{
  "slug": "generate-images",
  "label": "generate images",
  "blurb": "Create and edit images from text prompts through an API or MCP server.",
  "keywords": [
    "image generation",
    "text-to-image",
    "generate images",
    "image editing"
  ],
  "categories": [
    "content-media"
  ],
  "access": [
    "api",
    "mcp"
  ],
  "count": 10,
  "official": 7,
  "url": "https://agentswitchboard.dev/tasks/generate-images",
  "browseUrl": "https://agentswitchboard.dev/browse?task=generate-images",
  "agentsUrl": "https://agentswitchboard.dev/api/agents?task=generate-images",
  "agents": [
    {
      "name": "Picsart Creative APIs MCP",
      "slug": "picsart-mcp",
      "url": "https://agentswitchboard.dev/agents/picsart-mcp",
      "iconUrl": "https://agentswitchboard.dev/icons/picsart-mcp.png?v=14816d9e",
      "description": "Lets coding agents call Picsart Creative APIs over MCP to remove backgrounds, upscale, enhance, and generate images, and to write integration code from the API docs.",
      "provider": "Picsart",
      "categories": [
        "content-media"
      ],
      "accessMethods": [
        "mcp"
      ],
      "verified": true,
      "official": true,
      "featured": false,
      "authType": "apiKey",
      "why": "Image Editing: Removes or changes backgrounds, upscales, enhances faces, and applies effects to images, one tool per API action."
    },
    {
      "name": "Vellm MCP",
      "slug": "vellm-mcp",
      "url": "https://agentswitchboard.dev/agents/vellm-mcp",
      "iconUrl": "https://agentswitchboard.dev/icons/vellm-mcp.png?v=e32dea22",
      "description": "Generates short videos from user photos via a remote OAuth MCP server: named TikTok/Reels template routines, image-to-video, text-to-video, and image generation. Runs on Seedance 2.5; paid credits.",
      "provider": "Vellm",
      "categories": [
        "content-media"
      ],
      "accessMethods": [
        "mcp"
      ],
      "verified": true,
      "official": false,
      "featured": false,
      "authType": "oauth2",
      "why": null
    },
    {
      "name": "Luma AI API",
      "slug": "luma-ai-api",
      "url": "https://agentswitchboard.dev/agents/luma-ai-api",
      "iconUrl": "https://agentswitchboard.dev/icons/luma-ai-api.png?v=808580bb",
      "description": "Generates video with Luma's Ray 2 models and images with Photon through the Dream Machine API, with keyframes, extend, reframe, and modify, for apps using REST, Python, or JS SDKs.",
      "provider": "Luma AI",
      "categories": [
        "content-media"
      ],
      "accessMethods": [
        "api"
      ],
      "verified": true,
      "official": true,
      "featured": false,
      "authType": "apiKey",
      "why": "Photon Image Generation: Generates images with Photon or Photon Flash, guided by image, style, or character references."
    },
    {
      "name": "Polyphemus (Eye.Art)",
      "slug": "polyphemus",
      "url": "https://agentswitchboard.dev/agents/polyphemus",
      "iconUrl": "https://agentswitchboard.dev/icons/polyphemus.png?v=134166c7",
      "description": "Generates and edits images, icons, and editable SVG from natural language or page code (HTML/CSS/JSX/TSX) via a no-key MCP server and REST API; async raster jobs return a pollable job id.",
      "provider": "Shelled AI",
      "categories": [
        "content-media",
        "code-devtools"
      ],
      "accessMethods": [
        "mcp",
        "api"
      ],
      "verified": true,
      "official": false,
      "featured": false,
      "authType": "none",
      "why": "Generate Images: Creates raster images from a natural-language prompt; long jobs return a job id to poll (eye_art_make_image)."
