
6
Embed Compose UI into native windowing hosts, GPU Metal renderer for smooth resizing/scrolling, GraalVM native-image support, multi-window/multi-runtime, Gradle plugin automates native build.
0
Lightweight speech-bubble extraction model for manga/comics; 0.93M parameters, 1.8MB FP16, fast CPU/GPU inference, UNet+MobileNetV3, outputs mask/boundary/confidence, distilled from SAM, fine-tuned on synthetic hard samples.