Age | Commit message (Collapse) | Author | |
---|---|---|---|
2023-08-13 | Clear sampler before decoding images | catboxanon | |
More significant VRAM reduction. | |||
2023-08-13 | use dataclass for StableDiffusionProcessing | AUTOMATIC1111 | |
2023-08-13 | add refiner to StableDiffusionProcessing class | AUTOMATIC1111 | |
write out correct model name in infotext, rather than the refiner model | |||
2023-08-12 | make it possible to use hires fix together with refiner | AUTOMATIC1111 | |
2023-08-12 | put refiner into main UI, into the new accordions section | AUTOMATIC1111 | |
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 | |||
2023-08-11 | Fix color correction by converting image to RGB | catboxanon | |
2023-08-11 | Merge pull request #12470 from Splendide-Imaginarius/mask-blur-property+kernel | AUTOMATIC1111 | |
Make `StableDiffusionProcessingImg2Img.mask_blur` a property, make more inline with PIL `GaussianBlur` | |||
2023-08-10 | Merge branch 'shared-hires-prompt-raw' into shared-hires-prompt-test | Robert Barron | |
2023-08-10 | Merge branch 'dev' into refiner | AUTOMATIC1111 | |
2023-08-10 | add VAE to infotext | AUTOMATIC1111 | |
2023-08-10 | fix --use-textbox-seed | AUTOMATIC1111 | |
2023-08-10 | face restoration and tiling moved to settings - use "Options in main UI" ↵ | AUTOMATIC1111 | |
setting if you want them back | |||
2023-08-10 | add a custom UI element that combines accordion and checkbox | AUTOMATIC1111 | |
rework hires fix UI to use accordion prevent bogus progress output in console when calculating hires fix dimensions | |||
2023-08-09 | Add slerp import for extension backwards compat | catboxanon | |
2023-08-09 | allow first pass and hires pass to use a single prompt to do different ↵ | Robert Barron | |
prompt editing, hires is 1.0..2.0: relative time range is [1..2] absolute time range is [steps+1..steps+hire_steps], e.g. with 30 steps and 20 hires steps, '20' is 2/3rds through first pass, and 40 is halfway through hires pass | |||
2023-08-09 | rework RNG to use generators instead of generating noises beforehand | AUTOMATIC1111 | |
2023-08-09 | fix styles missing from the prompt in infotext when making a grid of batch ↵ | AUTOMATIC1111 | |
of multiplie images | |||
2023-08-08 | Merge pull request #12412 from dhwz/dev | AUTOMATIC1111 | |
fix typo | |||
2023-08-08 | fix webui not switching back to original model from refiner when batch count ↵ | AUTOMATIC1111 | |
is greater than 1 | |||
2023-08-08 | Merge branch 'dev' into refiner | AUTOMATIC1111 | |
2023-08-08 | REMOVE | AUTOMATIC1111 | |
2023-08-08 | fix typo | dhwz | |
2023-08-06 | add infotext | AUTOMATIC1111 | |
add proper support for recalculating conds in k-diffusion samplers remove support for compvis samplers | |||
2023-08-06 | initial refiner support | AUTOMATIC1111 | |
2023-08-06 | enable cond cache by default | AUTOMATIC1111 | |
2023-08-06 | fix rework saving incomplete images | AUTOMATIC1111 | |
2023-08-06 | do the same for s_tmax #12345 | AUTOMATIC1111 | |
2023-08-06 | Merge branch 'dev' into fix/s-noise | AUTOMATIC1111 | |
2023-08-06 | rework saving incomplete images | AUTOMATIC1111 | |
2023-08-06 | Merge pull request #12338 from AUTOMATIC1111/dont-save-incomplete-images | AUTOMATIC1111 | |
don't save incomplete images | |||
2023-08-05 | Correct s_noise fix | catboxanon | |
2023-08-05 | Attempt to read s_tmax from arg first if option not found | catboxanon | |
2023-08-05 | Add s_tmax | catboxanon | |
2023-08-05 | Allow s_noise override to actually be used | catboxanon | |
2023-08-05 | Option to not save incomplete images | w-e-w | |
2023-08-05 | do not add VAE Encoder/Decoder to infotext if it's the default | AUTOMATIC1111 | |
2023-08-05 | Fix some merge mistakes | Kohaku-Blueleaf | |
2023-08-05 | Merge branch 'dev' into efficient-vae-methods | Kohaku-Blueleaf | |
2023-08-05 | Reduce mask blur kernel size to 2.5 sigmas | Splendide Imaginarius | |
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. | |||
2023-08-05 | Merge pull request #12181 from AUTOMATIC1111/hires_checkpoint | AUTOMATIC1111 | |
Hires fix change checkpoint | |||
2023-08-05 | add infotext | Kohaku-Blueleaf | |
2023-08-04 | replace get_first_stage_encoding | Kohaku-Blueleaf | |
2023-08-04 | Revert "change all encode" | Kohaku-Blueleaf | |
This reverts commit 094c416a801b16c7d8e1944e2e9fae2c9e98bf12. | |||
2023-08-04 | change all encode | Kohaku-Blueleaf | |
2023-08-04 | Merge branch 'dev' into efficient-vae-methods | Kohaku-Blueleaf | |
2023-08-04 | resolve some of circular import issues for kohaku | AUTOMATIC1111 | |
2023-08-04 | add TAESD for i2i and t2i | Kohaku-Blueleaf | |
2023-08-03 | Make StableDiffusionProcessingImg2Img.mask_blur a property | Splendide Imaginarius | |
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. | |||
2023-08-03 | add NV option for Random number generator source setting, which allows to ↵ | AUTOMATIC1111 | |
generate same pictures on CPU/AMD/Mac as on NVidia videocards. | |||
2023-08-02 | add yet another torch_gc to reclaim some of VRAM after the initial stage of ↵ | AUTOMATIC1111 | |
img2img |