Expand AI

1 tokenTools

Extend cropped photos with AI outpainting

Overview

Expand AI extends the boundaries of a cropped photo using AI outpainting. The AI seamlessly continues the scene beyond the original frame — generating floors, walls, ceilings, and furnishings that match the existing content. Perfect for making narrow room shots wider or extending compositions for marketing materials.

Image input

Endpoint

POST /api/v1/generate

bash

curl -X POST https://roomai.com/api/v1/generate \
  -H "Authorization: Bearer rai_live_your_api_key" \
  -H "Content-Type: application/json" \
  -d '{"model": "expand", ...}'

Parameters

Parameter	Type	Required	Description
`model`	string	Required	Must be "expand". expand
`image`	string	Required	URL of the image to expand.
`prompt`	string	Optional	Optional guidance for the expanded area (e.g. "continue the living room with a dining area").
`format`	string	Optional	Output format. Default: `"png"` png

Request Example

json

{
  "model": "expand",
  "image": "https://example.com/cropped-room.jpg",
  "prompt": "continue the room with large windows overlooking a garden"
}

Response

Success (200)

json

{
  "status": "success",
  "result": {
    "image_url": "https://storage.googleapis.com/...",
    "model": "expand",
    "tokens_used": 1,
    "processing_time_ms": 4500
  }
}

Error

json

{
  "status": "error",
  "error": {
    "code": "INSUFFICIENT_TOKENS",
    "message": "Not enough tokens",
    "required": 1,
    "balance": 0
  }
}

Code Examples

cURL

bash

curl -X POST https://roomai.com/api/v1/generate \
  -H "Authorization: Bearer rai_live_your_api_key" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "expand",
  "image": "https://example.com/cropped-room.jpg",
  "prompt": "continue the room with large windows overlooking a garden"
}'

JavaScript / Node.js

javascript

const response = await fetch("https://roomai.com/api/v1/generate", {
  method: "POST",
  headers: {
    "Authorization": "Bearer rai_live_your_api_key",
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
  "model": "expand",
  "image": "https://example.com/cropped-room.jpg",
  "prompt": "continue the room with large windows overlooking a garden"
}),
});

const data = await response.json();

if (data.status === "success") {
  console.log("Image URL:", data.result.image_url);
  console.log("Tokens used:", data.result.tokens_used);
} else {
  console.error("Error:", data.error.message);
}

Python

python

import requests

response = requests.post(
    "https://roomai.com/api/v1/generate",
    headers={
        "Authorization": "Bearer rai_live_your_api_key",
        "Content-Type": "application/json",
    },
    json={
  "model": "expand",
  "image": "https://example.com/cropped-room.jpg",
  "prompt": "continue the room with large windows overlooking a garden"
},
)

data = response.json()

if data["status"] == "success":
    print("Image URL:", data["result"]["image_url"])
    print("Tokens used:", data["result"]["tokens_used"])
else:
    print("Error:", data["error"]["message"])

Tips

1The AI expands in all directions — provide a prompt to guide what appears in the expanded area.
2Works best when there are visual cues at the edges (partial furniture, wall lines) for the AI to continue.
3Great for turning portrait-orientation photos into landscape format for marketing materials.