Repair vintage portrait
Repair scratches and missing emulsion in the masked areas of the vintage portrait, preserve original facial features and film grain, maintain monochrome tonality, do not beautify or modernize.
Test the workflow,
not the marketing claim.
Restoration prompts need stronger preservation language than creative edits; this guide records protected facial features, damage targets, historical details, and acceptance criteria.
Remove tabletop object
Remove the red ceramic cup from the table and reconstruct the walnut grain and its soft window reflection; preserve every other object, crop, color, and shadow.
Expand cafe scene
Extend the cafe photograph horizontally, continuing the tiled wall, wooden counter and warm pendant lighting with correct perspective; keep the central subject unchanged and avoid adding people.
PYTHON QUICKSTART
Keep the request reproducible.
Store credentials in the environment. Record the exact model identifier, dimensions, test date, and retry count with the resulting asset.
import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ["APIMART_API_KEY"],
base_url="https://api.apimart.ai/v1",
)
result = client.images.generate(
model="gpt-image-1-official",
prompt=PROMPT,
size="1024x1024",
n=1,
)Before you publish a result
- Record model ID, parameters, date, latency, and retry count.
- Review instruction following and protected attributes.
- Flag invented text, marks, anatomy, or unwanted objects.
- Keep the raw output linked to the original fixture.
- Do not claim a universal winner from one prompt.