3DGen AI

3 tokens3D

Generate exportable 3D models from images

Overview

Generate 3D models from photos. Upload an image of a furniture piece or object and the AI generates a 3D model that can be exported and used in 3D modeling software, game engines, or AR/VR applications. Provide multiple angle photos for improved accuracy.

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": "3dgen", ...}'

Parameters

Parameter	Type	Required	Description
`model`	string	Required	Must be "3dgen". 3dgen
`image`	string	Required	URL of the primary image (front view recommended).
`prompt`	string	Optional	Describe the object for better 3D interpretation (e.g. "a round wooden dining table").
`extra_image_1`	string	Optional	URL of a second angle photo (side view).
`extra_image_2`	string	Optional	URL of a third angle photo (back or top view).
`extra_image_3`	string	Optional	URL of a fourth angle photo.
`format`	string	Optional	Output format. Default: `"png"` png

Request Example

json

{
  "model": "3dgen",
  "image": "https://example.com/chair-front.jpg",
  "prompt": "a modern accent chair with wooden legs",
  "extra_image_1": "https://example.com/chair-side.jpg",
  "extra_image_2": "https://example.com/chair-back.jpg"
}

Response

Success (200)

json

{
  "status": "success",
  "result": {
    "image_url": "https://storage.googleapis.com/...",
    "model": "3dgen",
    "tokens_used": 3,
    "processing_time_ms": 4500
  }
}

Error

json

{
  "status": "error",
  "error": {
    "code": "INSUFFICIENT_TOKENS",
    "message": "Not enough tokens",
    "required": 3,
    "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": "3dgen",
  "image": "https://example.com/chair-front.jpg",
  "prompt": "a modern accent chair with wooden legs",
  "extra_image_1": "https://example.com/chair-side.jpg",
  "extra_image_2": "https://example.com/chair-back.jpg"
}'

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": "3dgen",
  "image": "https://example.com/chair-front.jpg",
  "prompt": "a modern accent chair with wooden legs",
  "extra_image_1": "https://example.com/chair-side.jpg",
  "extra_image_2": "https://example.com/chair-back.jpg"
}),
});

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": "3dgen",
  "image": "https://example.com/chair-front.jpg",
  "prompt": "a modern accent chair with wooden legs",
  "extra_image_1": "https://example.com/chair-side.jpg",
  "extra_image_2": "https://example.com/chair-back.jpg"
},
)

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

1Provide 2-3 angle photos for significantly better 3D model accuracy.
2Clean backgrounds (white or solid color) help the AI isolate the object.
3Costs 3 tokens per generation due to the computational complexity.
4Include a descriptive prompt to help the AI understand the object geometry.