| Commit message (Collapse) | Author | Age | Files | Lines | |
|---|---|---|---|---|---|
| * | Use Spandrel for upscaling and face restoration architectures (aside from ↵ | Aarni Koskela | 2023-12-30 | 1 | -0/+3 |
| | | | | | GFPGAN and LDSR) | ||||
| * | extras tab batch: actually use original filename | AUTOMATIC1111 | 2023-12-02 | 1 | -3/+3 |
| | | | | | preprocessing upscale: do not do an extra upscale step if it's not needed | ||||
| * | Fix missing ext_filter kwarg | Chanchana Sornsoontorn | 2023-06-03 | 1 | -1/+1 |
| | | |||||
| * | Use a more concise calculation for dest dims | ramyma | 2023-06-03 | 1 | -2/+2 |
| | | |||||
| * | Round upscaled dimensions only when not divisible by 8 | ramyma | 2023-06-03 | 1 | -2/+2 |
| | | |||||
| * | Round down scale destination dimensions to nearest multiple of 8 | ramyma | 2023-05-28 | 1 | -2/+2 |
| | | |||||
| * | change upscalers to download models into user-specified directory (from ↵ | AUTOMATIC | 2023-05-19 | 1 | -0/+1 |
| | | | | | commandline args) rather than the default models/<...> | ||||
| * | fixes for B007 | AUTOMATIC | 2023-05-10 | 1 | -1/+1 |
| | | |||||
| * | F401 fixes for ruff | AUTOMATIC | 2023-05-10 | 1 | -1/+1 |
| | | |||||
| * | imports cleanup for ruff | AUTOMATIC | 2023-05-10 | 1 | -2/+0 |
| | | |||||
| * | manual fixes for ruff | AUTOMATIC | 2023-05-10 | 1 | -1/+1 |
| | | |||||
| * | add data-dir flag and set all user data directories based on it | Max Audron | 2023-01-27 | 1 | -3/+2 |
| | | |||||
| * | Fix unable to find Real-ESRGAN model info error (AttributeError: 'NoneType' ↵ | AUTOMATIC | 2023-01-17 | 1 | -0/+1 |
| | | | | | object has no attribute 'data_path') #6841 #5170 | ||||
| * | make it possible to use fractional values for SD upscale. | AUTOMATIC | 2023-01-02 | 1 | -3/+3 |
| | | |||||
| * | fix upscale loop erroneously applied multiple times | AUTOMATIC | 2022-11-04 | 1 | -2/+10 |
| | | |||||
| * | add resrgan 8x, allow use 1x and up to 8x extra models, move BSRGAN model, ↵ | victorca25 | 2022-10-30 | 1 | -1/+16 |
| | | | | | add nearest | ||||
| * | fix logic error in #1832 | AUTOMATIC | 2022-10-09 | 1 | -1/+1 |
| | | |||||
| * | Removed duplicate definition model_path | Milly | 2022-10-09 | 1 | -3/+4 |
| | | |||||
| * | fix the bug with broken rescaling in PR | AUTOMATIC | 2022-09-30 | 1 | -1/+1 |
| | | |||||
| * | fix bugs in the PR | AUTOMATIC | 2022-09-30 | 1 | -1/+1 |
| | | |||||
| * | Holy $hit. | d8ahazard | 2022-09-29 | 1 | -0/+121 |
| 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. | |||||
 |
index : stable-diffusion-webui-gfx803.git | |
| stable-diffusion-webui by AUTOMATIC1111 with patches for gfx803 GPU and Dockerfile |
| aboutsummaryrefslogtreecommitdiffstats |