Age | Commit message (Collapse) | Author | |
---|---|---|---|
2023-06-13 | Upscaler.load_model: don't return None, just use exceptions | Aarni Koskela | |
2023-06-13 | Add TODO comments to sus model loads | Aarni Koskela | |
2023-06-13 | Fix up `if "http" in ...:` to be more sensible startswiths | Aarni Koskela | |
2023-06-13 | Move `load_file_from_url` to modelloader | Aarni Koskela | |
2023-05-19 | change upscalers to download models into user-specified directory (from ↵ | AUTOMATIC | |
commandline args) rather than the default models/<...> | |||
2023-05-10 | fixes for B007 | AUTOMATIC | |
2023-05-10 | imports cleanup for ruff | AUTOMATIC | |
2023-05-09 | Fix up string formatting/concatenation to f-strings where feasible | Aarni Koskela | |
2022-11-17 | Revert "MPS Upscalers Fix" | brkirch | |
This reverts commit 768b95394a8500da639b947508f78296524f1836. | |||
2022-10-30 | add resrgan 8x, allow use 1x and up to 8x extra models, move BSRGAN model, ↵ | victorca25 | |
add nearest | |||
2022-10-25 | MPS Upscalers Fix | brkirch | |
Get ESRGAN, SCUNet, and SwinIR working correctly on MPS by ensuring memory is contiguous for tensor views before sending to MPS device. | |||
2022-10-09 | update ESRGAN architecture and model to support all ESRGAN models in the DB, ↵ | victorca25 | |
BSRGAN and real-ESRGAN models | |||
2022-10-09 | Removed duplicate definition model_path | Milly | |
2022-10-08 | Add hypernetwork support to split cross attention v1 | brkirch | |
* Add hypernetwork support to split_cross_attention_forward_v1 * Fix device check in esrgan_model.py to use devices.device_esrgan instead of shared.device | |||
2022-10-04 | Add --use-cpu command line option | brkirch | |
Remove MPS detection to use CPU for GFPGAN / CodeFormer and add a --use-cpu command line option. | |||
2022-10-02 | Update esrgan_model.py | d8ahazard | |
Use alternate ESRGAN Model download path. | |||
2022-09-30 | remove unwanted formatting/functionality from the PR | AUTOMATIC | |
2022-09-29 | Holy $hit. | d8ahazard | |
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. | |||
2022-09-26 | Cleanup existing directories, fixes | d8ahazard | |
2022-09-26 | Re-implement universal model loading | d8ahazard | |
2022-09-22 | Fix/Revert opts name from GAN to ESRGAN | d8ahazard | |
2022-09-22 | Add new models, fix shared opts issues | d8ahazard | |
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... | |||
2022-09-21 | Revert "fix for swininr PR breaking ESRGAN for new users" | AUTOMATIC | |
This reverts commit 8d1d64f9a238272d7a166d21e25cf529c09b2ad5. | |||
2022-09-21 | fix for swininr PR breaking ESRGAN for new users | AUTOMATIC | |
2022-09-11 | Modular device management | Abdullah Barhoum | |
2022-09-08 | add a helpful message when user puts RealESRGAN model into ESRGAN directory. | AUTOMATIC | |
2022-09-07 | Added support for launching on Apple Silicon | xeonvs | |
2022-09-04 | ESRGAN support | AUTOMATIC | |