MAI Image 2.7 API
Plan edits with the Microsoft MAI Image 2.7 model. In the MAI Image API Playground, pair a source image with clear instructions for the scene, lighting, text, and details you want to retain.
MAI Image 2.7 API configuration
- Source image from a file or URL
- Editing instructions in your prompt
- Form and JSON configuration
Specify what to change and which details to preserve.
Choose an image and describe the changes.
Prepare focused edits with MAI Image 2.7 API
Start with your image and a precise editing goal. Use the editing workspace to separate requested changes from the composition, materials, and details that should stay the same.
MAI Image 2.7 API example: image editing
Use these examples to organize an image-editing request with a source image and an editing prompt, then query the task to retrieve its result.
- 1
Authenticate the MAI Image 2.7 API request
Save your APIMart API key in the APIMART_API_KEY environment variable. Send it as Authorization: Bearer <key> when submitting the edit and querying the task.
- 2
Submit an image-editing task
Send POST /v1/images/generations with model set to mai-image-2.7, an editing prompt, and image_urls containing one HTTP or HTTPS source-image URL. Read the task ID from data[0].task_id in the response.
- 3
Retrieve the edited image
Send GET /v1/tasks/{task_id} to query the task. When its status is completed, read the image URL from data.result.images[0].url[0]. If the status is failed, read the reason from data.error.message.
See the APIMart documentation for APIMart authentication and general API usage.
curl -X POST https://api.apimart.ai/v1/images/generations \
-H "Authorization: Bearer $APIMART_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "mai-image-2.7",
"prompt": "Place the product from this image on a marble kitchen counter in soft morning light, keeping its shape and label unchanged.",
"image_urls": [
"https://example.com/source-image.jpg"
]
}'import os
import time
import requests
API_BASE = "https://api.apimart.ai"
headers = {"Authorization": f"Bearer {os.environ['APIMART_API_KEY']}"}
# 1. Submit the generation task
payload = {
"model": "mai-image-2.7",
"prompt": "Place the product from this image on a marble kitchen counter in soft morning light, keeping its shape and label unchanged.",
"image_urls": [
"https://example.com/source-image.jpg"
]
}
resp = requests.post(f"{API_BASE}/v1/images/generations", headers=headers, json=payload, timeout=60)
resp.raise_for_status()
task_id = resp.json()["data"][0]["task_id"]
# 2. Poll the task until it finishes
for _ in range(200):
task_resp = requests.get(f"{API_BASE}/v1/tasks/{task_id}", headers=headers, timeout=30)
task_resp.raise_for_status()
task = task_resp.json()["data"]
if task["status"] == "completed":
print(task["result"]["images"][0]["url"][0])
break
if task["status"] == "failed":
raise RuntimeError(task.get("error", {}).get("message", "generation failed"))
time.sleep(3)
else:
raise TimeoutError(f"task {task_id} did not finish in time; continue GET polling with this task ID")TASK_ID="task_xxx" # replace with the task_id returned by the POST request
curl "https://api.apimart.ai/v1/tasks/$TASK_ID" \
-H "Authorization: Bearer $APIMART_API_KEY"MAI Image 2.7 API parameters
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
model | string | Required | Default: mai-image-2.7 | Model value used in this page’s example: mai-image-2.7. |
prompt | string | Required | Default: — | Describe the edits to make and the elements of the source image to preserve. |
image_urls | array | Required | Default: — | An array containing exactly one HTTP or HTTPS URL for the source image to edit. |
