A terminal-based interface to MuAPI's collection of 100+ generative AI models for creating images, videos, and audio. You get five bash scripts that handle text-to-image (flux-dev), text-to-video (minimax-pro), image-to-video animation (kling-pro), and music generation (Suno V5), plus a CDN upload utility for chaining outputs. The schema-driven approach means model selection happens dynamically, which is clean but also means you're trusting the schema to pick the right endpoint. Good for prototyping media-heavy features or building quick demos without dealing with individual API integrations. At 3.4K stars and 594 installs, it's seeing real use despite the somewhat sparse documentation.

skills.sh installs
1.1K
GitHub stars
4K
last updated
Aug 21, 2026

Install

$ npx -y skills add samuraigpt/generative-media-skills --skill muapi-media-generation --agent claude-code

Installs into .claude/skills of the current project.

Files

🎨 MuAPI Media Generation

Schema-driven generation primitives for images, videos, and audio.

Generate professional-grade media directly from the terminal using 100+ state-of-the-art AI models. All scripts are powered by schema_data.json for dynamic model and endpoint resolution.

Available Scripts

ScriptDescriptionDefault Model
generate-image.shText-to-image generationflux-dev
generate-video.shText-to-video generationminimax-pro
image-to-video.shAnimate a static image into videokling-pro
create-music.shMusic creation, remix, extend, text/video-to-audioSuno V5
upload.shUpload local files to CDN for use with other skills—

Quick Start

# Generate an image
bash generate-image.sh --prompt "a sunset over mountains" --model flux-dev --view

# Generate a video
bash generate-video.sh --prompt "ocean waves at golden hour" --model minimax-pro --view

# Animate an image
bash image-to-video.sh --image-url "https://..." --prompt "camera slowly pans right" --model kling-pro

# Create music
bash create-music.sh --style "lo-fi hip hop" --prompt "chill beats for studying"

Sponsors

Details

Repository
github.com/samuraigpt/generative-media-skills
Categories
CLI & Terminal, Generative Media
First seen
Jun 3, 2026

More from samuraigpt/generative-media-skills

All 18
1inference-sh avatarllm-modelsinference-sh/skillsAccess Claude, Gemini, Kimi, GLM and 100+ LLMs via inference.sh CLI using OpenRouter. Models: Claude Opus 4.5, Claude Sonnet 4.5, Claude Haiku 4.5, Gemini 3 Pro1.1Kskills.sh installs
2mvanhorn avatarpp-hackernewsmvanhorn/printing-press-libraryHacker News from your terminal — with a local SQLite store, snapshot history, and agent-native output no other HN tool has. Trigger phrases: `check hacker news`1Kskills.sh installs
3subsy avatarralph-tui-create-beads-rustsubsy/ralph-tuiConvert PRDs to beads for ralph-tui execution using beads-rust (br CLI). Creates an epic with child beads for each user story. Use when you have a PRD and want 1Kskills.sh installs
4yeachan-heo avatarproject-session-manageryeachan-heo/oh-my-claudecodeWorktree-first dev environment manager for issues, PRs, and features with optional tmux sessions916skills.sh installs
5daymade avatarproduct-analysisdaymade/claude-code-skillsMulti-path parallel product analysis with cross-model test-time compute scaling. Spawns parallel agents (Claude Code agent teams + Codex CLI) to explore product909skills.sh installs
6youmind-openlab avataryoumindyoumind-openlab/skillsUse this skill when the task is clearly connected to the user's YouMind workspace, YouMind APIs, or the youmind CLI. It helps agents search, inspect, and call Y896skills.sh installs