Converts research papers into editable diagrams and slides

https://t.co/pRfnjfIXxT https://t.co/3SOJs9QOUf

OpenDCAI/Paper2Any

Source: https://github.com/OpenDCAI/Paper2Any

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 |

📑 Table of Contents

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

🔥 News

🆕 2026-04-24 · Image Model Playground Upgrade
Added a new Image Model Playground page for managed image generation across Nano Banana 2 / Nano Banana Pro / Image 2 / Image 2 All.
The workflow now supports language control, model-specific generation options, batch generation (1 / 2 / 4 / 8 / 16), compressed thumbnail previews, and one-click batch download.

🆕 2026-04-15 · 2026 Paper Updates
Two Paper2Any-related papers are now listed in the 2026 cycle:
Paper2SysArch: Structure-Constrained System Architecture Generation from Scientific Papers · CVPR 2026 Findings
SciFlow-Bench: Evaluating Structure-Aware Scientific Diagram Generation via Inverse Parsing · ACL 2026 Main

BibTeX

@article{guo2025paper2sysarch,
  title   = {Paper2SysArch: Structure-Constrained System Architecture Generation from Scientific Papers},
  author  = {Guo, Ziyi and Liu, Zhou and Zhang, Wentao},
  journal = {arXiv preprint arXiv:2511.18036},
  year    = {2025},
  note    = {CVPR 2026 Findings}
}

@article{zhang2026sciflowbench,
  title   = {SciFlow-Bench: Evaluating Structure-Aware Scientific Diagram Generation via Inverse Parsing},
  author  = {Zhang, Tong and Lin, Honglin and Liu, Zhou and Chen, Chong and Zhang, Wentao},
  journal = {arXiv preprint arXiv:2602.09809},
  year    = {2026},
  note    = {ACL 2026 Main}
}

🆕 2026-03-28 · Editable PPT Showcase Refresh
Added two new editable PPT showcase screenshots for the frontend-deck workflow:
a generated multi-slide gallery view and the canvas editing workspace with deck theme lock.

🆕 2026-03-26 · Workflow Showcase Update
Added showcase coverage for Paper2Video, Paper2Poster, and Paper2Citation.
The README now includes a compressed video demo plus refreshed English/Chinese workflow previews.

🆕 2026-02-02 · Paper2Rebuttal
Added rebuttal drafting support with structured response guidance and image-aware revision prompts.

🆕 2026-01-28 · Drawio Update
Added Drawio support for visual diagram creation and showcase-ready outputs in the workflow.
KB updates in one line: multi-file PPT generation with doc convert/merge, optional image injection, and embedding-assisted retrieval.

🆕 2026-01-25 · New Features
Added AI-assisted outline editing, three-layer model configuration system for flexible model selection, and user points management with daily quota allocation.
🌐 Online Demo: http://dcai-paper2any.nas.cpolar.cn/

🆕 2026-01-20 · Bug Fixes
Fixed bugs in experimental plot generation (image/text) and resolved the missing historical files issue.
🌐 Online Demo: http://dcai-paper2any.nas.cpolar.cn/

🆕 2026-01-14 · Feature Updates & Backend Architecture Upgrade

1. Feature Updates: Added Image2PPT, optimized Paper2Figure interaction, and improved PDF2PPT effects.
   
2. Standardized API: Refactored backend interfaces with RESTful /api/v1/ structure, removing obsolete endpoints for better maintainability.
   
