ItusiAI/Open-Magiviz

Magiviz：开源的 AI 视频创作引擎，把一整个剧组交给每一个开发者与创作者

What it solves

Magiviz simplifies the process of professional video production for non-experts. It removes the need for technical experience by automating the entire pipeline from an initial creative idea to a final rendered video, covering genres like anime, Hollywood-style films, advertisements, and educational content.

How it works

The platform uses a five-step serial workflow that can be paused and resumed:

  1. AI Script Generation: Converts a story outline into structured JSON containing scene breakdowns, character settings, and dialogue.
  2. Character Design: Generates visually consistent characters based on text or uploaded reference images.
  3. Storyboard Generation: Creates high-fidelity images for each scene, supporting a "first-last-frame" mode for better control over scene transitions.
  4. Video Rendering: Transforms storyboards into video clips using various AI models (e.g., Veo, Kling, Seedance, Wan).
  5. Final Composition: Stitches individual scene videos into a complete final product with synchronized audio and video tracks.

Who it’s for

It is designed for content creators, marketers, and anyone wanting to produce high-quality video content without needing professional filmmaking skills or expensive GPU hardware.

Highlights

  • Multi-Model Integration: Supports a wide array of video generation models including Veo, Kling, Seedance, Wan, and MiniMax H3.
  • Version Control: Implements a double-layer versioning system (versionGroupId and version) to track changes and allow users to roll back or edit previous iterations.
  • Granular Regeneration: Users can regenerate specific elements (e.g., a single character or one storyboard frame) without restarting the entire project.
  • Comprehensive Project Management: Includes a dedicated library for asset management, progress tracking, and one-click exports for scripts (JSON) and media (MP4/PNG).

Related

  • Project
    LingGuoAI/LingGuo-Drama

    An open-source workbench for AI short drama and video production that manages the pipeline from scriptwriting and asset generation to final video synthesis.

  • Project
    MemeCalculate/moyin-creator

    A production-grade AI filmmaking tool that automates the entire pipeline from script parsing and character consistency to batch video generation.

  • Project
    dramaclaw/dramaclaw

    DramaClaw is a self‑hosted, source‑available AI‑driven production platform that turns scripts into short films. It offers a node‑based “infinite canvas” (XiaHua) for free‑form generation of images, video, audio and 3‑D sets, plus a structured “Series” pipeline (XiaJi) that ingests a manuscript, plans episodes, writes scripts, creates story‑boards, synthesises voice‑overs, composes video and exports the final cut. An integrated AI assistant (Xia Director) can drive both tracks. The system runs via Docker, routes all heavy model inference through an OpenAI‑compatible gateway (official or custom), and is licensed under Elastic 2.0, allowing commercial use with a required credit badge.

  • Project
    xhongc/ai_story

    AI Story is a Docker‑based web platform that turns a short text prompt into a complete short video. It automatically rewrites the prompt into a script, creates a storyboard, generates images via multiple AI image services, plans camera motions, and renders the final video, all orchestrated with Django, Celery, Redis and a Vue front‑end.

  • Project
    HITsz-TMG/VideoClaw

    An AI director system that automates the entire creative video production pipeline from scriptwriting and character design to storyboarding and final editing.