/gc1 | AUTOMATIC1111 | 2023-08-13 | 1 | -0/+3 | |
|\ \ \ | | | | | | | | | Clear sampler and garbage collect before decoding images to reduce VRAM | |||||
| * | | | Clear sampler before decoding images | catboxanon | 2023-08-13 | 1 | -0/+3 | |
| | | | | | | | | | | | | | | | | More significant VRAM reduction. | |||||
* | | | | Lora: output warnings in UI rather than fail for unfitting loras; switch to ↵ | AUTOMATIC1111 | 2023-08-13 | 1 | -5/+8 | |
|/ / / | | | | | | | | | | logging for error output in console | |||||
* | | | use dataclass for StableDiffusionProcessing | AUTOMATIC1111 | 2023-08-13 | 1 | -146/+172 | |
| | | | ||||||
* | | | add refiner to StableDiffusionProcessing class | AUTOMATIC1111 | 2023-08-13 | 1 | -8/+30 | |
| | | | | | | | | | | | | write out correct model name in infotext, rather than the refiner model | |||||
* | | | make it possible to use hires fix together with refiner | AUTOMATIC1111 | 2023-08-12 | 1 | -0/+6 | |
| | | | ||||||
* | | | put refiner into main UI, into the new accordions section | AUTOMATIC1111 | 2023-08-12 | 1 | -7/+15 | |
| | | | | | | | | | | | | | | | | | | 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 | |||||
* | | | Fix color correction by converting image to RGB | catboxanon | 2023-08-11 | 1 | -1/+1 | |
| | | | ||||||
* | | | Merge pull request #12470 from Splendide-Imaginarius/mask-blur-property+kernel | AUTOMATIC1111 | 2023-08-11 | 1 | -5/+20 | |
|\ \ \ | |/ / |/| | | Make `StableDiffusionProcessingImg2Img.mask_blur` a property, make more inline with PIL `GaussianBlur` | |||||
| * | | Reduce mask blur kernel size to 2.5 sigmas | Splendide Imaginarius | 2023-08-05 | 1 | -2/+2 | |
| | | | | | | | | | | | | | | | | | | | | | | | | | | | This more closely matches the old behavior of PIL's Gaussian blur, and fixes breakage when tiling. See https://github.com/Coyote-A/ultimate-upscale-for-automatic1111/issues/111#issuecomment-1663504109 Thanks to Алексей Трофимов and eunnone for reporting the issue. | |||||
| * | | Make StableDiffusionProcessingImg2Img.mask_blur a property | Splendide Imaginarius | 2023-08-03 | 1 | -3/+18 | |
| | | | | | | | | | | | | | | | | | | | | | | | | Fixes breakage when mask_blur is set after construction. See https://github.com/Coyote-A/ultimate-upscale-for-automatic1111/issues/111#issuecomment-1652091424 Thanks to Алексей Трофимов and eunnone for reporting the issue. | |||||
* | | | Merge branch 'dev' into refiner | AUTOMATIC1111 | 2023-08-10 | 1 | -123/+80 | |
|\ \ \ | ||||||
| * | | | add VAE to infotext | AUTOMATIC1111 | 2023-08-10 | 1 | -0/+2 | |
| | | | | ||||||
| * | | | fix --use-textbox-seed | AUTOMATIC1111 | 2023-08-10 | 1 | -2/+10 | |
| | | | | ||||||
| * | | | face restoration and tiling moved to settings - use "Options in main UI" ↵ | AUTOMATIC1111 | 2023-08-10 | 1 | -2/+9 | |
| | | | | | | | | | | | | | | | | setting if you want them back | |||||
| * | | | add a custom UI element that combines accordion and checkbox | AUTOMATIC1111 | 2023-08-10 | 1 | -37/+40 | |
| | | | | | | | | | | | | | | | | | | | | rework hires fix UI to use accordion prevent bogus progress output in console when calculating hires fix dimensions | |||||
| * | | | Add slerp import for extension backwards compat | catboxanon | 2023-08-09 | 1 | -0/+1 | |
| | | | | ||||||
| * | | | rework RNG to use generators instead of generating noises beforehand | AUTOMATIC1111 | 2023-08-09 | 1 | -79/+10 | |
| | | | | ||||||
| * | | | fix styles missing from the prompt in infotext when making a grid of batch ↵ | AUTOMATIC1111 | 2023-08-09 | 1 | -2/+7 | |
| | | | | | | | | | | | | | | | | of multiplie images | |||||
| * | | | Merge pull request #12412 from dhwz/dev | AUTOMATIC1111 | 2023-08-08 | 1 | -1/+1 | |
