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.

Generate Convert Improve

Install / Use

npx skills add Anil-matcha/Open-AI-Micro-Drama-Generator

Installs into whichever agent you are using.

About this skill

Quality Score

0/100

README

<div align="center"> <h1 align="center">MicroDrama AI</h1> <h3 align="center">Agentic AI Micro-Drama Video Generator</h3> <p align="center"> <img src="https://img.shields.io/badge/🐍Python-3.10+-00d9ff?style=for-the-badge&logo=python&logoColor=white&labelColor=1a1a2e"> <img src="https://img.shields.io/badge/⚡Next.js-14-ff6b6b?style=for-the-badge&logo=next.js&logoColor=white&labelColor=1a1a2e"> <img src="https://img.shields.io/badge/License-MIT-4ecdc4?style=for-the-badge&logo=opensourceinitiative&logoColor=white&labelColor=1a1a2e"> </p> <p align="center"> <img src="https://img.shields.io/badge/MuAPI-Powered-7c3aed?style=for-the-badge&logoColor=white&labelColor=1a1a2e"> <img src="https://img.shields.io/badge/One_Key-Setup-FFC107?style=for-the-badge&logoColor=white&labelColor=1a1a2e"> </p> </div>

🚨 The problem with AI video today:

❌ Manual, fragmented workflow — Separate tools needed for scripting, image gen, and video gen
❌ No narrative structure — Raw T2V models don't understand story arcs or scene continuity
❌ Character inconsistency — Characters look different in every shot
❌ Visual-only — Missing scripts, narrative depth, and cinematic storytelling

💡 MicroDrama AI Solution:

🎬 Screenwriter, Storyboard Artist, Frame Generator, and Video Producer — all in one automated pipeline.

Type an idea. MicroDrama AI autonomously handles everything: story development, character design, shot-by-shot storyboarding, frame generation, and video clip production — then stitches it all into a complete cinematic micro-drama. Powered entirely by a single MuAPI key.

🎨 Explore 50+ more open-source AI apps →

Related Projects

Seedance 2.5 on MuAPI — Model landing page for the cinematic video workflow.
Seedance 2.5 text-to-video playground — Try the model used for short-form scenes.
AI-Youtube-Shorts-Generator — Auto-clip and crop your AI dramas into viral YouTube Shorts
Clip-Anything — Clip any moment from your AI drama with text prompts
AI-Faceless-Video-Generator — Generate faceless AI videos for your drama channel
awesome-ai-video-models — compare AI video models by API, price & speed
ai-creator-academy — free curriculum teaching creators how to monetize AI micro-dramas and video content

🎥 Demo Video

https://github.com/user-attachments/assets/f8b5d09c-8c58-40c1-b171-e3f42b0d71a8

Watch MicroDrama AI transform ideas into fully cinematic micro-drama videos using autonomous AI agents, character-consistent image generation, storyboarding, and MuAPI-powered video creation.

💡 Key Features

🎭 Idea to Video

From Spark to Screen

Transform a raw idea into a complete micro-drama. The AI develops the story, writes scene scripts, designs the storyboard, and generates the full video — zero manual steps.

</td> <td width="25%" align="center" valign="top" style="padding: 20px;">

📝 Script to Video

Bring Your Script to Life

Already have a scene script? Skip the writing phase and let MicroDrama AI handle storyboarding, character portraits, frame generation, and video production.

</td> <td width="25%" align="center" valign="top" style="padding: 20px;">

🎨 Character Consistency

Coherent Visual Identity

Characters are extracted with detailed static and dynamic features. Reference portraits are generated and used to keep characters visually consistent across every shot.

</td> <td width="25%" align="center" valign="top" style="padding: 20px;">

📡 Real-time Progress

Live Pipeline Visibility

Watch every stage of the pipeline in real time via SSE streaming — from story development through to the final concatenated video, with a live animated stage timeline.

