Anil-matcha/Open-AI-Micro-Drama-Generator

AI short drama & micro-drama video generator — turns any idea into a complete short-form drama using multi-agent AI pipeline (screenwriter → storyboard → frames → video). Seedance 2 VIP, Kling 3.0 Pro, Veo 3.1, Sora 2.

What it solves

MicroDrama AI addresses the fragmented nature of AI video production. Traditionally, creating a short film requires jumping between separate tools for scriptwriting, image generation, and video creation, often resulting in a lack of narrative structure and inconsistent character appearances across different shots.

How it works

The project uses an agentic pipeline powered by MuAPI to automate the entire production process. It operates in two modes: "Idea to Video" (full pipeline) and "Script to Video" (skips the writing phase).

  1. Narrative Planning: A Screenwriter agent develops the story and writes scene scripts, while a Character Extractor agent defines visual features for characters.
  2. Visual Design: A Storyboard Artist agent designs shot-by-shot descriptions. The system then generates reference portraits for characters to ensure visual consistency.
  3. Production: The pipeline generates the first frame for each shot using image-to-image (I2I) techniques and then converts those frames into 5-second video clips using image-to-video (I2V) models.
  4. Assembly: All generated clips are concatenated into a final .mp4 file using moviepy.

Who it’s for

It is designed for content creators and filmmakers who want to rapidly prototype cinematic micro-dramas or create short-form video content without manually managing multiple AI tools.

Highlights

  • End-to-End Automation: Handles everything from a raw idea to a final rendered video.
  • Character Consistency: Uses reference portraits and specific extraction agents to keep characters looking the same across scenes.
  • Agentic Workflow: Orchestrates specialized agents (Screenwriter, Storyboard Artist, Character Extractor) to handle different creative roles.
  • Real-time Monitoring: Features a Next.js frontend with SSE streaming to show the live progress of the 7-stage pipeline.

Related

  • Project
    xhongc/ai_story

    AI Story is a Docker‑based web app that automates the whole pipeline from a story prompt to a finished short video, using multiple AI models for script writing, storyboard creation, image generation, camera‑move planning, and video rendering.

  • Project
    pexoai/pexo-skills

    A set of open-source agent skills that automate the full video production pipeline, transforming text, images, or URLs into finished multi-shot videos with music and subtitles.

  • Project
    xuanyustudio/LocalMiniDrama

    An open-source, local-first AI short drama creator that automates the entire production pipeline from script generation to final video synthesis using various AI APIs.

  • Project
    chatfire-AI/huobao-drama

    An AI-powered automated production platform that streamlines the creation of short dramas, from script generation and character design to final video synthesis.

  • Project
    myccarl/ai-shortVideo-pipeline

    myAiVideos is an open‑source, Docker‑compose‑based system that automates the whole short‑video creation workflow (topic → script → visuals → audio → post‑production → distribution) for Chinese content. It uses a FastAPI orchestrator plus a Java Spring‑Boot gateway for auth, routing, circuit‑breaking and metering, and integrates multiple LLM and multimodal models (DeepSeek, GLM, Kling, TTS services). The pipeline is layered, fail‑over capable, and fully observable via Langfuse and Prometheus.