3. Dynamic Configuration: Supported dynamic model selection (e.g., GPT-4o, Qwen-VL) via API parameters, eliminating hardcoded model dependencies.
   🌐 Online Demo: http://dcai-paper2any.nas.cpolar.cn/

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

✨ Core Features

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: Model architecture diagrams, technical roadmaps (PPT + SVG), and experimental plots with editable PPTX output.
• 🧩 Paper2Diagram / Image2Drawio - Editable Diagrams: Generate draw.io diagrams from paper/text or images, with drawio/png/svg export and chat-based edits.
• 🎬 Paper2PPT - Editable Slide Decks: Paper/text/topic to PPT, long-doc support, and built-in table/figure extraction.
• 📝 Paper2Rebuttal: Draft structured rebuttals and revision responses with claims-to-evidence grounding.
• 🖼️ PDF2PPT - Layout-Preserving Conversion: Accurate layout retention for PDF → editable PPTX.
• 🖼️ Image2PPT - Image to Slides: Convert images or screenshots into structured slides.
• 🔥 Image Model Playground: Directly call backend-managed image models with prompt templates, language control, batch generation, compressed previews, and zip download.
• 🎨 PPTPolish - Smart Beautification: AI-based layout optimization and style transfer.
• 🎬 Paper2Video: Generate video scripts and narration assets.
• 🖼️ Paper2Poster - Academic Poster: Turn paper PDFs into poster-ready layouts with configurable sections, logos, and export assets.
• 🔎 Paper2Citation - Citation Explorer: Track citing authors, institutions, and notable downstream works from author names or DOI/paper URLs.
• 📝 Paper2Technical: Produce technical reports and method summaries.
• 📚 Knowledge Base (KB): Ingest/embedding, semantic search, and KB-driven PPT/podcast/mindmap generation.

📸 Showcase

🧩 Drawio

✨ Upload a paper figure or screenshot as the starting point

✨ Keep the source structure visible before conversion

✨ Convert the image into an editable DrawIO canvas

✨ Generate a model or system diagram directly inside the DrawIO workbench

✨ Refine the generated architecture with chat editing and export-ready layout

📝 Paper2Rebuttal: Rebuttal Drafting

_{✨ Rebuttal drafting and revision support}

📊 Paper2Figure: Scientific Figure Generation

<sub>✨ Model Architecture Diagram Generation

✨ Model Architecture Diagram Generation</sub>

✨ Technical roadmap workbench: choose route type, input source, model config, and visual template

✨ Generated technical roadmap figure with structured dual-column layout

_{✨ Experimental Plot Generation (Multiple Styles)}

🎬 Paper2PPT: Paper to Presentation

✨ End-to-end PPT generation demo

✨ Paper / text / topic to polished slide deck

✨ Edit slide text directly on canvas while keeping the deck theme locked

✨ Review the generated multi-page gallery before export

✨ AI-assisted outline refinement with targeted rewrite prompts

✨ Structured outline editing down to section and bullet detail

_{✨ Long document support for 40+ slides · Intelligent table extraction and insertion · Version history and iterative deck management}

🎬 Paper2Video: PPT to Narrated Video

_{✨ PPT / PDF to narrated video with script confirmation, Aliyun TTS voices, and downloadable output}

🖼️ Paper2Poster: Paper to Poster

PNG poster result

PPT poster result

_{✨ Paper PDF to academic poster with configurable layout, editable poster output, and one-click export}

🔎 Paper2Citation: Citation Explorer

_{✨ Search authors or papers to inspect citation candidates, institutions, and downstream citation context}

🎨 PPT Smart Beautification

<sub>✨ AI-based Layout Optimization

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

🖼️ PDF2PPT: Layout-Preserving Conversion

<sub>✨ Intelligent Cutout & Layout Preservation

✨ Image2PPT</sub>

🚀 Quick Start

Requirements

.env Modes

Paper2Any now supports two configuration styles:

• Simple mode: use *.env.simple.example. Recommended for most self-hosted users.
• Advanced mode: use *.env.example. Use this only when you need workflow-specific model/provider overrides.