</td> </tr> </table>

🏗️ Architecture

                   ┌──────────────────────────────────────────────────────────┐
                   │                MicroDrama AI Server                      │
  Idea / Script ─► │                                                          │
                   │  ┌────────────────────────────────────────────────────┐  │
                   │  │              Screenwriter Agent                     │  │
                   │  │  develop_story()  → write_script_based_on_story()  │  │
                   │  └──────────────────────────┬─────────────────────────┘  │
                   │                             │ story + scene scripts       │
                   │  ┌──────────────────────────▼─────────────────────────┐  │
                   │  │           Character Extractor Agent                 │  │
                   │  │      extract_characters(script) → List[char]       │  │
                   │  └──────────────────────────┬─────────────────────────┘  │
                   │                             │ characters[]               │
                   │  ┌──────────────────────────▼─────────────────────────┐  │
                   │  │           Storyboard Artist Agent                   │  │
                   │  │  design_storyboard() → List[ShotBriefDescription]  │  │
                   │  └──────────────────────────┬─────────────────────────┘  │
                   │                             │ shots[]                    │
                   │  ┌──────────────────────────▼─────────────────────────┐  │
                   │  │                  MuAPI Tools                        │  │
                   │  │  ① Portrait Gen  →  flux-dev-image  (T2I)          │  │
                   │  │  ② Frame Gen     →  flux-kontext-dev-i2i  (I2I)    │  │
                   │  │  ③ Video Gen     →  kling-v2.1-standard-i2v  (I2V) │  │
                   │  └──────────────────────────┬─────────────────────────┘  │
                   │                             │ video clips                │
                   │  ┌──────────────────────────▼─────────────────────────┐  │
                   │  │                moviepy Concat                       │  │
                   │  └──────────────────────────┬─────────────────────────┘  │
                   └────────────────────────────-┼──────────────────────────--┘
                                                 │
                                        final_video.mp4

All LLM calls (story, characters, storyboard) go through MuAPI's /claude-sonnet-4-6 endpoint. Only one API key is required for the entire pipeline.

🔄 Pipeline Stages

Idea to Video — Full Pipeline

| # | Stage | Agent / Tool | Output | |---|-------|-------------|--------| | 1 | Story Development | Screenwriter (MuAPI LLM) | Story outline in prose | | 2 | Character Extraction | CharacterExtractor (MuAPI LLM) | Characters with static + dynamic visual features | | 3 | Scene Scripting | Screenwriter (MuAPI LLM) | 2–4 individual scene scripts | | 4 | Character Portraits | MuAPI flux-dev-image (T2I) | Reference portrait per character — runs in parallel | | 5 | Storyboard Design | StoryboardArtist (MuAPI LLM) | 3–5 shots per scene: visual + motion + audio desc | | 6 | Frame Generation | MuAPI flux-kontext-dev-i2i (I2I) | First frame per shot using character reference images | | 7 | Video Generation | MuAPI kling-v2.1-standard-i2v (I2V) | 5-second video clip per shot — runs in parallel | | 8 | Concatenation | moviepy | All clips joined into final_video.mp4 |

Script to Video — Short Pipeline

Skips stages 1–3. Starts directly from your provided script.

| # | Stage | Agent / Tool | Output | |---|-------|-------------|--------| | 1 | Character Extraction | CharacterExtractor (MuAPI LLM) | Characters with visual descriptions | | 2 | Character Portraits | MuAPI flux-dev-image (T2I) | Reference portrait per character | | 3 | Storyboard Design | StoryboardArtist (MuAPI LLM) | Shots from your script | | 4 | Frame Generation | MuAPI flux-kontext-dev-i2i (I2I) | First frame per shot | | 5 | Video Generation | MuAPI kling-v2.1-standard-i2v (I2V) | 5-second video per shot | | 6 | Concatenation | moviepy | Final scene video |

🚀 Quick Start

Prerequisites

Python 3.10+
Node.js 18+
A MuAPI API key

1. Clone the repo

git clone https://github.com/Anil-matcha/Open-AI-Micro-Drama-Generator.git
cd Open-AI-Micro-Drama-Generator

2. Set up the server

cd server
python -m venv venv
source venv/bin/activate      # Windows: venv\Scripts\activate
pip install -r requirements.txt

cp .env.example .env
# Open .env and set MUAPI_KEY=your_key_here

3. Start the server

uvicorn api:app --reload --port 8000

API available at http://localhost:8000. Health check: GET /api/health.

4. Set up and start th

Related Skills

qqbot-channel

385.5k

QQ channel management skill. Use qqbot_channel_api for explicit QQ channel-management requests; confirm write, delete, and bulk actions before calling authenticated QQ Open Platform endpoints.

docs-writer

106.4k

Always use this skill when the task involves writing, reviewing, or editing files in the `/docs` directory or any `.md` files in the repository.

cpp

40.5k

Guide Cursor to write modern C++ and CMake code with clear structure, RAII, const-correctness, and safe error handling.

gamemaker-gml

40.5k

GameMaker Language (GML) rules for scripts, objects, events, rooms, data structures, and performance-minded game code