image-generate

📁 agntswrm/agent-media 📅 Jan 20, 2026
21
总安装量
15
周安装量
#17446
全站排名
安装命令
npx skills add https://github.com/agntswrm/agent-media --skill image-generate

Agent 安装分布

opencode 11
claude-code 10
codex 10
gemini-cli 8
windsurf 7
cursor 7

Skill 文档

Image Generate

Generates an image from a text prompt using AI image generation models.

Command

agent-media image generate --prompt <text> [options]

Inputs

Option Required Description
--prompt Yes Text description of the image to generate
--width No Width of the generated image in pixels (default: 1280)
--height No Height of the generated image in pixels (default: 720)
--count No Number of images to generate (default: 1)
--out No Output path, filename or directory (default: ./)
--provider No Provider to use (default: auto-detect)

Output

Returns a JSON object with the generated image path:

{
  "ok": true,
  "media_type": "image",
  "action": "generate",
  "provider": "fal",
  "output_path": "generated_123_abc.png",
  "mime": "image/png",
  "bytes": 567890
}

Examples

Generate an image:

agent-media image generate --prompt "a red robot standing in a forest"

Generate with specific dimensions:

agent-media image generate --prompt "sunset over mountains" --width 1024 --height 768

Generate using specific provider:

agent-media image generate --prompt "abstract art" --provider replicate

Providers

This action requires an external provider:

  • fal – Requires FAL_API_KEY
  • replicate – Requires REPLICATE_API_TOKEN
  • runpod – Requires RUNPOD_API_KEY
  • ai-gateway – Requires AI_GATEWAY_API_KEY

The local provider does not support image generation.