    },
    {
      "name": "ImagineVid AI Generation",
      "slug": "imaginevid-ai-generation",
      "url": "https://agentswitchboard.dev/agents/imaginevid-ai-generation",
      "iconUrl": "https://agentswitchboard.dev/icons/imaginevid-ai-generation.png?v=e8f95113",
      "description": "Generate images, videos, and music through an OAuth-protected MCP and CLI gateway with live quotes and explicit credit approval.",
      "provider": "ImagineVid",
      "categories": [
        "content-media"
      ],
      "accessMethods": [
        "mcp",
        "cli"
      ],
      "verified": true,
      "official": false,
      "featured": false,
      "authType": "oauth2",
      "why": null
    },
    {
      "name": "MiniMax MCP",
      "slug": "minimax-mcp",
      "url": "https://agentswitchboard.dev/agents/minimax-mcp",
      "iconUrl": "https://agentswitchboard.dev/icons/minimax-mcp.png?v=138accd8",
      "description": "Official MiniMax AI MCP server — generate speech from text, clone voices, create images and videos, and compose music via a single interface.",
      "provider": "MiniMax AI",
      "categories": [
        "content-media"
      ],
      "accessMethods": [
        "mcp",
        "cli"
      ],
      "verified": true,
      "official": true,
      "featured": false,
      "authType": "apiKey",
      "why": null
    },
    {
      "name": "Gemini API",
      "slug": "gemini-api",
      "url": "https://agentswitchboard.dev/agents/gemini-api",
      "iconUrl": "https://agentswitchboard.dev/icons/gemini-api.png?v=ebf423a0",
      "description": "Serves Google's Gemini models through the Gemini Developer API and Gen AI SDKs, with function calling, structured output, Live API voice, and image generation, for developers.",
      "provider": "Google",
      "categories": [
        "language",
        "infrastructure"
      ],
      "accessMethods": [
        "api"
      ],
      "verified": true,
      "official": true,
      "featured": false,
      "authType": "apiKey",
      "why": "Image Generation: Generates and edits images with Gemini image models from text and image prompts."
    },
    {
      "name": "Replicate",
      "slug": "replicate",
      "url": "https://agentswitchboard.dev/agents/replicate",
      "iconUrl": "https://agentswitchboard.dev/icons/replicate.png?v=a059c34b",
      "description": "Run open-source AI models in the cloud — image generation, language models, video, audio via simple API calls.",
      "provider": "Replicate",
      "categories": [
        "content-media",
        "infrastructure"
      ],
      "accessMethods": [
        "api",
        "cli"
      ],
      "verified": true,
      "official": true,
      "featured": false,
      "authType": "apiKey",
      "why": null
    },
    {
      "name": "Runway ML",
      "slug": "runway-ml",
      "url": "https://agentswitchboard.dev/agents/runway-ml",
      "iconUrl": "https://agentswitchboard.dev/icons/runway-ml.png?v=f29a8592",
      "description": "AI-powered creative tools for video generation, image editing, and motion design — includes Gen-3 Alpha for text-to-video.",
      "provider": "Runway",
      "categories": [
        "content-media"
      ],
      "accessMethods": [
        "api"
      ],
      "verified": true,
      "official": true,
      "featured": false,
      "authType": "apiKey",
      "why": null
    },
    {
      "name": "fal",
      "slug": "fal-ai",
      "url": "https://agentswitchboard.dev/agents/fal-ai",
      "iconUrl": "https://agentswitchboard.dev/icons/fal-ai.png?v=5e8f3a5e",
      "description": "Runs generative image, video, and audio models through a queue-based inference API, Python and JS clients, a CLI, and a hosted MCP server, with webhooks and streaming output.",
      "provider": "fal",
      "categories": [
        "content-media"
      ],
      "accessMethods": [
        "api",
        "cli",
        "mcp"
      ],
      "verified": true,
      "official": true,
      "featured": false,
      "authType": "apiKey",
      "why": null
    }
  ],
  "relatedTasks": [
    "make-videos",
    "turn-designs-into-code",
    "read-pdfs-and-documents",
    "manage-social-media"
  ],
  "stacks": []
}