
Original document
GPT Image 2 · en
{
"type": "8-panel comic infographic",
"reading_order": "From right to left",
"character": {
"name": "{argument name=\"character name\" default=\"Lisa\"}",
"appearance": "{argument name=\"character appearance\" default=\"Golden twin ponytails, black gothic dress, black heart-shaped choker\"}"
},
"panels": [
{
"number": 1,
"action": "Waving happily",
"speech_bubble": "{argument name=\"greeting text\" default=\"Hello! I'm Lisa! Today I'm going to talk to you about some major rumors surrounding OpenAI, specifically about GPT-image-2!\"}"
},
{
"number": 2,
"action": "Staring in surprise at the glowing screen",
"screen_text": "OpenAI{argument name=\"product name\" default=\"GPT-image-2\"} Smarter - Clearer - More Creative",
"speech_bubble": "According to leaked information, this update is ridiculously powerful!"
},
{
"number": 3,
"action": "Pointing to the coffee shop sign",
"sign_text": "Cafe Open (Coffee & Sweets)",
"speech_bubble": "First, the text processing! No more spelling errors on signs or menus! It's absolutely perfect!"
},
{
"number": 4,
"action": "Holding a smartphone displaying the application interface",
"ui_elements_count": 6,
"ui_elements": [
"My daily life",
"Searching for inspiration...",
"explore",
"creation",
"Image Gallery",
"Personal information"
],
"speech_bubble": "It can even generate application interfaces directly! The professional-level quality is truly amazing!"
},
{
"number": 5,
"action": "Show comparison chart",
"comparison": "Blurry portraits vs. sharp 4K realistic female portraits",
"speech_bubble": "4K resolution, photorealistic picture quality! Skin texture and lighting effects are extremely detailed!"
},
{
"number": 6,
"action": "blink and point forward",
"floating_objects_count": 7,
"floating_objects": [
"Palette",
"camera",
"Light bulb",
"Landscape photos",
"lantern",
"coffee cup",
"A notebook with IDEA written on it"
],
"speech_bubble": "Complex commands can be executed perfectly. Camera composition and prop placement can be done at will!"
},
{
"number": 7,
"action": "Pointing to the project",
"whiteboard_poses_count": 5,
"whiteboard_poses": [
"Front view, full body",
"Side view of the whole body",
"Front view of the face",
"Side profile",
"Half-body blink"
],
"speech_bubble": "There's also a character-fixing feature! Characters like mine will be able to maintain a consistent appearance from now on!"
},
{
"number": 8,
"action": "Give a thumbs up, wink, and the background sparkles.",
"speech_bubble": "{argument name=\"conclusion text\" default=\"The era of AI and humans co-creating stories is truly exciting! Be sure to stay tuned!\"}"
}
]
}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.





