原始文档
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.使用方法
- 复制完整原始提示词，并保留其中的参数。
- 按需求替换主体、文字和构图要求。
- 在兼容的外部工具中使用，核对当前使用条件并检查结果。
开始前需了解
- 先确认是否需要参考图。标注兼容模型，不代表该示例由这个模型生成。
- 核对名称、数字与画面文字；不同模型版本的结果可能不同。
