Original document
GPT Image 2 · en
{
"type": "3-panel comic layout",
"subject": "{argument name=\"subject\" default=\"Sam Altman\"}",
"object": "{argument name=\"object\" default=\"banana\"}",
"layout": {
"structure": "The left side is divided into two horizontal sections, while the right side is a large vertical panel.",
"panels": [
{
"number": "1",
"position": "Top left",
"description": "The subject is happily eating an object while laughing in an office environment."
},
{
"number": "2",
"position": "Bottom left",
"description": "The main body is shown in profile, with a strip of silver tape used to attach the fruit peel to a pure white wall."
},
{
"number": "3",
"position": "right half",
"description": "A close-up of an object's peel taped to a white wall. Below is {argument name=\"company logo\" default=\"OpenAI\"} The logo and text. Below the logo is another piece of tape with the handwritten words \"...\"{argument name=\"tape text\" default=\"Duct tape\"} The word \"\"."
}
]
}
}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.
