AI patio furniture preview: place a product photo in your patio

Your patio and the product shot

Retailers show furniture on white backgrounds. Buyers want it on their own patio. With a photo of the space and the catalog image of the set, one edit call places it.

Send the patio first and the product second in input_references, and name them. ChatGPT Image 2.5 takes up to 16 references, so you can add more angles of the set.

Sume Image API docs list ChatGPT Image 2.5 as openai/gpt-image-2.5 (Flare) and openai/gpt-image-2.5-sunburst. OpenAI's guide says to choose Sunburst where editing precision matters most and Flare for fast everyday generation, so these edits use Sunburst.

Give scale and position

Say where the set goes and about how large it is compared with the patio: on the stone area, left of the door, the table about 1.8 m long. Tell the model to keep the house, plants and ground unchanged and to match the light and shadows.

import os
import requests

REFS = [
    "https://example.com/patio.jpg",
    "https://example.com/patio-set.jpg",
]
resp = requests.post(
    "https://api.sume.com/v1/images",
    headers={"Authorization": f"Bearer {os.environ['SUME_API_KEY']}"},
    json={
        "model": "openai/gpt-image-2.5-sunburst",
        "prompt": "Image 1 is a patio photo, image 2 is a patio dining set. "
                  "Place the set on the stone area left of the door, table "
                  "about 1.8 m long, with matching light and soft shadows. "
                  "Keep house, plants and ground unchanged.",
        "aspect_ratio": "auto",
        "input_references": [
            {"type": "image_url", "image_url": {"url": u}} for u in REFS
        ],
    },
    timeout=60,
)
print(resp.status_code)
print(resp.json())

Check list for placement

One variable at a time is easier to judge.

Do not skip the tape measure

A render cannot guarantee that the set fits. Measure the area and compare it with the product dimensions from the retailer's page before buying.

Inputs Sume checks before it spends anything

Reference and mask URLs must be public HTTPS; localhost, private-network and non-HTTPS URLs are rejected. Sume also checks every field against the model's catalog entry, so a field the model does not list returns 400 unsupported_parameter instead of being dropped without a word.

If you are unsure which fields a model accepts, GET /v1/images/models lists them, and GET /v1/images/models/{id}/endpoints returns the per-endpoint capabilities and pricing.

Cost, retries and slow calls

Each edit is one billed image when it completes, and nothing when it fails. Sume's docs say the amount in usage.cost is what the wallet is charged, with the 1.25 multiplier on provider list price already applied. That makes a retry cheap to reason about: a failed attempt costs zero.

Slow settings, such as 4K output, high quality or a large n, can push a call past the 30-second wait. Then the response is 202 with a job envelope rather than the image, and you fetch the result from the job endpoints.