Yolov8 medium model trained on about 3k Manga, Webtoon, Manhua and Western Comic style(very few) Images for text detection and segmentation. Training Imgsize = 1024. Training Images were resized, not cropped. It can handle the extreme Image ratios often found in Korean webtoons.
Have the files? Submit a torrent.
Submit a torrent →Have the complete files and permission to share them? Replace the example folder path. The script checks the files, makes a torrent and submits its magnet and checksums. Keep your torrent client seeding. Get your community key from your settings, and read the script before running it.
curl -fsSL https://pirateface.co/package.sh | bash -s -- --repo ogkalu/comic-text-segmenter-yolov8m ./model-folder