Toonflow-app Documentation

File: README.md Copy Chapter

🌐 多语言支持

Toonflow 支持以下语言界面：

💡 更多语言适配中，欢迎贡献翻译！

🌟 主要功能

Toonflow 是面向短剧生产的 AI 工作台，围绕“策划 → 编剧 → 分镜 → 出片”构建完整闭环，并支持本地化、可编程、可持续迭代的生产流程。

• ✅ 无限画布生产工作台
  以类无限画布形式组织剧本、角色、分镜、素材与视频节点，支持自由编排、回溯与并行生产，不受线性步骤限制。
• ✅ 三层 Agent 协作体系
  决策层、执行层、监督层协同工作，覆盖任务拆解、内容生成、质量审阅与修订反馈，提升稳定性与成片一致性。
• ✅ 持久化 Agent 记忆
  基于本地 ONNX 向量检索的跨会话记忆系统，支持短期消息、长期摘要和语义召回，确保多轮创作连续性。
• ✅ 可编程供应商系统
  支持在设置中心直接编写供应商 TypeScript 逻辑并即时生效，无需改源码或重启，便于私有化和多模型接入。
• ✅ 章节事件图谱驱动改编
  自动提取原著章节事件并结构化存储，剧本改编按事件图谱精准调用上下文，减少长文本信息丢失。
• ✅ Skill 文件化配置
  ScriptAgent 与 ProductionAgent 的核心提示词外化为 Markdown Skill 文件，支持在线编辑与快速调优。

📦 应用场景

• 短视频内容创作
• 小说影视化实验
• AI 文学改编工具
• 剧本开发与快速原型
• 视频素材生成

🔰 使用指南

快速上手 Copy Chapter

1. 启动应用并登录（默认账号：admin / admin123）。
2. 在设置中心完成模型供应商配置（文本/图像/视频模型）。
3. 新建项目并导入原著，执行章节事件提取。
4. 进入 ScriptAgent 生成故事骨架、改编策略与结构化剧本。
5. 切换到 ProductionAgent，在无限画布中组织分镜、素材与视频节点。
6. 对分镜图进行节点化精调后回流工作台，完成视频拼接与导出。

📺 视频教程 Copy Chapter

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

Toonflow 12 分钟快速上手 AI 视频
👉 点击观看

📱 手机微信扫码观看

📸 演示截图与视频

以下截图及视频来自使用 Toonflow 制作的一段 AI 短剧 Demo，全程约 2 小时完成，涵盖剧本生成、分镜制作及剪辑环节。

🎬 Demo 视频 Copy Chapter

Demo 信息 Copy Chapter

成本明细 Copy Chapter

声明：Demo 原始分辨率为 1080×1882，发布版本已压缩至 480p。如涉及版权问题，请联系我们删除处理。

🚀 安装

前置条件 Copy Chapter

在安装和使用本软件之前，请准备以下内容：

• ✅ 大语言模型 AI 服务接口地址
• ✅ Sora 或豆包视频服务接口地址
• ✅ Nano Banana Pro 图片生成模型服务接口

本机安装 Copy Chapter

1. 下载与安装 Copy Section

[!CAUTION]
MacOS 系统请到 设置-隐私与安全性 配置安全性否则可能因证书问题无法正常打开

参考知乎文档：https://www.zhihu.com/question/433389276

因 Gitee OS 环境限制及 Release 文件上传大小限制，暂不提供 Gitee Release 下载地址。

2. 启动服务 Copy Section

安装完成后，启动程序即可开始使用本服务。

⚠️ 首次登录
账号：admin
密码：admin123

Docker 部署 Copy Chapter

前置条件 Copy Section

• 已安装 Docker（版本 20.10+）

方式一：在线部署 Copy Section

待完善，暂时使用本地构建。

方式二：本地构建 Copy Section

使用本地已有的源码直接构建，适合开发者或已克隆仓库的用户，这需要你在本地安装 git：

# 先克隆项目（如已有则跳过）
git clone https://github.com/HBAI-Ltd/Toonflow-app.git
cd Toonflow-app

# 使用 docker-compose 本地构建并启动
yarn docker:local

# 或者手动构建
docker build -t toonflow .
docker run -d -p <本地端口>:10588 -v <本地数据路径>:/app/data toonflow

# 此时在相应端口的 /web/index.html 路径即可访问页面
# 例如 http://localhost:10588/web/index.html

服务端口说明 Copy Section

环境变量说明：

云端部署 Copy Chapter

云服务器部署 Copy Section

一、服务器环境要求

• 系统：Ubuntu 20.04+ / CentOS 7+
• Node.js：24.x（推荐，最低 23.11.1+）
• 内存：2GB+

二、服务器部署

1. 安装环境

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

2. 部署项目

从 GitHub 克隆：

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

从 Gitee 克隆（国内推荐）：

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

3. 配置 PM2

创建 pm2.json 文件：

{
  "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/"
  }
}

环境变量说明：

4. 启动服务

pm2 start pm2.json
pm2 startup
pm2 save

5. 常用命令

pm2 list              # 查看进程
pm2 logs toonflow-app # 查看日志
pm2 restart all       # 重启服务
pm2 monit             # 监控面板

