| |

🚀 All-in-One Short Drama Workflow: From text to characters, from storyboards to videos — zero-threshold full-process AI automation, boosting creative efficiency by 10x+!

🌐 Multi-language Support

Toonflow supports the following interface languages:

Language	Language
Chinese (Simplified)	简体中文
Chinese (Traditional)	繁體中文
English	English
Thai	ไทย
Vietnamese	Tiếng Việt
Japanese	日本語
Russian	Русский

💡 More languages are being adapted — contributions for translations are welcome!

🌟 Key Features

Toonflow is an AI workstation designed for short drama production, building a complete closed loop around "Planning → Scriptwriting → Storyboarding → Final Output," supporting a localized, programmable, and continuously iterable production workflow.

✅ Infinite Canvas Production Workbench
Organize scripts, characters, storyboards, assets, and video nodes in an infinite canvas-like layout, supporting free arrangement, backtracking, and parallel production without linear constraints.
✅ Three-layer Agent Collaboration System
Decision, execution, and supervision layers work together, covering task decomposition, content generation, quality review, and revision feedback, improving stability and output consistency.
✅ Persistent Agent Memory
Cross-session memory system based on local ONNX vector retrieval, supporting short-term messages, long-term summaries, and semantic recall, ensuring multi-round creative continuity.
✅ Programmable Provider System
Write vendor TypeScript logic directly in the settings center, taking effect instantly without modifying source code or restarting, making it easy to privatize and integrate multiple models.
✅ Chapter Event Graph-driven Adaptation
Automatically extract chapter events from original novels and store them structurally. Script adaptation uses event graphs to precisely invoke context, reducing information loss in long texts.
✅ Skill File Configuration
Core prompts for ScriptAgent and ProductionAgent are externalized as Markdown Skill files, supporting online editing and rapid tuning.

📦 Application Scenarios

Short video content creation
Novel-to-film experimentation
AI literary adaptation tool
Script development and rapid prototyping
Video asset generation

🔰 User Guide

Quick Start

Launch the application and log in (default: admin / admin123).
Complete model vendor configuration in the settings center (text/image/video models).
Create a new project and import the original novel, then execute chapter event extraction.
Enter ScriptAgent to generate the story skeleton, adaptation strategy, and structured script.
Switch to ProductionAgent to organize storyboards, assets, and video nodes on the infinite canvas.
Perform node-based refinement on storyboard images, then return them to the workbench for video stitching and export.

📺 Video Tutorial

https://www.bilibili.com/video/BV1oXD7BqEqJ

Toonflow 12-minute Quick Start AI Video 👉 Click to Watch

📱 Scan with WeChat to watch

📸 Demo Screenshots & Video

The following screenshots and video are from a short AI drama demo made with Toonflow, completed in about 2 hours, covering script generation, storyboard creation, and editing.

🎬 Demo Video

demo.mp4

If the video cannot play, please click to download

Demo Info

Item	Details
Production Cycle	Approximately 2 hours
Video Model	Seedance 2.0
Image Model	GPT Image 2
Language Model	Claude Opus 4.6
Total Duration	Approximately 2 minutes (raw 3 min, cut ~1 min of unusable footage)

Cost Breakdown

Model Type	Cost
Language Model	~￥10
Video Model (full generation)	~￥120
Image Model	Less than ￥1
Total	~￥130

Disclaimer: The demo's original resolution is 1080×1882; the release version has been compressed to 480p. If there are any copyright issues, please contact us to delete it.

🚀 Installation

Prerequisites

Before installing and using this software, please prepare the following:

✅ Large language model AI service API endpoint
✅ Sora or Doubao video service API endpoint
✅ Nano Banana Pro image generation model service API

Local Installation

1. Download & Install

OS	GitHub	Notes
Windows	Release	Official release package
Linux	Release	Official release package
macOS	Release	Official release package

Caution

On macOS, go to Settings > Privacy & Security to configure security settings; otherwise, the app may not open due to certificate issues.

Reference: https://www.zhihu.com/question/433389276

Due to Gitee OS environment limitations and Release file upload size restrictions, we currently do not provide a Gitee Release download link.

2. Start the Service

After installation, launch the program to start using the service.

