Paper2Any

English | 中文

✨ Focus on paper multimodal workflows: from paper PDFs/screenshots/text to one-click generation of model diagrams, technical roadmaps, experimental plots, and slide decks ✨

| 📄 Universal File Support  |  🎯 AI-Powered Generation  |  🎨 Custom Styling  |  ⚡ Lightning Speed |

• Paper2Any (this repo):

  • Focuses on paper multimodal workflows (Paper2Figure, Paper2PPT, Paper2Video, etc.).
  • Provides one-click tools for scientific plotting, PPT generation, and video script assistance for researchers.

• DataFlow-Agent (new repo):

  • Focuses on DataFlow operator orchestration and authoring.
  • Provides a general-purpose multi-agent dataflow processing framework and operator development toolkits.

• 🔥 News
• ✨ Core Features
• 📸 Showcase
• 🚀 Quick Start
• 📂 Project Structure
• 🗺️ Roadmap
• 🤝 Contributing

• 2025-12-12 · Paper2Figure Web public beta is live
• 2025-10-01 · Released the first version 0.1.0

From paper PDFs / images / text to editable scientific figures, slide decks, video scripts, academic posters, and other multimodal content in one click.

Paper2Any currently includes the following sub-capabilities:

• 📊 Paper2Figure - Editable Scientific Figures: One-click generation of model architecture diagrams, technical roadmaps (PPT + SVG), and experimental plots. Supports multiple input sources and outputs editable PPTX.
• 🎬 Paper2PPT - Editable Slide Decks: Generate PPTs in arbitrary styles, support ultra-long document processing, and include built-in table extraction and chart parsing.
• 🖼️ PDF2PPT - Layout-Preserving Conversion: Intelligent cutout and layout analysis to accurately convert PDFs into editable PPTX.
• 🎨 PPT Smart Beautification: AI-based PPT layout optimization and style transfer.

<sub>✨ Model Architecture Diagram Generation

✨ Model Architecture Diagram Generation</sub>

_{✨ Technical Roadmap Generation}

_{✨ Experimental Plot Generation (Multiple Styles)}

<sub>✨ PPT Generation Demo

✨ Paper / Text / Topic → PPT</sub>

_{✨ Long Document Support (40+ Slides)}

_{✨ Intelligent Table Extraction & Insertion}

<sub>✨ AI-based Layout Optimization

✨ AI-based Layout Optimization & Style Transfer</sub>

<sub>✨ Intelligent Cutout & Layout Preservation

✨ Image2PPT</sub>

We recommend using Conda to create an isolated environment (Python 3.11).

# 0. Create and activate a conda environment
conda create -n paper2any python=3.11 -y
conda activate paper2any

# 1. Clone repository
git clone https://github.com/OpenDCAI/Paper2Any.git
cd Paper2Any

# 2. Install base dependencies
pip install -r requirements-base.txt

# 3. Install in editable (dev) mode
pip install -e .

Paper2Any involves LaTeX rendering, vector graphics processing as well as PPT/PDF conversion, which require extra dependencies:

# 1. Python dependencies
pip install -r requirements-paper.txt || pip install -r requirements-paper-backup.txt

# 2. LaTeX engine (tectonic) - recommended via conda
conda install -c conda-forge tectonic -y

# 3. Resolve doclayout_yolo dependency conflicts (Important)
pip install doclayout_yolo --no-deps

# 4. System dependencies (Ubuntu example)
sudo apt-get update
sudo apt-get install -y inkscape libreoffice poppler-utils wkhtmltopdf

export DF_API_KEY=your_api_key_here
export DF_API_URL=xxx  # Optional: if you need a third-party API gateway
export MINERU_DEVICES="0,1,2,3" # Optional: MinerU task GPU resource pool

Create a .env file under the frontend-workflow directory and fill in the following configuration:

# frontend-workflow/.env

VITE_SUPABASE_URL=your_supabase_url
VITE_SUPABASE_ANON_KEY=your_supabase_anon_key

# Backend
SUPABASE_URL=your_supabase_url
SUPABASE_ANON_KEY=your_supabase_anon_key
SUPABASE_SERVICE_ROLE_KEY=your_service_role_key
SUPABASE_JWT_SECRET=your_jwt_secret

# Application Settings
DAILY_WORKFLOW_LIMIT=10

# 0. Create and activate a conda environment
conda create -n paper2any python=3.12 -y
conda activate paper2any

# 1. Clone repository
git clone https://github.com/OpenDCAI/Paper2Any.git
cd Paper2Any

# 2. Install base dependencies
pip install -r requirements-win-base.txt

# 3. Install in editable (dev) mode
pip install -e .

Paper2Any involves LaTeX rendering and vector graphics processing, which require extra dependencies (see requirements-paper.txt):

# Python dependencies
pip install -r requirements-paper.txt

# tectonic: LaTeX engine (recommended via conda)
conda install -c conda-forge tectonic -y

🎨 Install Inkscape (SVG/Vector Graphics Processing | Recommended/Required)

1. Download and install (Windows 64-bit MSI): Inkscape Download
2. Add the Inkscape executable directory to the system environment variable Path (example): C:\Program Files\Inkscape\bin\

Release page: vllm-windows releases
Recommended version: 0.11.0

pip install vllm-0.11.0+cu124-cp312-cp312-win_amd64.whl

Paper2Any - Paper Workflow Web Frontend (Recommended)

# Start backend API
cd fastapi_app
uvicorn main:app --host 0.0.0.0 --port 8000

# Start frontend (new terminal)
cd frontend-workflow
npm install
npm run dev

Configure Frontend Proxy

Modify server.proxy in frontend-workflow/vite.config.ts:

export default defineConfig({
  plugins: [react()],
  server: {
    port: 3000,
    open: true,
    allowedHosts: true,
    proxy: {
      '/api': {
        target: 'http://127.0.0.1:8000',  // FastAPI backend address
        changeOrigin: true,
      },
    },
  },
})

Visit http://localhost:3000.

Windows: Load MinerU Pre-trained Model

# Start in PowerShell
vllm serve opendatalab/MinerU2.5-2509-1.2B `
  --host 127.0.0.1 `
  --port 8010 `
  --logits-processors mineru_vl_utils:MinerULogitsProcessor `
  --gpu-memory-utilization 0.6 `
  --trust-remote-code `
  --enforce-eager

# Start backend API
cd fastapi_app
uvicorn main:app --host 0.0.0.0 --port 8000

# Start frontend (new terminal)
cd frontend-workflow
npm install
npm run dev

Visit http://localhost:3000.

Paper2Any/
├── dataflow_agent/          # Core codebase
│   ├── agentroles/         # Agent definitions
│   │   └── paper2any_agents/ # Paper2Any-specific agents
│   ├── workflow/           # Workflow definitions
│   ├── promptstemplates/   # Prompt templates
│   └── toolkits/           # Toolkits (drawing, PPT generation, etc.)
├── fastapi_app/            # Backend API service
├── frontend-workflow/      # Frontend web interface
├── static/                 # Static assets
├── script/                 # Script tools
└── tests/                  # Test cases

Feature	Status	Sub-features
📊 Paper2Figure Editable Scientific Figures
🎬 Paper2PPT Editable Slide Decks
🖼️ PDF2PPT Layout-Preserving Conversion
🎨 PPT Beautification Smart Layout Optimization

We welcome all forms of contribution!

This project is licensed under Apache License 2.0.