⚠️ 首次登录
账号：admin
密码：admin123

6. 部署前端网站

如需单独部署或定制前端界面，请参考前端仓库：

• GitHub：Toonflow-web
• Gitee：Toonflow-web

💡 说明：本仓库已内置编译好的前端资源，普通用户无需单独部署前端。前端仓库仅供需要二次开发的开发者使用。

云平台部署 Copy Section

🎉 官方认证算力合作平台 —— 智星云

智星云 是 Toonflow 官方授权的商用镜像服务商，已合法搭载、分发并支持商用全套 Toonflow AI 短剧制作镜像，开箱即用，无需手动部署。

• 🌐 官网：https://www.ai-galaxy.com
• 📖 镜像部署图文教程：点击查看教程

📄 点击展开文字版教程

一、租用 GPU 阶段教程

1. 智星云 - 算力市场 - 4090 / 4090 Plus，点击「立即租用」进入租用详情页。

   💡 建议开启「按小时自动续租」模式，防止正在跑视频时实例到期停工。

2. 镜像选择：windows10LTSCwin10_Toonflow - 创建实例。
3. 等待实例启动 30s ~ 60s，查看链接方式 - RDP 登录文件下载 - 点击复制密码 - 双击已下载好的云端连接文件。
4. 将复制好的密码粘贴并登录，连接进入云端桌面。

   💡 鼠标移到云端桌面顶端稍作停留，会显示切换桌面操作栏，可点击“——”切换回自己的电脑桌面，或点击“□”缩小布置到自己的电脑桌面作为操作窗口。

二、配置 Toonflow、启动 ComfyUI 阶段教程

1. 先配置调用 Agent 的模型：打开桌面上的 Toonflow - 模型服务 - OpenAI 标准接口 - 填入 API 密钥以及请求地址。
   默认账号：admin　密码：admin123（建议登录后修改密码）

   💡 这里直接使用智星云的 AI 大模型 Token 服务，官方接口，稳定安全，低至 6 折（小说转剧本调用一次，约花费 6.4 毛钱）。

   • 智星云调用模型 Token 请求地址：https://token.ai-galaxy.com/v1
   • 智星云 Token 充值步骤：Token 市场 - 账户概览 - 充值 - 将智星云账户余额或算力券充值到 Token 账户中。
   • 充值完成后进入「Key 管理」- 新建 API 管理，名称填 Toonflow 或其他均可，点击确定并复制 API 密钥。
2. 回到步骤 1，将生成的 API 密钥和请求地址粘贴到 Toonflow 模型服务中，填好后点击空白处，系统会提示「供应商配置已更新」。
   点击「手动添加」，回到智星云 - Token 市场页面，复制完整的模型名称。

   💡 一个 Key 可以调用智星云上的所有模型，选择你想用的即可，推荐 deepseek-v4-pro。
   将模型名称完整复制粘贴到 Toonflow 中并确认，完成模型配置。

3. 配置完成后检查两处：
   • 模型服务中的三个模型调用开关是否已开启
   • Agent 配置中调用的模型是否与你配置的一致（不一致时点击选择改正即可）
4. 启动 ComfyUI：云端桌面 - 绘世启动器 - 一键启动。
5. 启动大约需要 1~2 分钟，启动完成后保持页面开启状态即可。

🔧 开发流程指南

[!CAUTION]
🚧 PR 提交规范 🚧

⛔ master 分支不接受任何 PR ｜ ✅ 请将 PR 提交到 develop 分支

欢迎开发者们共同参与 Toonflow 的共创。如有兴趣加入，请在交流群内联系主理人 ACT

🛠️ 技术栈 Copy Chapter

开发环境准备 Copy Chapter

• Node.js：版本要求 23.11.1 及以上
• Yarn：推荐作为项目包管理器

快速启动项目 Copy Chapter

1. 克隆项目

   从 GitHub 克隆：

   bash Copy

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

   从 Gitee 克隆（国内推荐）：

   bash Copy

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

2. 安装依赖

   请先在项目根目录下执行以下命令以安装依赖项：

   bash Copy

   yarn install

3. 启动开发环境

   本项目包含 后端 API 服务 和 前端页面 两部分，请根据需要选择启动方式：

   • 方式一：仅启动后端服务

     bash Copy

     yarn dev

     ⚠️ 此命令仅启动后端 API 服务（端口 10588），不包含前端页面。直接访问 http://localhost:10588 只能调用 API 接口，无法看到完整的网页界面。如需同时使用前端页面，请配合前端项目单独启动，或使用下方的 GUI 模式。