⚠️ First Login
Username: admin
Password: admin123

Docker Deployment

Prerequisites

Docker installed (version 20.10+)

Method 1: Online Deployment

To be completed; use local build for now.

Method 2: Local Build

Build directly from existing local source code, suitable for developers or users who have already cloned the repository. Requires git installed locally:

# Clone the project first (skip if already cloned)
git clone https://github.com/HBAI-Ltd/Toonflow-app.git
cd Toonflow-app

# Build and start locally using docker-compose
yarn docker:local

# Or build manually
docker build -t toonflow .
docker run -d -p <local_port>:10588 -v <local_data_path>:/app/data toonflow

# Access the page at the corresponding port path /web/index.html
# Example: http://localhost:10588/web/index.html

Service Port Description

Port	Purpose	Deployment Mapping
`10588`	Software UI	`10588:10588`

Environment Variables:

Variable	Description
`NODE_ENV`	Running environment; `prod` for production
`PORT`	Service listening port (default 10588)
`OSSURL`	File storage access URL for static assets

Cloud Deployment

I. Server Environment Requirements

OS: Ubuntu 20.04+ / CentOS 7+
Node.js: 24.x (recommended, minimum 23.11.1+)
Memory: 2GB+

II. Server Deployment

1. Install Environment

# Install Node.js
curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.39.7/install.sh | bash
source ~/.bashrc
nvm install 24
# Install Yarn and PM2
npm install -g yarn pm2

2. Deploy the Project

Clone from GitHub:

cd /opt
git clone https://github.com/HBAI-Ltd/Toonflow-app.git
cd Toonflow-app
yarn install
yarn build

Clone from Gitee (recommended for China):

cd /opt
git clone https://gitee.com/HBAI-Ltd/Toonflow-app.git
cd Toonflow-app
yarn install
yarn build

3. Configure PM2

Create pm2.json file:

{
  "name": "toonflow-app",
  "script": "data/serve/app.js",
  "instances": "max",
  "exec_mode": "cluster",
  "env": {
    "NODE_ENV": "prod",
    "PORT": 10588,
    "OSSURL": "http://127.0.0.1:10588/"
  }
}

Environment Variable Description:

Variable	Description
`NODE_ENV`	Running environment; `prod` for production
`PORT`	Service listening port
`OSSURL`	File storage access URL for static assets

4. Start the Service

pm2 start pm2.json
pm2 startup
pm2 save

5. Common Commands

pm2 list              # View processes
pm2 logs toonflow-app # View logs
pm2 restart all       # Restart services
pm2 monit             # Monitoring dashboard

⚠️ First Login
Username: admin
Password: admin123

6. Deploy the Frontend

If you need to deploy or customize the frontend separately, please refer to the frontend repository:

GitHub: Toonflow-web
Gitee: Toonflow-web

💡 Note: This repository already includes pre-built frontend resources; regular users do not need to deploy the frontend separately. The frontend repository is for developers who need secondary development.

🔧 Development Guide

Caution

🚧 PR Submission Guidelines 🚧

⛔ Do not submit PRs to the master branch. ✅ Please submit PRs to the develop branch.

Developers are welcome to contribute to Toonflow. If interested, please contact the maintainer ACT in the community group.

🛠️ Tech Stack

Category	Technology
Runtime	Node.js 23.11.1+
Language	TypeScript 5.x
Backend	Express 5
Database	SQLite (better-sqlite3 / knex)
AI Integration	Vercel AI SDK (OpenAI / Anthropic / Google / DeepSeek / Zhipu / MiniMax / Tongyi Qianwen / xAI)
Local Inference	@huggingface/transformers (ONNX)
Real-time	Socket.IO
Desktop	Electron 40
Image Processing	Sharp
Containerization	Docker

Development Environment Setup

Node.js: Version 23.11.1 or higher
Yarn: Recommended as package manager

Quick Start Project

Clone the Project

Clone from GitHub:

git clone https://github.com/HBAI-Ltd/Toonflow-app.git
cd Toonflow-app

Clone from Gitee (recommended for China):

git clone https://gitee.com/HBAI-Ltd/Toonflow-app.git
cd Toonflow-app

Install Dependencies

Run the following command in the project root to install dependencies:
```
yarn install
```
Start Development Environment

