| Commit message (Collapse) | Author | Age | Files | Lines | |
|---|---|---|---|---|---|
| * | load_spandrel_model: make `half` `prefer_half` | Aarni Koskela | 2024-01-02 | 1 | -1/+1 |
| | | | | | | As discussed with the Spandrel folks, it's good to heed Spandrel's "supports half precision" flag to avoid e.g. black blotches and what-not. | ||||
| * | Be more clear about Spandrel model nomenclature | Aarni Koskela | 2023-12-30 | 1 | -2/+2 |
| | | |||||
| * | Correct RealESRGAN expected architecture type to ESRGAN | Aarni Koskela | 2023-12-30 | 1 | -1/+1 |
| | | |||||
| * | Verify architecture for loaded Spandrel models | Aarni Koskela | 2023-12-30 | 1 | -3/+4 |
| | | |||||
| * | Use Spandrel for upscaling and face restoration architectures (aside from ↵ | Aarni Koskela | 2023-12-30 | 1 | -91/+62 |
| | | | | | GFPGAN and LDSR) | ||||
| * | tell RealESRGANer which device to run on, could be cuda, M1, or other GPU | yajun | 2023-08-23 | 1 | -0/+1 |
| | | |||||
| * | Upscaler.load_model: don't return None, just use exceptions | Aarni Koskela | 2023-06-13 | 1 | -18/+15 |
| | | |||||
| * | Move `load_file_from_url` to modelloader | Aarni Koskela | 2023-06-13 | 1 | -2/+2 |
| | | |||||
| * | rename print_error to report, use it with together with package name | AUTOMATIC | 2023-05-31 | 1 | -5/+5 |
| | | |||||
| * | Add & use modules.errors.print_error where currently printing exception info ↵ | Aarni Koskela | 2023-05-29 | 1 | -9/+5 |
| | | | | | by hand | ||||
| * | change upscalers to download models into user-specified directory (from ↵ | AUTOMATIC | 2023-05-19 | 1 | -1/+1 |
| | | | | | commandline args) rather than the default models/<...> | ||||
| * | F401 fixes for ruff | AUTOMATIC | 2023-05-10 | 1 | -3/+3 |
| | | |||||
| * | autofixes from ruff | AUTOMATIC | 2023-05-10 | 1 | -1/+1 |
| | | |||||
| * | Fix up string formatting/concatenation to f-strings where feasible | Aarni Koskela | 2023-05-09 | 1 | -4/+4 |
| | | |||||
| * | fix `--realesrgan-models-path` not working | hitomi | 2023-04-04 | 1 | -2/+12 |
| | | |||||
| * | Refactor conditional casting, fix upscalers | brkirch | 2023-01-28 | 1 | -1/+1 |
| | | |||||
| * | Fix unable to find Real-ESRGAN model info error (AttributeError: 'NoneType' ↵ | AUTOMATIC | 2023-01-17 | 1 | -8/+4 |
| | | | | | object has no attribute 'data_path') #6841 #5170 | ||||
| * | Removed duplicate definition model_path | Milly | 2022-10-09 | 1 | -2/+0 |
| | | |||||
| * | remove unwanted formatting/functionality from the PR | AUTOMATIC | 2022-09-30 | 1 | -8/+4 |
| | | |||||
| * | Holy $hit. | d8ahazard | 2022-09-29 | 1 | -102/+107 |
| | | | | | | | | | | | | | | | | | | 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. | ||||
| * | Re-implement universal model loading | d8ahazard | 2022-09-26 | 1 | -4/+19 |
| | | |||||
| * | reworking #775 | AUTOMATIC | 2022-09-22 | 1 | -5/+50 |
| | | |||||
| * | Basic settings for realesrgan model selection. | d8ahazard | 2022-09-22 | 1 | -37/+5 |
| | | | | | I don't like that you have to restart the app, but it works. | ||||
| * | Fix/Revert opts name from GAN to ESRGAN | d8ahazard | 2022-09-22 | 1 | -2/+2 |
| | | |||||
| * | Cleanup Imports | d8ahazard | 2022-09-22 | 1 | -3/+1 |
| | | |||||
| * | Typo Fix | d8ahazard | 2022-09-22 | 1 | -1/+1 |
| | | |||||
| * | Add new models, fix shared opts issues | d8ahazard | 2022-09-22 | 1 | -6/+27 |
| | | | | | | | Add General x4x3, GeneralWDN x4x3, and AnimeVideo models from newer ESRGAN releases. Fix issues caused by renaming ESRGAN_tille values to GAN_tile without using an IDE... | ||||
| * | Revert "fix for swininr PR breaking ESRGAN for new users" | AUTOMATIC | 2022-09-21 | 1 | -1/+1 |
| | | | | | This reverts commit 8d1d64f9a238272d7a166d21e25cf529c09b2ad5. | ||||
| * | fix for swininr PR breaking ESRGAN for new users | AUTOMATIC | 2022-09-21 | 1 | -1/+1 |
| | | |||||
| * | honor tiling settings for RealESRGAN also | AUTOMATIC | 2022-09-08 | 1 | -2/+4 |
| | | | | | load scripts earlier to get errors before model loads | ||||
| * | ESRGAN support | AUTOMATIC | 2022-09-04 | 1 | -0/+15 |
| | | |||||
| * | split codebase into multiple files; to anyone this affects negatively: sorry | AUTOMATIC | 2022-09-03 | 1 | -0/+70 |
 |
index : stable-diffusion-webui-gfx803.git | |
| stable-diffusion-webui by AUTOMATIC1111 with patches for gfx803 GPU and Dockerfile |
| aboutsummaryrefslogtreecommitdiffstats |