GitHub - awesome-genmedia/skills: Awesome skills for AI image generation, video generation, song generation and more!

562 generative media skills for AI agents, powered by each::labs.

Generate images, videos, audio, 3D models, and more using 431 AI models through a single API. Install as a Claude Code plugin and get instant access to every skill.

Install

# Claude Code plugin
/plugin install awesome-genmedia

# Or add individual skills
npx skills add awesome-genmedia/skills@image-generation
npx skills add awesome-genmedia/skills@flux-2-max
npx skills add awesome-genmedia/skills@logo-design

Setup

1. Sign up at eachlabs.ai
2. Get your API key from Settings
3. Set environment variable:

   export EACHLABS_API_KEY="your-api-key"

Quick Example

curl -X POST https://eachsense-agent.core.eachlabs.run/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "messages": [{"role": "user", "content": "Generate a professional headshot, studio lighting, neutral background"}],
    "stream": false
  }'

Default Skills (14)

Core generative media capabilities at the root level:

Categories (117 skills)

Use-case specific skills organized by domain:

Models (431)

Every AI model available on each::labs has its own skill under models/:

Image Generation

flux-2-max · flux-2-pro · flux-2 · flux-kontext-pro · flux-kontext-max · nano-banana-pro · nano-banana-2-text-to-image · gemini-3-pro-image-preview · imagen-4-fast · imagen4-preview · bytedance-seedream-v4-5-text-to-image · bytedance-seedream-v5-lite-text-to-image · kling-v3-text-to-image · gpt-image-v1-5-text-to-image · xai-grok-imagine-text-to-image · reve-text-to-image · ideogram-v3-turbo · stable-diffusion-3-5-large · and more...

Video Generation

veo-3 · veo3-1-text-to-video · veo3-1-text-to-video-fast · kling-o3-pro-text-to-video · kling-v3-pro-text-to-video · sora-2-text-to-video-pro · pixverse-v5-6-text-to-video · wan-v2-6-text-to-video · runway-gen4-aleph · pika-v2-2-text-to-video · seedance-v1-5-pro-text-to-video · minimax-hailuo-v2-3-pro-text-to-video · and more...

Image Editing

flux-2-edit · flux-2-max-edit · flux-fill-pro · eachlabs-bg-remover-v1 · topaz-upscale-image · kling-face-swap · nano-banana-pro-edit · qwen-ai-image-edit · firered-image-edit-v1-1 · and more...

Audio & Music

elevenlabs-text-to-speech · mureka-generate-song · mureka-generate-instrumental · mureka-generate-lyrics · stable-audio-2-5-text-to-audio · xai-grok-tts-text-to-speech · google-text-to-speech · deepgram-nova-3-speech-to-text · whisper · and more...

Video Editing & Effects

topaz-upscale-video · auto-subtitle · heygen-video-translate · pixverse-lip-sync · merge-videos · ffmpeg-api-merge-audio-video · and more...

Talking Head & Avatar

bytedance-omnihuman-v1-5 · bytedance-dreamactor-v2 · kling-avatar-v2-pro · sync-lipsync-v2-pro · infinitalk-image-to-video · and more...

Browse all 431 models →

API

each::sense (for use-case skills)

OpenAI-compatible endpoint that auto-selects the best model:

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_EACHLABS_API_KEY",
    base_url="https://eachsense-agent.core.eachlabs.run/v1"
)

response = client.chat.completions.create(
    model="eachsense/beta",
    messages=[{"role": "user", "content": "Generate a logo for a coffee brand"}]
)

Prediction API (for specific models)

Direct model access:

curl -X POST https://api.eachlabs.ai/v1/prediction \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "model": "flux-2-max",
    "version": "0.0.1",
    "input": {
      "prompt": "A professional headshot, studio lighting",
      "aspect_ratio": "1:1"
    }
  }'

Documentation

• each::sense Overview
• API Reference
• Models Directory
• Workflows

Contributing

See CONTRIBUTING.md for guidelines.

License

MIT