FAL Image/Video MCP Server

MIT License

Overview InspectNew Schema Related Servers Reviews Score

stable_diffusion_35

Generate custom images from text prompts using advanced AI models. Choose image size, control steps, and guidance scale for precise results. Supports multiple image outputs.

Instructions

Stable Diffusion 3.5 Large - Improved image quality and performance

Input Schema

Name	Required	Description	Default
`guidance_scale`	No
`image_size`	No		landscape_4_3
`negative_prompt`	No	Negative prompt
`num_images`	No
`num_inference_steps`	No
`prompt`	Yes	Text prompt for image generation

Input Schema (JSON Schema)

{
  "properties": {
    "guidance_scale": {
      "default": 3.5,
      "maximum": 20,
      "minimum": 1,
      "type": "number"
    },
    "image_size": {
      "default": "landscape_4_3",
      "enum": [
        "square_hd",
        "square",
        "portrait_4_3",
        "portrait_16_9",
        "landscape_4_3",
        "landscape_16_9"
      ],
      "type": "string"
    },
    "negative_prompt": {
      "description": "Negative prompt",
      "type": "string"
    },
    "num_images": {
      "default": 1,
      "maximum": 4,
      "minimum": 1,
      "type": "number"
    },
    "num_inference_steps": {
      "default": 25,
      "maximum": 50,
      "minimum": 1,
      "type": "number"
    },
    "prompt": {
      "description": "Text prompt for image generation",
      "type": "string"
    }
  },
  "required": [
    "prompt"
  ],
  "type": "object"
}

Install Server

HTTP connection URL

Related Tools

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/RamboRogers/fal-image-video-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server