1. 07 10月, 2022 2 次提交
  2. 06 10月, 2022 6 次提交
  3. 05 10月, 2022 1 次提交
  4. 04 10月, 2022 6 次提交
  5. 03 10月, 2022 4 次提交
  6. 02 10月, 2022 1 次提交
  7. 01 10月, 2022 2 次提交
  8. 30 9月, 2022 4 次提交
    • D
      Set default value for ckpt-dir · 9fc1e49b
      d8ahazard 提交于
      9fc1e49b
    • A
      return the dropdown that mysteriously disappeared · b60cd080
      AUTOMATIC 提交于
      b60cd080
    • A
      remove unwanted formatting/functionality from the PR · d1f09854
      AUTOMATIC 提交于
      d1f09854
    • D
      Holy $hit. · 0dce0df1
      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.
      0dce0df1
  9. 29 9月, 2022 2 次提交
  10. 28 9月, 2022 6 次提交
  11. 27 9月, 2022 5 次提交
  12. 26 9月, 2022 1 次提交