AutoFigure-Edit: Generating Editable Scientific Illustration

TL;DR

AutoFigure-Edit is an end-to-end system that generates fully editable, style-adaptable scientific illustrations from text, combining long-context understanding, reference-guided styling, and native SVG editing for efficient creation.

Contribution

It introduces a novel system that produces editable scientific illustrations from text with flexible style control using reference images.

Findings

Enables efficient creation of high-quality scientific illustrations.

Supports flexible style adaptation through user-provided references.

Provides an interactive platform and open-source code for the community.

Abstract

High-quality scientific illustrations are essential for communicating complex scientific and technical concepts, yet existing automated systems remain limited in editability, stylistic controllability, and efficiency. We present AutoFigure-Edit, an end-to-end system that generates fully editable scientific illustrations from long-form scientific text while enabling flexible style adaptation through user-provided reference images. By combining long-context understanding, reference-guided styling, and native SVG editing, it enables efficient creation and refinement of high-quality scientific illustrations. To facilitate further progress in this field, we release the video at https://youtu.be/10IH8SyJjAQ, full codebase at https://github.com/ResearAI/AutoFigure-Edit and provide a website for easy access and interactive use at https://deepscientist.cc/.