Original document
GPT Image 2 · en
Create a whimsical photorealistic vertical image of a tiny miniature {argument name="character description" default="young man with curly dark hair, wearing a red-and-black plaid flannel shirt, dark cuffed jeans, brown lace-up boots, and an olive backpack"} sitting on the rim of an oversized speckled ceramic latte cup. The character sits with legs dangling over the front of the mug, hands resting near the knees, looking thoughtfully upward to the right. The giant cup is filled with creamy latte art and visible soft steam rising from the surface, with the handle on the right. Set the scene on a warm wooden kitchen table in a cozy sunlit kitchen, using shallow depth of field, golden morning light, cinematic realism, soft bokeh, and detailed textures. Include exactly 1 miniature person, 1 oversized latte cup, 1 wooden spoon in the foreground, 1 bowl filled with coffee beans on the left, 2 croissants on small plates, 3 chocolate chip cookies on plates, and scattered roasted coffee beans across the tabletop. In the blurred background include a bright window, potted plants, a sink and faucet, wooden counters, kitchen utensils, a cutting board, and a stove, all softly out of focus. Mood: magical, cozy, viral miniature-world aesthetic, ultra-detailed, realistic lighting, vertical 9:16 composition, no text, no watermark.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.