   • 方式二：启动 Electron 桌面客户端

     bash Copy

     yarn dev:gui

     此命令会同时启动后端服务和 Electron 桌面窗口，自带内置前端页面，开箱即用，无需额外配置。适合想要完整体验所有功能的开发者。

   • 方式三：生产模式启动

     bash Copy

     yarn start

     以生产模式直接运行编译后的服务（需先执行 yarn build）。

4. 项目打包

   • 编译并生成 TypeScript 文件：

     bash Copy

     yarn build

   • 打包为 Windows 平台可执行程序：

     bash Copy

     yarn dist:win

   • 打包为 Mac 平台可执行程序：

     bash Copy

     yarn dist:mac

   • 打包为 Linux 平台可执行程序：

     bash Copy

     yarn dist:linux

5. 代码质量检查

   • 进行全局语法和规范检查：

     bash Copy

     yarn lint

6. AI 调试面板（可选）

   启动 AI SDK 的可视化调试工具，方便调试 AI 调用：

   bash Copy

   yarn debug:ai

前端开发 Copy Chapter

如需修改前端界面，请前往前端仓库进行开发：

• GitHub：Toonflow-web
• Gitee：Toonflow-web

前端构建后，将 dist 目录内容复制到本项目的 data/web 目录即可集成。

项目结构 Copy Chapter

/* Detailed source-code truncated for AI context efficiency. */

🔗 相关仓库

💡 提示：如果您只是想使用 Toonflow，直接下载本仓库的客户端即可。前端仓库仅供需要二次开发或定制前端界面的开发者使用。

👨‍👩‍👧‍👦 微信交流群

拉群小助手:

也可以点击图标加入 Discord：

或点击邀请连接： https://discord.gg/HEjKmpNpAZ

💌 联系我们

📧 邮箱：[email protected]

📜 许可证

Toonflow 基于 Apache-2.0 协议开源发布，并附有补充商业协议。

许可证详情：https://www.apache.org/licenses/LICENSE-2.0

补充协议 Copy Chapter

• 若将本软件以产品形式分发给 2 个及以上独立第三方使用，须取得 HBAI-Ltd 书面商业授权。
• ≤ 5 个法人联合运营内部使用，不对外提供服务的，视为内部使用，无需授权。
• 不得删除或修改 Toonflow 中的标识或版权信息。

永久免费场景 Copy Chapter

• ✅ 用 Toonflow 制作内容并获得平台分账
• ✅ 二次开发供自己团队内部使用
• ✅ ≤ 5 个法人联合运营内部使用
• ✅ 个人学习、研究、非商业用途

商业授权定价 Copy Chapter

不追溯条款：v1.0.8 发布前基于 AGPL-3.0 使用的用户，继续按 AGPL-3.0 执行，不受本协议变更约束。

完整协议详见 LICENSE 文件。

⭐️ 星标历史

🙏 致谢

感谢以下开源项目为 Toonflow 提供强大支持：

• Express - 快速、开放、极简的 Node.js Web 框架
• AI SDK - 面向 TypeScript 的 AI 工具包
• Better-SQLite3 - 高性能 SQLite3 绑定库
• Sharp - 高性能 Node.js 图像处理库
• Axios - 基于 Promise 的 HTTP 客户端
• Zod - TypeScript 优先的模式验证库
• Socket.IO - 实时双向事件通信引擎
• Electron - 跨平台桌面应用开发框架
• Hugging Face Transformers - 本地 ML 推理库

感谢以下组织/单位/个人为 Toonflow 提供支持：

完整的第三方依赖清单请查阅 NOTICES.txt

copyright © 北京爱阿科技有限公司

File: docs/README.en.md Copy Chapter

🌐 Multi-language Support

Toonflow supports the following interface languages:

💡 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 Copy Chapter

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

📺 Video Tutorial Copy Chapter

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 Copy Chapter

Demo Info Copy Chapter

Cost Breakdown Copy Chapter

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 Copy Chapter

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 Copy Chapter

1. Download & Install Copy Section

[!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 Copy Section

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

⚠️ First Login
Username: admin
Password: admin123

Docker Deployment Copy Chapter

Prerequisites Copy Section

• Docker installed (version 20.10+)

Method 1: Online Deployment Copy Section

To be completed; use local build for now.

