jasna: Restores mosaics in videos and images through a simple app and command line that run on your GPU.
What problem it solves
Mosaics obscure portions of videos and images, making it difficult to view the affected content without changing the rest of the picture. Users need a restoration workflow that can identify selected mosaic regions and process them with GPU-accelerated video handling.
Key features
Targeted mosaic restoration — Detects mosaics in videos and restores them while leaving the rest of each picture unchanged. A preview and Segment Editor let users select which parts to process.
Source: README
App and command-line workflows — Provides a graphical application and a command line capable of handling videos, images, and folders. The command line supports one video, one image, or a whole directory.
Source: README
Multiple restoration models — Offers the free BasicVSR++ model and the supporter-only LTX model. LTX adds more detail but is described as slower than BasicVSR++.
Source: README
Video and image formats — Handles VR180 videos and still images, with SD 1.5 available as a supporter model for images. Also includes a Video Player for viewing restored video live without creating a file.
Source: README
Quick start
Copied verbatim from the project's README.
# One video
jasna --input input.mp4 --output output.mkv
# One image
jasna --input photo.png --output restored.png
# A whole folder
jasna --input input_folder --output output_folderWho it may suit
This project may suit users who want to restore selected mosaic areas in personal videos or images through a desktop app or command line. It may also suit users with compatible NVIDIA or AMD GPUs who need GPU-based processing.
Topics to discuss
Which restoration model and settings produce the most acceptable results for different source videos?
How should segment selection and mosaic previews be improved for more complex scenes?
What additional workflows or output controls would be useful for VR180 video restoration?
Written by ReadmeX AI from the project's README, source and public GitHub data; it may contain mistakes.
Read the original README https://github.com/Kruk2/jasna#readme
ReadmeX opened this community for a trending project; it is not run by the project. Maintainers can claim it from the community page.
Comments
…