This project includes both the backend API service and frontend pages. Choose the appropriate startup method:
- Method 1: Start backend only
```
yarn dev
```
  ⚠️ This command starts only the backend API service (port 10588), without the frontend. Accessing http://localhost:10588 will only call API endpoints, not display the full UI. To use the frontend, either run the frontend project separately or use the GUI mode below.
- Method 2: Start Electron Desktop Client
```
yarn dev:gui
```
  This command starts both the backend service and the Electron desktop window with a built-in frontend page, ready to use out of the box. Ideal for developers who want the full experience.
- Method 3: Production Mode
```
yarn start
```
  Runs the compiled service in production mode (requires yarn build first).
Package the Project
- Compile and generate TypeScript files:
```
yarn build
```
- Package as Windows executable:
```
yarn dist:win
```
- Package as macOS executable:
```
yarn dist:mac
```
- Package as Linux executable:
```
yarn dist:linux
```
Code Quality Check
- Run global syntax and lint checks:
```
yarn lint
```
AI Debug Panel (Optional)

Launch a visual debugging tool for the AI SDK to facilitate debugging AI calls:
```
yarn debug:ai
```

Frontend Development

To modify the frontend, please use the frontend repository:

GitHub: Toonflow-web
Gitee: Toonflow-web

After building the frontend, copy the dist directory contents into the data/web directory of this project to integrate.

Project Structure

📂 build/                    # Build artifacts
📂 data/                     # Runtime data
│  ├─ 📂 models/            # Local inference models (ONNX)
│  ├─ 📂 oss/               # Object storage (assets/characters/scenes)
│  ├─ 📂 serve/             # Production entry point
│  ├─ 📂 skills/            # Agent skill prompts
│  └─ 📂 web/               # Frontend build artifacts (built-in)
📂 docs/                     # Documentation resources
📂 env/                      # Environment configuration
📂 scripts/                  # Build and helper scripts
📂 src/
├─ 📂 agents/               # AI Agent modules
│  ├─ 📂 productionAgent/   # Production Agent
│  └─ 📂 scriptAgent/       # Script Agent
├─ 📂 lib/                  # Common libraries (DB init, response formats)
├─ 📂 middleware/            # Middleware
├─ 📂 routes/               # Route modules
│  ├─ 📂 agents/            # Agent memory management
│  ├─ 📂 artStyle/          # Art style management
│  ├─ 📂 assets/            # Asset management
│  ├─ 📂 assetsGenerate/    # Asset generation
│  ├─ 📂 cornerScape/       # Storyboard management
│  ├─ 📂 general/           # General interfaces
│  ├─ 📂 login/             # Login authentication
│  ├─ 📂 migrate/           # Data migration
│  ├─ 📂 modelSelect/       # Model selection
│  ├─ 📂 novel/             # Novel management
│  ├─ 📂 other/             # Other features
│  ├─ 📂 production/        # Production management
│  ├─ 📂 project/           # Project management
│  ├─ 📂 script/            # Script generation
│  ├─ 📂 scriptAgent/       # Script Agent API
│  ├─ 📂 setting/           # System settings
│  ├─ 📂 task/              # Task management
│  └─ 📂 test/              # Test interfaces
├─ 📂 socket/               # WebSocket real-time communication
├─ 📂 types/                # TypeScript type declarations
├─ 📂 utils/                # Utility functions
├─ 📄 app.ts                # Application entry
├─ 📄 core.ts               # Core initialization
├─ 📄 env.ts                # Environment variable handling
├─ 📄 err.ts                # Error handling
├─ 📄 logger.ts             # Logging module
├─ 📄 router.ts             # Route registration
└─ 📄 utils.ts              # Common utilities
📄 Dockerfile                # Docker build file
📄 electron-builder.yml      # Electron packaging config
📄 skillList.json            # Skill list
📄 LICENSE                   # License (Apache-2.0)
📄 NOTICES.txt               # Third-party dependency notices
📄 package.json              # Project configuration
📄 tsconfig.json             # TypeScript configuration

🔗 Related Repositories

Repository	Description	GitHub	Gitee
Toonflow-app	Full client (this repo, recommended for regular users)	GitHub	Gitee
Toonflow-web	Frontend source code (for frontend developers)	GitHub	Gitee

💡 Tip: If you simply want to use Toonflow, download the client from this repository. The frontend repository is for developers who need secondary development or UI customization.

