PaperBanana is an AI research visualization tool and framework designed to generate and refine high-resolution academic illustrations from conceptual and technical descriptions. It employs an automated generation pipeline that transforms scientific text and captions into publication-quality diagrams and plots.
The system utilizes a multi-stage process consisting of retrieval-augmented planning, image synthesis, and a critic-based iterative refinement mechanism. This workflow allows for the adjustment of image details and the upscaling of visual outputs to 4K resolution.
The project includes capabilities for batch-parallel image synthesis to facilitate comparative selection and prototyping. It further provides a scientific image evaluation framework to measure output quality against ground-truth datasets and tracks the evolution of images through intermediate state visualization.
