PaperBanana is an AI-based figure-generation tool tailored for researchers. It accepts natural-language descriptions or uploaded sketches and produces methodological diagrams, system architectures, statistical plots, and educational infographics. A multi-agent architecture translates text into structured layouts and renders visuals with a dedicated model, while statistical plots are produced as executable Matplotlib code to guarantee numeric accuracy. Advanced mode can ingest articles to recover visual styles and refine aesthetics to publication standards.

PaperBanana is an agentic framework designed to automate academic illustration. Users provide methodology descriptions, datasets, sketches, or concept text; five specialized agents (Retriever, Planner, Stylist, Visualizer, Critic) collaborate to fetch references, devise layout and content plans, apply academic styling, render high-resolution images or code-based plots, and iteratively refine outputs until they meet publication quality. Outputs include polished diagrams, accurate statistical plots with downloadable Python code, and enhanced sketches ready for insertion into papers or presentations.