Quick choice:

cp fastapi_app/.env.simple.example fastapi_app/.env
cp frontend-workflow/.env.simple.example frontend-workflow/.env

If you need fine-grained workflow overrides instead:

cp fastapi_app/.env.example fastapi_app/.env
cp frontend-workflow/.env.example frontend-workflow/.env

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

# 2. Configure environment variables
cp fastapi_app/.env.simple.example fastapi_app/.env
cp frontend-workflow/.env.simple.example frontend-workflow/.env
cp deploy/docker.env.example deploy/docker.env

# Internal API auth key. Must match frontend VITE_API_KEY.
BACKEND_API_KEY=your-backend-api-key

# Recommended: let backend own all workflow model choices
APP_BILLING_MODE=free
PAPER2ANY_CONFIG_MODE=simple

# Required: unified text entry
SIMPLE_TEXT_API_URL=https://your-text-gateway/v1
SIMPLE_TEXT_API_KEY=your_text_key

# Optional but recommended: unified image entry
SIMPLE_IMAGE_API_URL=https://your-image-gateway
SIMPLE_IMAGE_API_KEY=your_image_key

# Optional: DrawIO OCR / VLM service
SIMPLE_OCR_API_URL=https://dashscope.aliyuncs.com/compatible-mode/v1
SIMPLE_OCR_API_KEY=your_dashscope_key

# Optional: MinerU official remote API
MINERU_API_BASE_URL=https://mineru.net/api/v4
MINERU_API_KEY=your_mineru_api_key

# Optional: SAM3 segmentation service for PDF2PPT / Image2PPT / Image2Drawio
# SAM3_SERVER_URLS=http://GPU_MACHINE_IP:8001
# SAM3_SERVER_URLS=http://GPU1:8021,http://GPU2:8022

# Optional: Supabase (skip for no auth — core features still work)
# SUPABASE_URL=https://your-project-id.supabase.co
# SUPABASE_ANON_KEY=your_supabase_anon_key

# Must match BACKEND_API_KEY in fastapi_app/.env
VITE_API_KEY=your-backend-api-key

# Usually keep VITE_API_BASE_URL empty in Docker, because nginx proxies /api and /outputs
VITE_API_BASE_URL=

# Frontend display defaults only
VITE_DEFAULT_LLM_API_URL=https://your-text-gateway/v1
VITE_DEFAULT_LLM_MODEL=gpt-4o

# Optional: Supabase (keep consistent with backend)
# VITE_SUPABASE_URL=https://your-project-id.supabase.co
# VITE_SUPABASE_ANON_KEY=your_supabase_anon_key

BACKEND_PORT=8000
FRONTEND_PORT=3000
DOCKER_APP_WORKERS=1

# Optional: enable local SAM3 container by running DOCKER_WITH_SAM3=1 bash deploy/docker-up.sh
SAM3_PORT=8021
SAM3_SERVER_URLS=

# 3. Build + run
bash deploy/docker-up.sh

🐧 Linux Installation

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

1. Create Environment & Install Base Dependencies

# 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 .

2. Install Paper2Any-specific Dependencies (Required)

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

The dependency boundary is now:

• requirements-base.txt: shared cross-platform Python runtime
• requirements-paper.txt: paper / PDF / figure extras
• requirements-cu12.txt: NVIDIA CUDA 12 Linux GPU extras
• requirements-system-ubuntu.txt: Ubuntu/Debian system packages, not Python packages

# 1. Paper / PDF / figure Python extras
pip install -r requirements-paper.txt

# 2. NVIDIA GPU runtime extras (Linux + CUDA 12 only)
pip install -r requirements-cu12.txt

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

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

# 5. System dependencies (Ubuntu example; full list is mirrored in requirements-system-ubuntu.txt)
sudo apt-get update
sudo apt-get install -y ffmpeg inkscape libreoffice poppler-utils wkhtmltopdf

ffmpeg, libreoffice/soffice, inkscape, poppler-utils, wkhtmltopdf, and tectonic are external system tools. They are not installed by pip, and deploy/start*.sh does not auto-install them.

3. Environment Variables

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

📚 For detailed configuration guide, see Configuration Guide for step-by-step instructions on configuring models, environment variables, and starting services.

