FreePaperBanana

Generate publication-ready academic diagrams from methodology text using AI.

Open-source reimplementation of PaperBanana (Zhu et al., 2026). Six specialized agents generate methodology diagrams and statistical plots via a two-phase pipeline: planning (Prompt Enhancer → Retriever → Planner → Stylist) and iterative refinement (Visualizer ↔ Critic). Powered by Google Gemini.

Disclaimer: Unofficial, independent reimplementation for research and education. Not affiliated with or endorsed by the original authors or Google/DeepMind.

---

Demo

Text prompt → iterative refinement → publication-ready diagram:

VLM-as-Judge Framework	Pipeline Architecture	Segmentation	Quantum
Score: 9.2/10	Score: 9.8/10	Comparison grid	Surface code

Each diagram generated from text in ~3 minutes for ~$0.50. See example prompts for the full scored prompts.

---

Why This Tool?

• Free and open source. No $300/year subscription. Bring your own Gemini API key (~$0.50 per diagram).
• Publication-ready output. Exports to PNG (300 DPI). Designed for NeurIPS/ICML-style figures.

---

Quick Start

Install

git clone https://github.com/efradeca/freepaperbanana.git
cd freepaperbanana
pip install -e ".[dev]"

Setup API key

freepaperbanana setup
# Opens browser to get a free Gemini API key → saves to .env

Generate a diagram

import asyncio
from freepaperbanana import FreePaperBananaPipeline, GenerationInput, DiagramType

async def main():
    pipeline = FreePaperBananaPipeline()
    result = await pipeline.generate(
        GenerationInput(
            source_context="We propose a transformer-based encoder-decoder...",
            communicative_intent="Overview of the proposed architecture.",
            diagram_type=DiagramType.METHODOLOGY,
        )
    )
    print(f"Output: {result.image_path}")

asyncio.run(main())

Try it online: HF Space demo (no installation needed)

---

Examples

1. Methodology Diagram

result = await pipeline.generate(
    GenerationInput(
        source_context="""
        We propose a multi-agent framework consisting of five specialized agents.
        A Retriever selects reference examples, a Planner generates textual descriptions
        via in-context learning, and a Stylist refines them for aesthetics. In the
        refinement phase, a Visualizer renders images and a Critic evaluates them,
        iterating for T rounds.
        """,
        communicative_intent="Overview of the multi-agent illustration pipeline.",
        diagram_type=DiagramType.METHODOLOGY,
    )
)

2. Model Architecture

result = await pipeline.generate(
    GenerationInput(
        source_context="""
        Our model uses a U-Net architecture with skip connections. The encoder
        downsamples through 4 stages of conv-batchnorm-relu blocks. The decoder
        mirrors this with transposed convolutions. Skip connections concatenate
        encoder features at each scale.
        """,
        communicative_intent="U-Net encoder-decoder with skip connections.",
        diagram_type=DiagramType.METHODOLOGY,
    )
)

3. Statistical Plot

freepaperbanana plot \
  -d results.csv \
  --intent "Grouped bar chart comparing F1 scores across 4 models on 3 benchmarks"

---

Supported Figure Types

Type	Status	Description
Methodology diagrams	Ready	Flowcharts, pipelines, system architectures
Model architectures	Ready	Neural network structures, encoder-decoders
Process diagrams	Ready	Multi-stage workflows, data flows
Training pipelines	Ready	Training loops, loss flows, optimization steps
Comparison figures	Ready	Side-by-side method comparisons, ablation visuals
Statistical plots	Ready	Bar charts, line plots, scatter plots (via matplotlib)
Multi-panel figures	Partial	Limited by aspect ratio constraints
Tables / algorithms	Coming soon	Not yet supported

---

Export Formats

Format	Resolution	Recommended Use
PNG	300 DPI	Paper submissions, presentations

---

Roadmap

• Multi-provider support (OpenAI, Anthropic alongside Gemini)
• Multi-panel figure generation with sub-figure layout
• PyPI package (pip install freepaperbanana)
• Algorithm/pseudocode rendering
• Interactive editing — click to modify specific diagram elements

---

Contributing

Contributions welcome! See CONTRIBUTING.md for setup, conventions, and PR guidelines.

Look for issues labeled good first issue to get started.

---

Testing

pytest tests/ -v          # 179 tests, all mocked (no API key needed)
ruff check src/ tests/    # Lint
ruff format --check src/  # Format check

---

Legal

• License: MIT (code) / CC BY 4.0 + Public Domain (reference images).
• Independent implementation: Inspired by the published paper (arXiv:2601.23265). No code was copied from any existing repository. The llmsresearch/paperbanana community project (MIT) was consulted as architectural reference.
• Generated outputs: Images produced by this pipeline are generated via the Google Gemini API. Users are responsible for compliance with Google's Generative AI Terms of Service.

---

Citation

If you use FreePaperBanana in your research, please cite the original paper:

@article{zhu2026paperbanana,
  title={PaperBanana: Automating Academic Illustration for AI Scientists},
  author={Zhu, Dawei and Meng, Rui and Song, Yale and Wei, Xiyu and Li, Sujian and Pfister, Tomas and Yoon, Jinsung},
  journal={arXiv preprint arXiv:2601.23265},
  year={2026}
}

@software{freepaperbanana2026,
  title={FreePaperBanana: Open-Source Multi-Agent Academic Illustration Generation},
  author={Deulofeu, Efrain},
  year={2026},
  url={https://github.com/efradeca/freepaperbanana},
  license={MIT}
}

---

Acknowledgments

• PaperBanana (Zhu et al., 2026) for the original methodology.
• 331 reference figures from 80 published papers (all CC BY 4.0 / Public Domain). See THIRD_PARTY_NOTICES.md. Authors may request removal via Issues.
• llmsresearch/paperbanana community reimplementation (MIT), consulted as architectural reference.