muapi-character-story-video

Generates multi-part animated story videos with consistent characters using MuAPI image and video models.

4.2k|481|Updated May 25, 2023
One-click install
npx skills add https://github.com/SamurAIGPT/Generative-Media-Skills --skill muapi-character-story-video
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: muapi-character-story-video
Source: https://github.com/SamurAIGPT/Generative-Media-Skills/tree/main/library/motion/character-story-video
Command: npx skills add https://github.com/SamurAIGPT/Generative-Media-Skills --skill muapi-character-story-video

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Creating a coherent multi-scene animated story requires keeping a character visually consistent across separate image and video generations, which is difficult when prompting models scene by scene.

Core Features & Use Cases

  • Character Establishment: Generates a consistent main character with nano-banana-pro, optionally starting from a user-provided reference image.
  • Sequential Scene Generation: Produces beginning, middle, and end story scenes via image editing models (nano-banana-2-edit, flux-kontext-pro-i2i) anchored to the established character.
  • Scene Animation: Converts each scene into a video clip using image-to-video models such as kling-v3.0-pro or veo3.1, with optional ffmpeg concatenation into one movie.
  • Use Case: Describe a character like "a piglet in an aviator jacket" and a premise like "building a jetpack to fly to space", and receive a three-part animated story sequence.

Quick Start

Ask the agent to create a three-part animated story video about your character and story premise, providing an optional reference image for character consistency.

Frequently Asked Questions about muapi-character-story-video

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I create a multi-part animated story video with AI?

Provide a character description and story premise, and the skill generates a consistent character, creates three sequential story scenes with image editing models, then animates each scene with an image-to-video model like kling-v3.0-pro or veo3.1.

How do I keep a character consistent across AI-generated scenes?

The skill first establishes the character with nano-banana-pro or uses your reference image, then passes that image as the reference for every scene via image editing models such as nano-banana-2-edit or flux-kontext-pro-i2i.

Can I use my own character image for the story video?

Yes, supply the optional reference_image input and the skill skips character creation, using your image as the established character for all subsequent scene generation and animation steps.

What do I need to run the muapi character story video workflow?

You need the muapi CLI installed and a configured MUAPI_API_KEY, set via muapi auth configure. For models without a CLI alias, the skill falls back to direct curl calls to the MuAPI endpoint with polling via muapi predict wait.

Can the generated story clips be merged into one video?

Yes, after the three scene videos are generated, the skill suggests using muapi predict result together with an ffmpeg concat step to merge the parts into a single movie when requested.