4. Configure Environment Files (Optional)

# Copy backend environment file
cp fastapi_app/.env.example fastapi_app/.env

# Copy frontend environment file
cp frontend-workflow/.env.example frontend-workflow/.env

SUPABASE_URL=https://your-project-id.supabase.co
SUPABASE_ANON_KEY=your_supabase_anon_key

# Default LLM API URL
DEFAULT_LLM_API_URL=http://123.129.219.111:3000/v1/

# Workflow-level defaults
PAPER2PPT_DEFAULT_MODEL=gpt-5.1
PAPER2PPT_DEFAULT_IMAGE_MODEL=gemini-3-pro-image-preview
PDF2PPT_DEFAULT_MODEL=gpt-4o
# ... see .env.example for full list

# DrawIO OCR / VLM
PAPER2DRAWIO_OCR_API_URL=https://dashscope.aliyuncs.com/compatible-mode/v1
PAPER2DRAWIO_OCR_API_KEY=your_dashscope_key

# MinerU official remote API; if MINERU_API_KEY is empty, backend falls back to local MINERU_PORT
MINERU_API_BASE_URL=https://mineru.net/api/v4
MINERU_API_KEY=your_mineru_api_key
MINERU_API_MODEL_VERSION=vlm

# SAM3 segmentation service for PDF2PPT / Image2PPT / Image2Drawio
# One endpoint:
SAM3_SERVER_URLS=http://127.0.0.1:8001
# Or multiple endpoints for load balancing:
# SAM3_SERVER_URLS=http://127.0.0.1:8021,http://127.0.0.1:8022

# Default API URL shown in the UI
VITE_DEFAULT_LLM_API_URL=https://api.apiyi.com/v1

# Available API URLs in the dropdown (comma-separated)
VITE_LLM_API_URLS=https://api.apiyi.com/v1,http://b.apiyi.com:16888/v1,http://123.129.219.111:3000/v1

VITE_SUPABASE_URL=https://your-project.supabase.co
VITE_SUPABASE_ANON_KEY=your-anon-key

Quick Start: You can skip the .env configuration entirely and use CLI scripts directly with --api-key parameter. See CLI Scripts section below.

bash script/start_local_sam3_dev.sh

🪟 Windows Installation

We currently recommend trying Paper2Any on Linux / WSL. If you need to deploy on native Windows, please follow the steps below.

1. Create Environment & Install Base Dependencies

# 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 .

2. Install Paper2Any-specific Dependencies (Recommended)

Paper2Any involves LaTeX rendering and vector graphics processing, which require extra dependencies:

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

# NVIDIA GPU runtime extras (Linux only; skip on Windows)
# pip install -r requirements-cu12.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\

After configuring the Path, it is recommended to reopen the terminal (or restart VS Code / PowerShell) to ensure the environment variables take effect.

⚡ Install Windows Build of vLLM (Optional | For Local Inference Acceleration)

Release page: vllm-windows releases
Recommended version: 0.11.0

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

Please make sure the .whl matches your current environment:

• Python: cp312 (Python 3.12)
• Platform: win_amd64
• CUDA: cu124 (must match your local CUDA / driver)

Launch Application

Paper2Any - Paper Workflow Web Frontend (Recommended)

# Recommended one-click entrypoint on NVIDIA machines
bash deploy/start_nv.sh

Default local addresses:

• Frontend dev server: http://localhost:3000
• Backend health: http://127.0.0.1:8000/health

Useful local deploy commands:

• Start full stack (recommended): bash deploy/start_nv.sh
• Start backend only after loading a deploy profile: set -a && source deploy/profiles/nv.env && set +a && bash deploy/start.sh
• Stop backend: ./deploy/stop.sh
• Restart backend: ./deploy/restart.sh

Notes:

• deploy/start.sh reads deploy/app_config.sh, but it does not load deploy/profiles/*.env by itself.
• deploy/start_nv.sh is the safe one-click entrypoint because it loads deploy/profiles/nv.env, prepares local models, starts model servers, then starts backend and frontend.
• If you change APP_PORT, update the frontend proxy target in frontend-workflow/vite.config.ts as well.