Method 2: Local Build Copy Section

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 /index.html
# Example: http://localhost:10588/index.html

Service Port Description Copy Section

Environment Variables:

Cloud Deployment Copy Chapter

Cloud Server Deployment Copy Section

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 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:

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.

Cloud Platform Deployment Copy Section

🎉 Newly Certified Official Compute Partner Platform — AI Galaxy

AI Galaxy is a Toonflow officially authorized commercial image provider, offering a fully compliant, pre-built Toonflow AI short-drama production image for commercial use — ready to use out of the box, no manual deployment required.

• 🌐 Website: https://www.ai-galaxy.com
• 📖 Official image deployment tutorial: Click to view

📄 Click to expand the text tutorial

I. GPU Rental Stage

1. On AI Galaxy - Compute Marketplace - RTX 4090 / 4090 Plus, click "Rent Now" to open the rental details page.

   💡 It's recommended to enable "hourly auto-renewal" to prevent the instance from expiring while a video render is still in progress.

2. Select the image: windows10LTSCwin10_Toonflow - Create Instance.
3. Wait 30–60 seconds for the instance to start, then check the connection method — download the RDP login file, copy the password, and double-click the downloaded remote desktop file.
4. Paste the copied password and log in to enter the cloud desktop.

   💡 Move the mouse to the top of the cloud desktop and pause briefly to reveal the desktop-switching toolbar. Click "──" to switch back to your local desktop, or "□" to shrink it into a window on your local desktop.

II. Configure Toonflow & Start ComfyUI Stage

1. First configure the model used by the Agent: open Toonflow on the desktop - Model Services - OpenAI-compatible interface - enter the API key and request URL.
   Default account: admin Password: admin123 (recommended to change the password after logging in)

   💡 This uses AI Galaxy's AI model Token service directly — an official interface that's stable, secure, and up to 40% off (converting a novel into a script cost about ¥0.64).

   • AI Galaxy model Token request URL: https://token.ai-galaxy.com/v1
   • AI Galaxy Token top-up steps: Token Marketplace - Account Overview - Top Up - transfer your AI Galaxy balance or compute vouchers into your Token account.
   • After topping up, go to "Key Management" - New API, name it Toonflow or anything you like, confirm, and copy the API key.
2. Back in step 1, paste the generated API key and request URL into Toonflow's Model Services, then click elsewhere; the system will show "Provider configuration updated".
   Click "Add Manually", go back to the AI Galaxy Token Marketplace page, and copy the full model name.

   💡 One key can call every model on AI Galaxy — just pick the one you want to use; deepseek-v4-pro is recommended.
   Paste the full model name into Toonflow and confirm to complete the model configuration.

3. After configuration, check two things:
   • Whether all three model toggles in Model Services are enabled
   • Whether the model configured in the Agent settings matches your configuration (click to correct it if not)
4. Start ComfyUI: Cloud Desktop - ComfyUI Launcher - One-Click Start.
5. Startup takes about 1–2 minutes; keep the page open once it's running.

🔧 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 Copy Chapter

Development Environment Setup Copy Chapter

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

Quick Start Project Copy Chapter

1. Clone the Project

   Clone from GitHub:

   bash Copy

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

   Clone from Gitee (recommended for China):

   bash Copy

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

2. Install Dependencies

   Run the following command in the project root to install dependencies:

   bash Copy

   yarn install

3. Start Development Environment

   This project includes both the backend API service and frontend pages. Choose the appropriate startup method:

   • Method 1: Start backend only

     bash Copy

     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

     bash Copy

     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

     bash Copy

     yarn start

     Runs the compiled service in production mode (requires yarn build first).

4. Package the Project

   • Compile and generate TypeScript files:

     bash Copy

     yarn build

   • Package as Windows executable:

     bash Copy

     yarn dist:win

   • Package as macOS executable:

     bash Copy

     yarn dist:mac

   • Package as Linux executable:

     bash Copy

     yarn dist:linux

5. Code Quality Check

   • Run global syntax and lint checks:

     bash Copy

     yarn lint

6. AI Debug Panel (Optional)

   Launch a visual debugging tool for the AI SDK to facilitate debugging AI calls:

   bash Copy

   yarn debug:ai

Frontend Development Copy Chapter

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 Copy Chapter

/* Detailed source-code truncated for AI context efficiency. */

🔗 Related Repositories

💡 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: [[email protected]](mailto:[email protected]?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 Copy Chapter

• 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 Copy Chapter

• ✅ 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 Copy Chapter

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:

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

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