
Original document
GPT Image 2 · en
{
"type": "Japanese beverage advertising banner",
"subject": {
"description": "A young Japanese woman, with a warm smile, gazes at the audience, wearing a white shirt and holding a can of beer.",
"speech_bubble": "{argument name=\"speech bubble text\" default=\"This is my reward for today!\"}"
},
"product": {
"name": "{argument name=\"product name\" default=\"PREMIUM LAGER\"}",
"packaging": "White and gold beer cans with hop patterns and blue lettering"
},
"layout": {
"background": "Soft, bright, and blurred outdoor greenery background",
"sections": [
{
"position": "Top left corner",
"type": "promotional slogans",
"text": [
"{argument name=\"main catchphrase\" default=\"We've created a new delicious flavor.\"}",
"{argument name=\"secondary catchphrase\" default=\"A refreshing aroma and a crisp, delicious taste!\"}"
]
},
{
"position": "Middle left",
"type": "Product Brand",
"main_text": "{argument name=\"product name\" default=\"PREMIUM LAGER\"}",
"sub_text": "プレミアムラガー",
"badges": [
"New Release",
"100% malt"
],
"graphics": "Golden Hops Illustration"
},
{
"position": "Lower left",
"type": "Product Highlights",
"count": 3,
"style": "Rounded rectangle with icon",
"items": [
{
"icon": "hop",
"text": "Luxurious aroma, using aromatic hops"
},
{
"icon": "water drop",
"text": "Refreshing and pleasant, with a crisp aftertaste"
},
{
"icon": "wheat",
"text": "100% malt, rich and smooth flavor"
}
]
},
{
"position": "bottom",
"type": "Promotional banner",
"background_color": "Dark blue",
"main_text": "A new premium lager is born.",
"campaign_box": {
"badge": "Win great prizes in our lucky draw!",
"text": "{argument name=\"campaign text\" default=\"Click here for the convenience store free exchange coupon lottery campaign >\"}",
"element": "QR code"
},
"footer": "Legal drinking age warning and recycling symbol"
}
]
}
}How to use
- Copy the complete original prompt, including any parameters.
- Replace the subject, text and composition with your own requirements.
- Use a compatible external tool; check its current access conditions and review the result.
Before you start
- Check whether a reference image is required. A compatible model label does not mean this example was generated with that model.
- Keep names, figures and visible text accurate; results can vary between model versions.





