GitHub  |  Gitee  |  Atomgit Atomgit

简体中文 | 繁體中文 | English | ไทย | Tiếng Việt | 日本語 | Русский

Toonflow Logo # Toonflow

AI Short Drama Factory
With a tap, novels instantly become episodes!
AI scripts × AI visuals × Turbo generation 🔥

Stars Badge Apache-2.0 License Badge release

> 🚀 **One-stop short drama production**: From text to characters, from storyboard to video, 0 barrier full-process AI, 10x+ creation efficiency!
--- # 🌟 Main Features Toonflow is an AI short drama comic tool that leverages AI technology to automatically convert novels into scripts, and uses AI-generated images and videos for efficient short drama creation. With Toonflow, you can easily complete the entire process from text to images, making short drama production more intelligent and convenient. - ✅ **Character Generation** Automatically analyzes the original novel text, intelligently identifies and generates character settings, including appearance, personality, identity, etc., providing a reliable foundation for subsequent script and visual creation. - ✅ **Script Generation** Based on selected events and chapters, the system automatically generates structured scripts, covering dialogue, scene descriptions, and plot direction, enabling efficient transformation from literary texts to film/TV scripts. - ✅ **Storyboard Production** Based on the script content, intelligently generates storyboard prompts and visual design, detailing foreground/midground/background, character dynamics, prop settings, and scene layout; automatically turns scripts into storyboards, providing a complete route blueprint for video production. - ✅ **Video Composition** Integrates AI image and video technologies to generate video clips using AI. Includes online editing and supports personalized output adjustments, making film & TV production collaborative and efficient. --- # 📦 Application Scenarios - Short video content creation - Novel-to-film/TV experiments - AI literature adaptation tools - Script development and rapid prototyping - Video material generation --- # 🔰 User Guide ## 📺 Video Tutorial https://www.bilibili.com/video/BV1na6wB6Ea2 [![Toonflow 8-Minute Quick Start AI Video](./videoCover.png)](https://www.bilibili.com/video/BV1na6wB6Ea2) **Toonflow 8-Minute Quick Start AI Video** 👉 [Click to watch](https://www.bilibili.com/video/BV1na6wB6Ea2/?share_source=copy_web&vd_source=5b718c25439a901a34c7bc0c1d35b38e) 📱 Scan with WeChat on your phone to watch Scan WeChat to Watch --- # 🚀 Installation ## Prerequisites Before installing and using this software, please prepare the following: - ✅ Large language model AI service API address - ✅ Sora or Doubao video service API address - ✅ Nano Banana Pro image generation model service API ## Local Installation ### 1. Download & Install | Operating System | GitHub Download | Quark Cloud Download | Notes | | :--------------: | :------------------------------------------------------------ | :----------------------------------------------- | :------------- | | Windows | [Release](https://github.com/HBAI-Ltd/Toonflow-app/releases) | [Quark Cloud](https://pan.quark.cn/s/94ef07509df0) | Official installer | | Linux | [Release](https://github.com/HBAI-Ltd/Toonflow-app/releases) | [Quark Cloud](https://pan.quark.cn/s/94ef07509df0) | Official installer | | macOS | [Release](https://github.com/HBAI-Ltd/Toonflow-app/releases) | [Quark Cloud](https://pan.quark.cn/s/94ef07509df0) | Official installer | > [!CAUTION] > On MacOS, please go to Settings - Privacy & Security to configure security settings, otherwise, you may not be able to open the app due to certificate issues. > > See Zhihu documentation: [https://www.zhihu.com/question/433389276](https://www.zhihu.com/question/433389276) > Due to Gitee OS environment and Release file upload size limits, Gitee Release download is currently not available. ### 2. Start Service After installation, launch the program to start using this service. > ⚠️ **First-time Login** > Username: `admin` > Password: `admin123` ## Docker Deployment ### Prerequisites - [Docker](https://docs.docker.com/get-docker/) installed (version 20.10+) ### Method 1: Online Deployment To be developed; please use local build for now. ### Method 2: Local Build Build directly from local source code, suitable for developers or users who have cloned the repo; requires Git installed locally: ```shell # Clone the project (skip if already cloned) git clone https://github.com/HBAI-Ltd/Toonflow-app.git cd Toonflow-app # Build and start locally with docker-compose yarn docker:local # Or build manually docker build -t toonflow . docker run -d -p :10588 -v :/app/data toonflow # After this, the site can be accessed at /web/index.html on the mapped port # e.g. http://localhost:10588/web/index.html ``` ### Service Port Description | Port | Purpose | Deployment Mapping | | -------- | ------------ | -------------------- | | `10588` | App Interface | `10588:10588` | **Environment variable descriptions:** | Variable | Description | | ------------- | ------------------------------------------- | | `NODE_ENV` | Environment; `prod` for production | | `PORT` | Service listening port (default 10588) | | `OSSURL` | File storage access address for static files | --- ## Cloud Deployment ### 1. Server Requirements - **OS:** Ubuntu 20.04+ / CentOS 7+ - **Node.js:** 24.x (recommended, minimum 23.11.1+) - **RAM:** 2GB+ ### 2. Server Deployment #### 1. Install Environment ```bash # 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 Project **Clone from GitHub:** ```bash cd /opt git clone https://github.com/HBAI-Ltd/Toonflow-app.git cd Toonflow-app yarn install yarn build ``` **Clone from Gitee (Mainland China recommended):** ```bash cd /opt git clone https://gitee.com/HBAI-Ltd/Toonflow-app.git cd Toonflow-app yarn install yarn build ``` #### 3. Configure PM2 Create a `pm2.json` file: ```json { "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 descriptions:** | Variable | Description | | ------------- | ------------------------------------------- | | `NODE_ENV` | Environment; `prod` for production | | `PORT` | Service listening port | | `OSSURL` | File storage access address for static files | --- #### 4. Start Service ```bash pm2 start pm2.json pm2 startup pm2 save ``` #### 5. Common Commands ```bash pm2 list # View process list pm2 logs toonflow-app # View logs pm2 restart all # Restart service pm2 monit # Monitoring panel ``` > ⚠️ **First-time Login** > Username: `admin` > Password: `admin123` #### 6. Deploying the Frontend Website For standalone frontend deployment or customization, refer to the frontend repository: - **GitHub**: [Toonflow-web](https://github.com/HBAI-Ltd/Toonflow-web) - **Gitee**: [Toonflow-web](https://gitee.com/HBAI-Ltd/Toonflow-web) > 💡 **Note:** This repo already contains a compiled frontend by default. Regular users do NOT need to separately deploy the frontend. The frontend repo is for developers requiring secondary development. --- # 🔧 Developer Guide > [!CAUTION] > 🚧 **PR Submission Guidelines** 🚧 > > ⛔ `master` branch does NOT accept PRs | ✅ Please submit PRs to the `develop` branch > > Developers are invited to co-develop Toonflow. To join, contact owner ACT in the group chat. ## 🛠️ 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 / Qwen / xAI)| | Local Inference | @huggingface/transformers (ONNX) | | Real-Time | Socket.IO | | Desktop | Electron 40 | | Image Proc. | Sharp | | Container | Docker | ## Development Environment Preparation - **Node.js:** version 23.11.1 or above required - **Yarn:** recommended as the package manager ## Quick Start 1. **Clone the project** **Clone from GitHub:** ```bash git clone https://github.com/HBAI-Ltd/Toonflow-app.git cd Toonflow-app ``` **Clone from Gitee (Mainland China recommended):** ```bash git clone https://gitee.com/HBAI-Ltd/Toonflow-app.git cd Toonflow-app ``` 2. **Install dependencies** In the project root directory, install dependencies: ```bash yarn install ``` 3. **Start development environment** This project includes both **backend API service** and **frontend interface**. Start as needed: - **Option 1: Start backend service only** ```bash yarn dev ``` > ⚠️ This command starts only the backend API (port 10588), **without the web interface**. Accessing `http://localhost:10588` allows API calls only; the full web UI is unavailable. To use the frontend, start the frontend project separately or use GUI mode below. - **Option 2: Start Electron desktop client** ```bash yarn dev:gui ``` > This command starts both backend and Electron window, with built-in web UI. Out-of-the-box, no extra config needed. Recommended for a full experience. - **Option 3: Production mode** ```bash yarn start ``` > Runs compiled service in production mode (requires `yarn build` first). 