@Xudong07452910: Driven crazy by drawing figures for papers, revising till dawn? The open-source tool PaperBanana helps you generate figures with just one sentence: • Drop in the methodology text/PDF + a caption • Multi-Agent auto-pipeline: Plan → Stylize → Generate → Self-critic → Redraw • …

X AI KOLs Timeline Tools

Summary

PaperBanana is an open-source tool that uses a multi-agent pipeline to automatically generate high-quality academic illustrations from paper PDFs and user descriptions. It supports multiple AI providers such as GPT-Image and Gemini, and provides CLI, Python API, and a web interface.

Tired of drawing figures for papers and revising till dawn? Open-source magic PaperBanana helps you generate figures with just one sentence: • Drop in the methodology text/PDF + a caption • Multi-Agent auto-pipeline: Plan → Stylize → Generate → Self-critic → Redraw • Keep going until the Critic is satisfied; you just receive the final product I added OpenAI's latest gpt-image-2 on top of the original repo: - Any resolution, up to 4K - Native support for 8 aspect ratios - Four quality levels: low / medium / high / auto - Automatic pixel alignment, never exceeding limits I've open-sourced the code, just grab it and run: https://github.com/hxdflying/paperbanana… Share this with researchers who are still manually drawing figures or getting unsatisfactory GPT-generated images.
Original Article
View Cached Full Text

Cached at: 05/16/26, 01:19 PM

PaperBanana

Automated Academic Illustration for AI Scientists

Similar Articles

@Xudong07452910: Paper2Any: Convert papers, texts, or topics into editable research diagrams, technical roadmaps, and presentations with one click. This is an open-source project focused on academic visualization and presentation creation. Main features include: 1.Paper2Figure: Generate editable model architecture diagrams, technical roadmaps, experimental flowcharts (supports PPTX/SVG formats)

X AI KOLs Timeline

Paper2Any is an open-source project that converts papers, texts, or topics into editable research diagrams, technical roadmaps, and presentations with one click, supporting multiple output formats, suitable for researchers to quickly create paper illustrations and presentation materials.

@GitHub_Daily: When writing a paper, switching between different tools for drawing model architecture diagrams, making PPT presentations, and organizing experimental data charts, each step requires different tools and repetitive format adjustments — it's indeed time-consuming. Recently, I came across the open-source project Paper2Any, which directly takes a paper and generates various academic materials with one click. Upload a paper PDF, screenshot, or text, and A…

X AI KOLs Timeline

Paper2Any is an open-source project that automatically generates academic materials such as model architecture diagrams, PPT presentations, and experiment charts from paper PDFs, screenshots, or text. It supports editing and one-click Docker deployment.

@QingQ77: Upload academic paper PDFs or LaTeX source code to automatically generate editable PowerPoint presentations through multi-agent collaboration. https://github.com/CRui5in/paper-ppt-agent… Paper PPT Agent uses three ag…

X AI KOLs Timeline

Paper PPT Agent is an open-source multi-agent collaboration tool that automatically converts academic paper PDFs or LaTeX source code into editable PowerPoint presentations, featuring content summarization, layout design, and visual quality review capabilities.

@Xudong07452910: Tired of formatting your paper to the point of collapse? Try open-source project PaperFit! A lifesaver for researchers, usable directly in Claude Code, Codex, and Cursor. Content written, LaTeX compiled, but the layout is too ugly to submit? PaperFit uses a visual feedback loop to directly solve it: - Auto-compile …

X AI KOLs Timeline

PaperFit is a vision-based LaTeX layout agent system that automatically compiles, diagnoses PDF layout issues, and fixes the source code. It supports use in Claude Code, Codex, and Cursor.