| |\ \ \ | | | | | | | | | | | fix typo | |||||
| | * | | | fix typo | dhwz | 2023-08-08 | 1 | -1/+1 | |
| | | |/ | | |/| | ||||||
* | | | | fix webui not switching back to original model from refiner when batch count ↵ | AUTOMATIC1111 | 2023-08-08 | 1 | -0/+2 | |
| | | | | | | | | | | | | | | | | is greater than 1 | |||||
* | | | | Merge branch 'dev' into refiner | AUTOMATIC1111 | 2023-08-08 | 1 | -3/+0 | |
|\| | | | ||||||
| * | | | REMOVE | AUTOMATIC1111 | 2023-08-08 | 1 | -3/+0 | |
| |/ / | ||||||
* | | | add infotext | AUTOMATIC1111 | 2023-08-06 | 1 | -0/+10 | |
| | | | | | | | | | | | | | | | add proper support for recalculating conds in k-diffusion samplers remove support for compvis samplers | |||||
* | | | initial refiner support | AUTOMATIC1111 | 2023-08-06 | 1 | -0/+4 | |
|/ / | ||||||
* | | enable cond cache by default | AUTOMATIC1111 | 2023-08-06 | 1 | -13/+18 | |
| | | ||||||
* | | fix rework saving incomplete images | AUTOMATIC1111 | 2023-08-06 | 1 | -1/+1 | |
| | | ||||||
* | | do the same for s_tmax #12345 | AUTOMATIC1111 | 2023-08-06 | 1 | -2/+2 | |
| | | ||||||
* | | Merge branch 'dev' into fix/s-noise | AUTOMATIC1111 | 2023-08-06 | 1 | -9/+12 | |
|\ \ | ||||||
| * | | rework saving incomplete images | AUTOMATIC1111 | 2023-08-06 | 1 | -9/+9 | |
| | | | ||||||
| * | | Merge pull request #12338 from AUTOMATIC1111/dont-save-incomplete-images | AUTOMATIC1111 | 2023-08-06 | 1 | -8/+11 | |
| |\ \ | | | | | | | | | don't save incomplete images | |||||
| | * | | Option to not save incomplete images | w-e-w | 2023-08-05 | 1 | -8/+11 | |
| | | | | ||||||
| * | | | Attempt to read s_tmax from arg first if option not found | catboxanon | 2023-08-06 | 1 | -1/+1 | |
| | | | | ||||||
| * | | | Add s_tmax | catboxanon | 2023-08-06 | 1 | -1/+1 | |
| | | | | ||||||
* | | | | Correct s_noise fix | catboxanon | 2023-08-06 | 1 | -2/+2 | |
| | | | | ||||||
* | | | | Allow s_noise override to actually be used | catboxanon | 2023-08-06 | 1 | -1/+1 | |
|/ / / | ||||||
* / / | do not add VAE Encoder/Decoder to infotext if it's the default | AUTOMATIC1111 | 2023-08-05 | 1 | -3/+9 | |
|/ / | ||||||
* | | Fix some merge mistakes | Kohaku-Blueleaf | 2023-08-05 | 1 | -1/+2 | |
| | | ||||||
* | | Merge branch 'dev' into efficient-vae-methods | Kohaku-Blueleaf | 2023-08-05 | 1 | -32/+66 | |
|\ \ | ||||||
| * \ | Merge pull request #12181 from AUTOMATIC1111/hires_checkpoint | AUTOMATIC1111 | 2023-08-05 | 1 | -31/+66 | |
| |\ \ | | | | | | | | | Hires fix change checkpoint | |||||
| | * | | fix "clamp_scalar_cpu" not implemented for 'Half' | AUTOMATIC1111 | 2023-07-31 | 1 | -1/+1 | |
| | | | | ||||||
| | * | | repair AttributeError: 'NoneType' object has no attribute 'conditioning_key' | AUTOMATIC1111 | 2023-07-31 | 1 | -7/+7 | |
| | | | | ||||||
| | * | | set the field to None instead | AUTOMATIC1111 | 2023-07-31 | 1 | -2/+2 | |
| | | | | ||||||
| | * | | delete the field that is preventing the model from being unloaded and is ↵ | AUTOMATIC1111 | 2023-07-30 | 1 | -0/+4 | |
| | | | | | | | | | | | | | | | | causing increased RAM usage | |||||
| | * | | make it so that VAE NaNs autodetection also works during first pass of hires fix | AUTOMATIC1111 | 2023-07-30 | 1 | -1/+1 | |
| | | | | ||||||
| | * | | this time for sure | AUTOMATIC1111 | 2023-07-30 | 1 | -3/+13 | |
| | | | | ||||||
| | * | | make it possible to use checkpoints of different types (SD1, SDXL) in first ↵ | AUTOMATIC1111 | 2023-07-30 | 1 | -3/+7 | |
| | | | | | | | | | | | | | | | | and second pass of hires fix | |||||
| | * | | repair non-latent upscaling broken for SDXL | AUTOMATIC1111 | 2023-07-30 | 1 | -0/+1 | |
| | | | | ||||||
| | * | | linter | AUTOMATIC1111 | 2023-07-30 | 1 | -1/+1 | |
| | | | |