Fill Room AI

1 tokenInterior

Fill empty rooms with AI-generated furniture

Overview

Fill Room AI is designed for virtual staging — it takes photos of empty or unfurnished rooms and fills them with stylistically appropriate furniture and decor. Ideal for real estate agents who need to stage vacant properties, or for homeowners visualizing how an empty space could look furnished. The AI understands the room geometry and places furniture naturally.

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": "fill", ...}'

Parameters

Parameter	Type	Required	Description
`model`	string	Required	Must be "fill". fill
`image`	string	Required	URL of the empty room photo.
`knows`	string	Optional	Room type for appropriate furniture selection. Living RoomKitchenBedroomBathroomDining RoomHome Office
`styles`	string	Optional	Design style to apply. Over 99 styles available including modern, minimalist, industrial, and more. ModernMinimalistScandinavianIndustrialMid-Century ModernBohemian
`prompt`	string	Optional	Custom text instructions describing the desired output.
`precise`	string	Optional	AI strength from "0" to "100". Lower values give the AI more creative freedom. Higher values preserve more of the original structure. Default: `"50"`
`style_transfer`	string	Optional	URL of a reference image whose style should be matched in the output.
`enhance_prompt`	string	Optional	Set to "true" to let the AI enhance and expand your prompt for better results. Default: `"false"` truefalse
`luwmodel`	string	Optional	AI model variant to use. Default: `"symphony-3"` symphony-3aria
`format`	string	Optional	Output image format. Default: `"png"` png
`seed`	number	Optional	Random seed for reproducible results. Using the same seed with the same parameters produces identical output.

Request Example

json

{
  "model": "fill",
  "image": "https://example.com/empty-bedroom.jpg",
  "styles": "scandinavian",
  "knows": "bedroom",
  "prompt": "cozy minimalist bedroom with warm lighting"
}

Response

Success (200)

json

{
  "status": "success",
  "result": {
    "image_url": "https://storage.googleapis.com/...",
    "model": "fill",
    "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": "fill",
  "image": "https://example.com/empty-bedroom.jpg",
  "styles": "scandinavian",
  "knows": "bedroom",
  "prompt": "cozy minimalist bedroom with warm lighting"
}'

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": "fill",
  "image": "https://example.com/empty-bedroom.jpg",
  "styles": "scandinavian",
  "knows": "bedroom",
  "prompt": "cozy minimalist bedroom with warm lighting"
}),
});

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": "fill",
  "image": "https://example.com/empty-bedroom.jpg",
  "styles": "scandinavian",
  "knows": "bedroom",
  "prompt": "cozy minimalist bedroom with warm lighting"
},
)

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

1Works best with photos of completely empty rooms — clear floors and walls produce the most natural staging results.
2Always specify the "knows" parameter so the AI places the right type of furniture (e.g. a bed in a bedroom, a sofa in a living room).
3Combine with a specific style for consistent design language across multiple rooms in a property listing.
4Great for real estate photography — stage a vacant property in multiple styles to appeal to different buyer tastes.