Set up a private AI image and video generation workspace for your team.
Manage generated media, uploads, and external references in a central media library.
Use the bundled web video editor to add subtitles and export video clips.
Extend the platform with custom AI model providers for your own workflows.
| zeeklog/megick-studio | abhi-arya1/riff | andersondanieln/hexllama | |
|---|---|---|---|
| Stars | 13 | 13 | 13 |
| Language | TypeScript | TypeScript | TypeScript |
| Setup difficulty | hard | hard | easy |
| Complexity | 4/5 | 4/5 | 2/5 |
| Audience | developer | developer | vibe coder |
Figures from each repo's GitHub metadata at analysis time.
Requires Node 20+, pnpm, MySQL 8, Redis, and an Aliyun OSS bucket (or Cloudflare R2) with environment variables configured.
``json { "i": 0, "repo": "zeeklog/Megick-Studio", "stars": 13, "lang": "TypeScript", "ok": true, "char_count": 1853, "text": "Megick Studio is a self-hosted AI image and video creation platform. It bundles together image generation, video generation, media asset management, template management, and an admin console into one application. Teams can use it as a private creative workspace or as a starting point for their own custom development.\n\nThe image studio supports text-to-image generation, reference-image generation, and image editing. The video studio handles text-to-video and image-to-video workflows. A built-in browser-based video editor called MegickCut provides a timeline, subtitle support, and export options. The template center handles public templates, category management, review, and publishing. The media center manages generated outputs, user uploads, and external media references. An admin console covers users, roles, models, providers, templates, storage, queues, audit logs, and site settings. A credits system lets administrators adjust user credits manually, though there is no built-in online purchase flow.\n\nThe project is built with TypeScript across three main pieces. The web frontend uses React 19 and Tailwind CSS. The API runs on NestJS with a MySQL database and Redis for job queues. A desktop version wraps the web app using Electron. File storage defaults to Aliyun OSS, with optional Cloudflare R2 support. The repository is organized into separate folders for the API, the web app, and the desktop shell, along with shared type definitions and documentation.\n\nTo run it locally, you need Node.js 20 or later, pnpm, MySQL 8, Redis, and an Aliyun OSS bucket. After installing dependencies, you copy example environment files and fill in database, Redis, OSS, and encryption settings. The project includes commands to initialize the database with sample data and a default administrator account. You then start the API and web servers separately. A Swagger API documentation page is available during development.\n\nThe README notes that adding new model providers requires explicit handling of reference images, async polling, output parsing, and storage. The project currently supports two provider protocol styles: OpenAI and Aliyun. Production deployment uses a build step, database migrations, and PM2 for process management. Contributions are welcome through GitHub issues and pull requests.", "error": null } ``
A self-hosted platform for teams to generate and manage AI images and videos. It bundles creation tools, media management, templates, and an admin console into one private workspace.
Mainly TypeScript. The stack also includes TypeScript, React 19, Tailwind CSS.
No license information is provided, so copyright defaults apply and reuse rights are unclear.
Setup difficulty is rated hard, with roughly 1h+ to a first successful run.
Mainly developer.
This repo across BitVibe Labs
Don't trust strangers blindly. Verify against the repo.