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,
      },
      '/outputs': {
        target: 'http://127.0.0.1:8000',
        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

Launch Application

🎨 Web Frontend (Recommended)

# Recommended one-click entrypoint on NVIDIA machines
bash deploy/start_nv.sh

Visit http://localhost:3000. Backend health is available at http://127.0.0.1:8000/health by default.

🖥️ CLI Scripts (Command-Line Interface)

Paper2Any provides standalone CLI scripts that accept command-line parameters for direct workflow execution without requiring the web frontend/backend.

Environment Variables

Configure API access via environment variables (optional):

export DF_API_URL=https://api.openai.com/v1  # LLM API URL
export DF_API_KEY=sk-xxx                      # API key
export DF_MODEL=gpt-4o                        # Default model

Available CLI Scripts

1. Paper2Figure CLI - Generate scientific figures (3 types)

# Generate model architecture diagram from PDF
python script/run_paper2figure_cli.py \
  --input paper.pdf \
  --graph-type model_arch \
  --api-key sk-xxx

# Generate technical roadmap from text
python script/run_paper2figure_cli.py \
  --input "Transformer architecture with attention mechanism" \
  --input-type TEXT \
  --graph-type tech_route

# Generate experimental data visualization
python script/run_paper2figure_cli.py \
  --input paper.pdf \
  --graph-type exp_data

Graph types: model_arch (model architecture), tech_route (technical roadmap), exp_data (experimental plots)

2. Paper2PPT CLI - Convert papers to PPT presentations

# Basic usage
python script/run_paper2ppt_cli.py \
  --input paper.pdf \
  --api-key sk-xxx \
  --page-count 15

# With custom style
python script/run_paper2ppt_cli.py \
  --input paper.pdf \
  --style "Academic style; English; Modern design" \
  --language en

3. PDF2PPT CLI - One-click PDF to editable PPT

# Basic conversion (no AI enhancement)
python script/run_pdf2ppt_cli.py --input slides.pdf

# With AI enhancement
python script/run_pdf2ppt_cli.py \
  --input slides.pdf \
  --use-ai-edit \
  --api-key sk-xxx

4. Image2PPT CLI - Convert images to editable PPT

# Basic conversion
python script/run_image2ppt_cli.py --input screenshot.png

# With AI enhancement
python script/run_image2ppt_cli.py \
  --input diagram.jpg \
  --use-ai-edit \
  --api-key sk-xxx

5. PPT2Polish CLI - Beautify existing PPT files

# Basic beautification
python script/run_ppt2polish_cli.py \
  --input old_presentation.pptx \
  --style "Academic style, clean and elegant" \
  --api-key sk-xxx

# With reference image for style consistency
python script/run_ppt2polish_cli.py \
  --input old_presentation.pptx \
  --style "Modern minimalist style" \
  --ref-img reference_style.png \
  --api-key sk-xxx

System Requirements for PPT2Polish:

• LibreOffice: sudo apt-get install libreoffice (Ubuntu/Debian)
• pdf2image: pip install pdf2image
• poppler-utils: sudo apt-get install poppler-utils

Common Options

All CLI scripts support these common options:

• --api-url URL - LLM API URL (default: from DF_API_URL env var)
• --api-key KEY - API key (default: from DF_API_KEY env var)
• --model NAME - Text model name (default: varies by script)
• --output-dir DIR - Custom output directory (default: outputs/cli/{script_name}/{timestamp})
• --help - Show detailed help message

For complete parameter documentation, run any script with --help:

python script/run_paper2figure_cli.py --help

📂 Project Structure

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

🗺️ Roadmap

Feature	Status	Sub-features
📊 Paper2Figure Editable Scientific Figures
🧩 Paper2Diagram Drawio Diagrams
🎬 Paper2PPT Editable Slide Decks
🖼️ PDF2PPT Layout-Preserving Conversion
🖼️ Image2PPT Image to Slides
🎨 PPTPolish Smart Beautification
📚 Knowledge Base KB Workflows
🎬 Paper2Video Video Script Generation

🤝 Contributing

We welcome all forms of contribution!

📄 License

This project is licensed under Apache License 2.0.