image-processing

AI image generation, editing, and background removal

Server path: /image-processing | Type: Embedded | PCID required: No

Tools

Tool	Description
image-processing_ai_background_removal	Remove the background from an image. Can also replace the background with a solid color, blur, or another image. Returns a transparent PNG or processed image.
image-processing_ai_generate	Text-to-image generation only (no image input). Use this for creating new images purely from a text description. Fast. For editing existing images or using reference images, use Nano Banana 2 or Nano Banana Pro instead.
image-processing_nano_banana	Fast image generation and editing with Google Search grounding. Can generate from text, edit existing images, blend up to 14 reference images, and render text. Unique feature: enable google_search or image_search to ground generation in real-time web data (weather, scores, events, logos). Use this when speed matters or when you need search-grounded images. For highest quality output (especially text/logos), use Nano Banana Pro instead.
image-processing_nano_banana_pro	Highest quality image generation and editing. Best for accurate text rendering, faithful logo reproduction, professional compositions, and detailed scenes. Can generate from text, edit existing images, and blend up to 14 reference images. Supports resolutions up to 4K. Slower than Nano Banana 2 but significantly better output quality. Does NOT support Google Search grounding — use Nano Banana 2 if you need search-grounded images.

---

image-processing_ai_background_removal

Remove the background from an image. Can also replace the background with a solid color, blur, or another image. Returns a transparent PNG or processed image.

Parameters:

Parameter	Type	Required	Default	Description
image_url	string	Yes	—	URL of the image to process
background_type	string	No	—	What to replace the background with: “rgba” (transparent), “white”, “green” (green screen), “blur” (blurred original). Default: rgba (transparent)
output_format	string	No	—	Output format. Use png for transparency (default: png)
reverse	boolean	No	—	If true, removes the foreground instead of background (default: false)

Show inputSchema

{
  "type": "object",
  "properties": {
    "image_url": {
      "type": "string",
      "description": "URL of the image to process"
    },
    "background_type": {
      "type": "string",
      "enum": [
        "rgba",
        "white",
        "green",
        "blur"
      ],
      "default": "rgba",
      "description": "What to replace the background with: \"rgba\" (transparent), \"white\", \"green\" (green screen), \"blur\" (blurred original). Default: rgba (transparent)"
    },
    "output_format": {
      "type": "string",
      "enum": [
        "png",
        "jpg"
      ],
      "default": "png",
      "description": "Output format. Use png for transparency (default: png)"
    },
    "reverse": {
      "type": "boolean",
      "default": false,
      "description": "If true, removes the foreground instead of background (default: false)"
    }
  },
  "required": [
    "image_url"
  ]
}

---

image-processing_ai_generate

Text-to-image generation only (no image input). Use this for creating new images purely from a text description. Fast. For editing existing images or using reference images, use Nano Banana 2 or Nano Banana Pro instead.

Parameters:

Parameter	Type	Required	Default	Description
prompt	string	Yes	—	Text description of the image to generate. Be specific and descriptive for best results.
aspect_ratio	string	No	—	Aspect ratio of the generated image (default: 1:1)
output_format	string	No	—	Output image format (default: png)

Show inputSchema

{
  "type": "object",
  "properties": {
    "prompt": {
      "type": "string",
      "description": "Text description of the image to generate. Be specific and descriptive for best results."
    },
    "aspect_ratio": {
      "type": "string",
      "enum": [
        "1:1",
        "3:4",
        "4:3",
        "9:16",
        "16:9"
      ],
      "default": "1:1",
      "description": "Aspect ratio of the generated image (default: 1:1)"
    },
    "output_format": {
      "type": "string",
      "enum": [
        "png",
        "jpg"
      ],
      "default": "png",
      "description": "Output image format (default: png)"
    }
  },
  "required": [
    "prompt"
  ]
}

---

image-processing_nano_banana

Fast image generation and editing with Google Search grounding. Can generate from text, edit existing images, blend up to 14 reference images, and render text. Unique feature: enable google_search or image_search to ground generation in real-time web data (weather, scores, events, logos). Use this when speed matters or when you need search-grounded images. For highest quality output (especially text/logos), use Nano Banana Pro instead.

