paperbanana-cn

English · 简体中文

Turn method descriptions and research data into scientific diagrams and statistical plots.
Keep the PaperBanana workflow; choose your own VLM, image service, interface language, aspect ratio, and resolution.

See it work

_{One real Studio run: configured input → live pipeline stages → completed result. No credentials or private endpoints are shown.}

Real outputs, not mockups

The methodology diagrams were generated and refined through the configured VLM and image roles. The statistical plot uses PaperBanana's deterministic plotting path; its values are synthetic demonstration data.

What V2 actually adds

Independent model rails	A complete bilingual Studio	Exact output control
Give the VLM and image generator different protocols, Base URLs, API keys, model names, and timeouts.	Switch the interface between Chinese and English without rewriting prompts, paper text, or labels inside the figure.	Choose 10 aspect ratios and 1K / 2K / 4K; unsupported combinations fail before a paid image request.

Studio, CLI, and MCP resolve the same saved connections. API keys remain outside the repository, are never filled back into the browser, and are excluded from run metadata.

Start in 60 seconds

1. Launch the desktop Studio

You need Python 3.10-3.12, uv, and a desktop browser:

uvx paperbanana-cn studio

Open http://127.0.0.1:7860. uvx uses an isolated environment and does not modify Debian or Ubuntu's system Python.

2. Connect the two model roles

Open Settings → VLM connection, enter the protocol, Base URL, API key, exact model name, and timeout, then select Save and use. Repeat under Image connection.

[!TIP] The two roles may use the same relay or completely different services. Editing a saved connection does not activate it, and leaving the key field blank preserves the existing key.

Show the connection manager

Supported protocols, credential storage, connection tests, and explicit legacy mode are documented in the connection guide.

3. Generate

Choose Methodology diagram, add the method content and communicative intent, select the aspect ratio and resolution, and run. The result canvas keeps the final figure, real output size, iteration history, and download actions together.

The same task from the CLI:

paperbanana-cn generate \
  --input method.txt \
  --caption "Overview of the proposed architecture" \
  --aspect-ratio 16:9 \
  --resolution 2K \
  --format png

A workbench built around the result

Area	Workflows	Required connections
Create	Methodology diagram, statistical plot	VLM + image / VLM only
Improve	Continue a saved run, quality evaluation	Determined by the run / VLM only
Automate	Full-paper orchestration, batch, parameter sweep	Determined by the task
Tools	Multi-panel composite, run browser	None

Task inputs stay in the left work area. The result canvas is the visual center; completed logs collapse out of the way, while failed runs keep the input and expose the actionable error.

One scientific workflow

PaperBanana-CN does not maintain a second scientific pipeline. Retrieval, planning, candidate generation, critique, refinement, deterministic plotting, recovery, batch processing, orchestration, and vector export continue through the upstream PaperBanana workflow.

Use it your way

Entry point	Best for	Start here
Studio	Interactive figure production and connection management	paperbanana-cn studio
CLI	Reproducible local runs and scripts	paperbanana-cn generate --help
MCP	Calling 11 figure tools from an MCP client	paperbanana-cn mcp
GitHub Action	Generating figures inside a repository workflow	Action reference
Docker	A pinned, isolated runtime	ghcr.io/mituan-ai/paperbanana-cn:2.0.1
Colab	Trying the package in a hosted notebook	Quickstart notebook

MCP client configuration

{
  "mcpServers": {
    "paperbanana-cn": {
      "command": "uvx",
      "args": ["paperbanana-cn", "mcp"]
    }
  }
}

The server reads the same active connections as Studio and CLI. See the MCP guide for all 11 tools and their arguments.

Docker launch

docker run --rm -p 7860:7860 \
  -v paperbanana-cn-config:/home/paperbanana/.config/paperbanana-cn \
  -v paperbanana-cn-data:/home/paperbanana/.local/share/paperbanana-cn \
  -v paperbanana-cn-outputs:/work/outputs \
  ghcr.io/mituan-ai/paperbanana-cn:2.0.1 \
  studio --host 0.0.0.0

Output control without surprises

Aspect ratios

1:1 · 4:3 · 3:2 · 5:4 · 16:9 · 21:9 · 4:5 · 3:4 · 2:3 · 9:16

Resolution tiers

1K · 2K · 4K

Each image adapter declares whether it accepts native tiers, explicit pixels, fixed presets, or a prompt hint. Studio shows the actual request size or native tier. It never silently crops, stretches, or substitutes an unsupported ratio.

Permanent install, source setup, and optional providers

Install the command in an isolated, uv-managed environment:

uv tool install paperbanana-cn
paperbanana-cn studio

Run the current source checkout:

git clone https://github.com/mituan-ai/PaperBanana-CN.git
cd PaperBanana-CN
uv sync
uv run paperbanana-cn studio

The default package includes Studio, MCP, PDF input, OpenAI-compatible services, and Gemini.

Optional adapter	Install
AWS Bedrock	uv tool install "paperbanana-cn[bedrock]"
Anthropic	uv tool install "paperbanana-cn[anthropic]"
LiteLLM	uv tool install "paperbanana-cn[litellm]"
All optional providers	uv tool install "paperbanana-cn[all-providers]"

For CI, read credentials from environment variables rather than command-line values:

paperbanana-cn connections add \
  --role vlm \
  --name "Primary VLM" \
  --provider openai \
  --base-url "https://vlm.example.com/v1" \
  --model "your-vlm-model" \
  --api-key-env VLM_API_KEY

V1 is preserved. V2 moves forward.

V2 is maintained on main as the paperbanana-cn distribution, paperbanana_cn Python module, and paperbanana-cn command. V1 remains available as a frozen historical release:

• Browse the independent v1 branch
• Download the v1.0.0 release

Project and community

PaperBanana-CN is maintained by mituan.

• Ask usage questions in Discussions.
• Report reproducible bugs in Issues.
• Report vulnerabilities through Private Vulnerability Reporting.
• Read CONTRIBUTING.md before opening a pull request.

PaperBanana-CN is released under the MIT License. Its scientific figure-generation core is based on llmsresearch/paperbanana. This is an unofficial community implementation and is not affiliated with or endorsed by the upstream authors.

Development checks

git clone https://github.com/mituan-ai/PaperBanana-CN.git
cd PaperBanana-CN
uv sync --extra dev
uv run pytest tests/ -q
uv run ruff check paperbanana_cn/ mcp_server/ tests/ scripts/

Never upload API keys, private relay URLs, unpublished papers, private datasets, local connection stores, or generated run directories.

Star history