4. **Build the project** - Compile TypeScript files: ```bash yarn build ``` - Build executable for Windows: ```bash yarn dist:win ``` - Build executable for Mac: ```bash yarn dist:mac ``` - Build executable for Linux: ```bash yarn dist:linux ``` 5. **Code quality check** - Perform lint check: ```bash yarn lint ``` 6. **AI Debug panel (Optional)** Start the Vercel AI SDK visual debugging tool for easier AI integration debugging: ```bash yarn debug:ai ``` ## Frontend Development To modify the frontend UI, develop in the frontend repository: - **GitHub**: [Toonflow-web](https://github.com/HBAI-Ltd/Toonflow-web) - **Gitee**: [Toonflow-web](https://gitee.com/HBAI-Ltd/Toonflow-web) After frontend build, copy the `dist` contents to this project's `data/web` to integrate. ## Project Structure ``` 📂 build/ # Compiled output 📂 data/ # Runtime data │ ├─ 📂 models/ # Local inference models (ONNX) │ ├─ 📂 oss/ # Object storage (assets/characters/scenes) │ ├─ 📂 serve/ # Production entry │ ├─ 📂 skills/ # Agent skill prompts │ └─ 📂 web/ # Built-in frontend assets 📂 ./ # Documentation assets 📂 env/ # Environment configs 📂 scripts/ # Build and helper scripts 📂 src/ ├─ 📂 agents/ # AI Agent modules │ ├─ 📂 productionAgent/ # Production Agent │ └─ 📂 scriptAgent/ # Script Agent ├─ 📂 lib/ # Common libraries (db, responses) ├─ 📂 middleware/ # Middleware ├─ 📂 routes/ # API routes │ ├─ 📂 agents/ # Agent memory management │ ├─ 📂 artStyle/ # Art style management │ ├─ 📂 assets/ # Asset management │ ├─ 📂 assetsGenerate/ # Asset generation │ ├─ 📂 cornerScape/ # Storyboard management │ ├─ 📂 general/ # General APIs │ ├─ 📂 login/ # Auth │ ├─ 📂 migrate/ # Data migration │ ├─ 📂 modelSelect/ # Model selection │ ├─ 📂 novel/ # Novel management │ ├─ 📂 other/ # Other features │ ├─ 📂 production/ # Production management │ ├─ 📂 project/ # Project management │ ├─ 📂 script/ # Script generation │ ├─ 📂 scriptAgent/ # Script Agent APIs │ ├─ 📂 setting/ # System settings │ ├─ 📂 task/ # Task management │ └─ 📂 test/ # Test APIs ├─ 📂 socket/ # WebSocket comms ├─ 📂 types/ # TypeScript types ├─ 📂 utils/ # Utility functions ├─ 📄 app.ts # App entry point ├─ 📄 core.ts # Core initialization ├─ 📄 env.ts # Env vars ├─ 📄 err.ts # Error handling ├─ 📄 logger.ts # Logging module ├─ 📄 router.ts # Route registration └─ 📄 utils.ts # General tools 📄 Dockerfile # Docker build config 📄 electron-builder.yml # Electron packaging config 📄 skillList.json # Skills list 📄 LICENSE # (Apache-2.0) License 📄 NOTICES.txt # Third-party dependencies 📄 package.json # Project config 📄 tsconfig.json # TypeScript config ``` --- # 🔗 Related Repositories | Repository | Description | GitHub | Gitee | | ---------------- | ---------------------------------- | ------------------------------------------------- | ------------------------------------------------- | | **Toonflow-app** | Full client (this repo, for users) | [GitHub](https://github.com/HBAI-Ltd/Toonflow-app)| [Gitee](https://gitee.com/HBAI-Ltd/Toonflow-app) | | **Toonflow-web** | Frontend source (for FE devs) | [GitHub](https://github.com/HBAI-Ltd/Toonflow-web)| [Gitee](https://gitee.com/HBAI-Ltd/Toonflow-web) | > 💡 **Tip:** If you just want to use Toonflow, download the client from this repo directly. The frontend repo is for developers needing secondary dev or UI customization. --- # 👨‍👩‍👧‍👦 WeChat Groups ~~Group 1~~ ~~Group 2~~ ... ~~Group 10~~ ~~Group 11~~ ~~Group 12~~ ~~Group 13~~ ... ~~Group 24~~ Group Assistant: Toonflow QR --- # 💌 Contact Us 📧 Email: [ltlctools@outlook.com](mailto:ltlctools@outlook.com?subject=Toonflow inquiry) --- # 📜 License Toonflow is open source under Apache-2.0; license details: https://www.apache.org/licenses/LICENSE-2.0 You may use Toonflow for all purposes, including commercial, so long as you comply with the terms of Apache-2.0. --- # ⭐️ Star History [![Star History Chart](https://api.star-history.com/svg?repos=HBAI-Ltd/Toonflow-app&type=timeline&legend=top-left)](https://www.star-history.com/#HBAI-Ltd/Toonflow-app&type=timeline&legend=top-left) --- # 🙏 Thanks Thank you to the following open-source projects for supporting Toonflow: - [Express](https://expressjs.com/) - Fast, open, minimalist Node.js Web framework - [AI SDK](https://ai-sdk.dev/) - TypeScript-first AI toolkit - [Better-SQLite3](https://github.com/WiseLibs/better-sqlite3) - High-performance SQLite3 bindings - [Sharp](https://sharp.pixelplumbing.com/) - High-performance Node.js image toolkit - [Axios](https://axios-http.com/) - Promise-based HTTP client - [Zod](https://zod.dev/) - TypeScript-first schema validation library - [Socket.IO](https://socket.io/) - Real-time bidirectional event framework - [Electron](https://www.electronjs.org/) - Cross-platform desktop app framework - [Hugging Face Transformers](https://huggingface.co./transformers.js) - Local ML inference library Thanks to the following organizations/individuals for their support:
SophNet Logo SophNet Cloud provides computing power sponsorship [Official Website]
For a complete list of third-party dependencies, see `NOTICES.txt`