
Original document
GPT Image 2 · en
{
"type": "VTuber live stream cover",
"theme": "pastel colors, soft and cute, lace, ribbons, hearts, and bunny elements.",
"character": {
"position": "Right side, bust",
"appearance": "Anime girl,{argument name=\"hair color\" default=\"pink\"} Long, wavy hair, large gray eyes, blush, and pink heart-shaped earrings.",
"accessories": "White bunny ears, with a big pink bow on her head.",
"outfit": "A white ruffled dress with lace trim and a large pink bow with a heart-shaped gemstone at the neckline."
},
"layout": {
"background": "A soft pink color with subtle shimmer, lace details, and floating hearts.",
"text_elements": [
{
"type": "Main title",
"position": "Top left corner",
"style": "Large artistic pink text with white outline",
"text": "{argument name=\"main title\" default=\"Casual chat stream\"}"
},
{
"type": "speech bubbles",
"position": "Above the main title",
"text": "まったり"
},
{
"type": "round badge",
"position": "Top right corner",
"details": "Lace trim with a small pink bow",
"text": "きてくれてありがとう♡"
},
{
"type": "Heart Badge",
"position": "bottom right corner",
"details": "Large lace-edged heart",
"text": "I'm looking forward to chatting with everyone ♡"
}
],
"list_section": {
"position": "bottom left corner",
"count": 3,
"style": "Horizontal capsule-shaped banners with lace trim, each banner featuring a pink heart with white bunny ears and a miniature bow on the left side.",
"items": [
"{argument name=\"list item 1\" default=\"First-time viewers welcome\"}",
"{argument name=\"list item 2\" default=\"Points can be collected.\"}",
"{argument name=\"list item 3\" default=\"ROM〇\"}"
]
}
}
}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.





