Releases: Tohrusky/Final2x-core
Releases · Tohrusky/Final2x-core
Release 2024-12-14
- ccrestoration v0.2.1
- Support: HAT, SRCNN
Release 2024-11-19
feat: reserve interface for other torch devices (#27)
Release 2024-11-09
- ccrestoration v0.1.2
- Support: DAT
Release 2024-11-08
Final2x-core v3.0.0 has been released!
- ccrestoration: v0.1.1
We are thrilled to announce the release of Final2x-core v3.0.0, which brings a significant upgrade to our image restoration capabilities. This release marks a major milestone as we transition to utilizing ccrestoration (PyTorch) for our algorithm implementation, enhancing performance and expanding the range of supported models.
Breaking Changes
- Deprecation of ncnn: After v3.0.0, ncnn will no longer be supported. The project will now use ccrestoration (PyTorch) for all algorithm implementations.
- Project Refactoring: The entire project has been refactored, resulting in incompatible configurations and APIs with the 2.x version.
- Windows User Changes: Only Nvidia users can use GPU acceleration.
- Linux User Changes: Linux users need to install using pip, as we will no longer provide pre-built packages. (Install ROCm PyTorch for AMD GPU)
- MacOS Intel User Changes: MacOS Intel users can not use GPU acceleration, only CPU.
Features
- Expanded Model Support: We are excited to introduce support for a variety of new models, including RealESRGAN, RealCUGAN, EDSR, SwinIR, and SCUNet.
- Future-Proofing: We will continue to add support for more models in future updates!
Release 2024-09-23
Auto Release.
- feat: -n flag for not opening output folder
Release 2024-07-01
Auto Release.
- Support APISR-RRDB
- Fix macos build
Release 2024-01-01
Auto Release.