👨‍👩‍👧‍👦 WeChat Group

Helper bot:

You can also click the icon to join Discord:

Or click the invite link: https://discord.gg/HEjKmpNpAZ

💌 Contact Us

📧 Email: [ltlctools@outlook.com](mailto:ltlctools@outlook.com?subject=Toonflow Inquiry)

📜 License

Toonflow is open-sourced under the Apache-2.0 license, with supplementary commercial terms.

License details: https://www.apache.org/licenses/LICENSE-2.0

Supplementary Agreement

If you distribute this software as a product to 2 or more independent third parties, you must obtain written commercial authorization from HBAI-Ltd.
≤ 5 legal entities jointly operating for internal use without providing services externally is considered internal use and does not require authorization.
Do not remove or modify any Toonflow identifiers or copyright information.

Permanent Free Use Cases

✅ Creating content with Toonflow and receiving platform revenue shares
✅ Secondary development for internal team use
✅ ≤ 5 legal entities joint internal operation
✅ Personal learning, research, non-commercial use

Commercial License Pricing

Stage	Annual Revenue	Annual Fee
🌱 Support	< ¥100,000	Free license upon request
🚀 Startup	¥100–500,000	¥5,000/year
📈 Growth	¥500k–1.5M	¥20,000/year
🏢 Scale	¥1.5M–5M	¥80,000/year
🌐 Enterprise	> ¥5M	Negotiable

Non-retroactive clause: Users who used Toonflow under AGPL-3.0 before the v1.0.8 release will continue to be governed by AGPL-3.0 and are not affected by this agreement change.

See the full agreement in the LICENSE file.

⭐️ Star History

🙏 Acknowledgements

We thank the following open-source projects for providing powerful support to Toonflow:

Express - Fast, unopinionated, minimalist web framework for Node.js
AI SDK - AI toolkit for TypeScript
Better-SQLite3 - High-performance SQLite3 binding
Sharp - High-performance Node.js image processing
Axios - Promise-based HTTP client
Zod - TypeScript-first schema validation
Socket.IO - Real-time bidirectional event-based communication
Electron - Cross-platform desktop application framework
Hugging Face Transformers - Local ML inference library

We also thank the following organizations/units/individuals for their support:

Name	Support Type	Introduction	Website
Sophnet	💻 Computing Sponsorship	Committed to building a faster, more stable, and more cost-effective one-stop model inference API service platform	Website
Atlas Cloud	💻 Computing Sponsorship	The world's first full-modality reasoning platform. Dialogue, image, video, audio — all unified API. 300+ models, OpenAI compatible.	Website
Tencent Hunyuan 3D	🌐 World Model Technical Support	Tencent Hunyuan 3D AI creation engine based on version 2.5 of the Hunyuan 3D generation large model, the industry's first one-stop 3D content AI creation platform. Features text-to-3D, image-to-3D, 3D animation generation, texture generation, supports sketch-to-3D, 3D character generation, with advantages in low-poly model generation.	Website

For the complete list of third-party dependencies, please refer to NOTICES.txt

FilesExpand file tree

README.en.md

Latest commit

History

README.en.md

File metadata and controls

🌐 Multi-language Support

🌟 Key Features

📦 Application Scenarios

🔰 User Guide

Quick Start

📺 Video Tutorial

📸 Demo Screenshots & Video

🎬 Demo Video

Demo Info

Cost Breakdown

🚀 Installation

Prerequisites

Local Installation

1. Download & Install

2. Start the Service

Docker Deployment

Prerequisites

Method 1: Online Deployment

Method 2: Local Build

Service Port Description

Cloud Deployment

I. Server Environment Requirements

II. Server Deployment

1. Install Environment

2. Deploy the Project

3. Configure PM2

4. Start the Service

5. Common Commands

6. Deploy the Frontend

🔧 Development Guide

🛠️ Tech Stack

Development Environment Setup

Quick Start Project

Frontend Development

Project Structure

🔗 Related Repositories

👨‍👩‍👧‍👦 WeChat Group

💌 Contact Us

📜 License

Supplementary Agreement

Permanent Free Use Cases

Commercial License Pricing

⭐️ Star History

🙏 Acknowledgements

copyright © Beijing Ai'a Technology Co., Ltd.