Age | Commit message (Collapse) | Author | |
---|---|---|---|
2023-12-02 | extras tab batch: actually use original filename | AUTOMATIC1111 | |
preprocessing upscale: do not do an extra upscale step if it's not needed | |||
2023-06-03 | Fix missing ext_filter kwarg | Chanchana Sornsoontorn | |
2023-06-03 | Use a more concise calculation for dest dims | ramyma | |
2023-06-03 | Round upscaled dimensions only when not divisible by 8 | ramyma | |
2023-05-28 | Round down scale destination dimensions to nearest multiple of 8 | ramyma | |
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 | F401 fixes for ruff | AUTOMATIC | |
2023-05-10 | imports cleanup for ruff | AUTOMATIC | |
2023-05-10 | manual fixes for ruff | AUTOMATIC | |
2023-01-27 | add data-dir flag and set all user data directories based on it | Max Audron | |
2023-01-17 | Fix unable to find Real-ESRGAN model info error (AttributeError: 'NoneType' ↵ | AUTOMATIC | |
object has no attribute 'data_path') #6841 #5170 | |||
2023-01-02 | make it possible to use fractional values for SD upscale. | AUTOMATIC | |
2022-11-04 | fix upscale loop erroneously applied multiple times | AUTOMATIC | |
2022-10-30 | add resrgan 8x, allow use 1x and up to 8x extra models, move BSRGAN model, ↵ | victorca25 | |
add nearest | |||
2022-10-09 | fix logic error in #1832 | AUTOMATIC | |
2022-10-09 | Removed duplicate definition model_path | Milly | |
2022-09-30 | fix the bug with broken rescaling in PR | AUTOMATIC | |
2022-09-30 | fix bugs in 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. |