- 30 9月, 2022 36 次提交
-
-
由 d8ahazard 提交于
Cleanup. Sorry.
-
由 d8ahazard 提交于
Ensure we find checkpoints within subdirectories.
-
由 d8ahazard 提交于
-
由 d8ahazard 提交于
-
由 d8ahazard 提交于
Also, clean up logging in the ldsr arch file.
-
由 d8ahazard 提交于
If we accidentally downloaded the wrong file and saved it as project.yaml, this will delete it so it can be re-downloaded.
-
由 d8ahazard 提交于
-
由 RnDMonkey 提交于
-
由 RnDMonkey 提交于
-
由 Andrew Savchyn 提交于
-
由 Andrew Savchyn 提交于
-
由 AUTOMATIC 提交于
-
由 AUTOMATIC 提交于
-
由 AUTOMATIC 提交于
-
由 C43H66N12O12S2 提交于
-
由 AUTOMATIC 提交于
-
由 AUTOMATIC 提交于
-
由 AUTOMATIC 提交于
-
由 AUTOMATIC 提交于
-
由 AUTOMATIC 提交于
-
由 AUTOMATIC 提交于
-
由 AUTOMATIC 提交于
-
由 AUTOMATIC1111 提交于
Model Loader, Fixes
-
由 AUTOMATIC 提交于
-
由 AUTOMATIC 提交于
-
由 C43H66N12O12S2 提交于
-
由 DepFA 提交于
-
由 DepFA 提交于
-
由 DepFA 提交于
-
由 Mackerel 提交于
-
由 d8ahazard 提交于
-
由 d8ahazard 提交于
-
由 d8ahazard 提交于
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.
-
由 Nick Renieris 提交于
Fixes bug where if Type is Nothing and axis values are filled out (from ie. previously using another Type), it will still needlessly run it N times (with identical results).
-
由 Justin Maier 提交于
-
由 Justin Maier 提交于
-
- 29 9月, 2022 4 次提交
-
-
由 AUTOMATIC 提交于
-
由 AUTOMATIC 提交于
-
由 AUTOMATIC 提交于
-
由 C43H66N12O12S2 提交于
-