Parameters:

Parameter	Type	Required	Default	Description
prompt	string	Yes	—	Text description of the image to generate, or instruction describing how to edit the image. Examples: “make the background sunset”, “add sunglasses”, “a product photo of a coffee mug”
image_urls	string[]	No	—	Array of image URLs to use as input/reference for editing (supports up to 14 images)
aspect_ratio	string	No	—	Output aspect ratio (default: match_input_image)
resolution	string	No	—	Resolution of the generated image. Higher resolutions take longer. (default: 1K)
output_format	string	No	—	Output image format (default: jpg)
google_search	boolean	No	—	Use Google Web Search grounding to generate images based on real-time information (e.g. weather, sports scores, recent events). Default: false
image_search	boolean	No	—	Use Google Image Search grounding to find web images as visual context for generation. When enabled, web search is also used automatically. Default: false

Show inputSchema

{
  "type": "object",
  "properties": {
    "prompt": {
      "type": "string",
      "description": "Text description of the image to generate, or instruction describing how to edit the image. Examples: \"make the background sunset\", \"add sunglasses\", \"a product photo of a coffee mug\""
    },
    "image_urls": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "default": [],
      "description": "Array of image URLs to use as input/reference for editing (supports up to 14 images)"
    },
    "aspect_ratio": {
      "type": "string",
      "enum": [
        "match_input_image",
        "1:1",
        "1:4",
        "1:8",
        "2:3",
        "3:2",
        "3:4",
        "4:1",
        "4:3",
        "4:5",
        "5:4",
        "8:1",
        "9:16",
        "16:9",
        "21:9"
      ],
      "default": "match_input_image",
      "description": "Output aspect ratio (default: match_input_image)"
    },
    "resolution": {
      "type": "string",
      "enum": [
        "1K",
        "2K",
        "4K"
      ],
      "default": "1K",
      "description": "Resolution of the generated image. Higher resolutions take longer. (default: 1K)"
    },
    "output_format": {
      "type": "string",
      "enum": [
        "jpg",
        "png"
      ],
      "default": "jpg",
      "description": "Output image format (default: jpg)"
    },
    "google_search": {
      "type": "boolean",
      "default": false,
      "description": "Use Google Web Search grounding to generate images based on real-time information (e.g. weather, sports scores, recent events). Default: false"
    },
    "image_search": {
      "type": "boolean",
      "default": false,
      "description": "Use Google Image Search grounding to find web images as visual context for generation. When enabled, web search is also used automatically. Default: false"
    }
  },
  "required": [
    "prompt"
  ]
}

---

image-processing_nano_banana_pro

Highest quality image generation and editing. Best for accurate text rendering, faithful logo reproduction, professional compositions, and detailed scenes. Can generate from text, edit existing images, and blend up to 14 reference images. Supports resolutions up to 4K. Slower than Nano Banana 2 but significantly better output quality. Does NOT support Google Search grounding — use Nano Banana 2 if you need search-grounded images.

Parameters:

Parameter	Type	Required	Default	Description
prompt	string	Yes	—	Text description of the image to generate, or instruction describing how to edit the image. Examples: “a retro movie poster for STELLAR DRIFT”, “transform this photo into Van Gogh style”
image_urls	string[]	No	—	Array of image URLs to use as input/reference for editing (supports up to 14 images)
aspect_ratio	string	No	—	Output aspect ratio (default: match_input_image)
resolution	string	No	—	Resolution of the generated image. Higher resolutions take longer. (default: 2K)
output_format	string	No	—	Output image format (default: jpg)

Show inputSchema

{
  "type": "object",
  "properties": {
    "prompt": {
      "type": "string",
      "description": "Text description of the image to generate, or instruction describing how to edit the image. Examples: \"a retro movie poster for STELLAR DRIFT\", \"transform this photo into Van Gogh style\""
    },
    "image_urls": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "default": [],
      "description": "Array of image URLs to use as input/reference for editing (supports up to 14 images)"
    },
    "aspect_ratio": {
      "type": "string",
      "enum": [
        "match_input_image",
        "1:1",
        "2:3",
        "3:2",
        "3:4",
        "4:3",
        "4:5",
        "5:4",
        "9:16",
        "16:9",
        "21:9"
      ],
      "default": "match_input_image",
      "description": "Output aspect ratio (default: match_input_image)"
    },
    "resolution": {
      "type": "string",
      "enum": [
        "1K",
        "2K",
        "4K"
      ],
      "default": "2K",
      "description": "Resolution of the generated image. Higher resolutions take longer. (default: 2K)"
    },
    "output_format": {
      "type": "string",
      "enum": [
        "jpg",
        "png"
      ],
      "default": "jpg",
      "description": "Output image format (default: jpg)"
    }
  },
  "required": [
    "prompt"
  ]
}