
Original document
GPT Image 2 · en
{
"type": "3x3 character facial expressions grid",
"style": "{argument name=\"art style\" default=\"3D animation, Pixar style\"}",
"character_base": "{argument name=\"character description\" default=\"A young woman with voluminous dark wavy hair and wearing round, thin-rimmed glasses\"}",
"common_theme": "{argument name=\"framing concept\" default=\"Peeking through the torn holes in the white paper\"}",
"layout": {
"rows": 3,
"columns": 3,
"total_panels": 9,
"panels": [
{
"position": "Top left",
"expression": "blink",
"action": "Adjusting glasses",
"outfit": "green sweater"
},
{
"position": "Upper-middle",
"expression": "evil smile",
"action": "Pull down dark sunglasses",
"outfit": "Red leather jacket"
},
{
"position": "Top right",
"expression": "think",
"action": "fingers pressed against chin",
"outfit": "yellow hoodie"
},
{
"position": "Left and Middle",
"expression": "laughing out loud",
"action": "Arms resting on the edge",
"outfit": "Black and white striped shirt"
},
{
"position": "middle",
"expression": "Smile",
"action": "thumbs up",
"outfit": "orange shirt"
},
{
"position": "Right Center",
"expression": "neutral",
"action": "Drinking bubble tea",
"outfit": "blue sweater"
},
{
"position": "Bottom left",
"expression": "happy",
"action": "wave",
"outfit": "A white shirt layered under a purple sweater vest"
},
{
"position": "Middle to lower",
"expression": "Laughing with eyes closed",
"action": "crossed arms",
"outfit": "pink cardigan"
},
{
"position": "Bottom right",
"expression": "funny",
"action": "poking cheeks",
"outfit": "blue sweater"
}
]
}
}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.





