Post

Ever had a single file full of hand-drawn icons or shapes and wished you could automatically separate them into clean, individually named assets?

It uses computer vision, CV geometry, and export normalization to detect isolated forms, place them on a shared canvas, and generate structured outputs in formats like PNG, JPG, TIFF, and SVG.

It can also enrich results with metadata injection and optional local model support through Ollama for semantic naming, all without relying on cloud APIs.