
Sunlit Cafe Popsicle Portrait
A photorealistic vertical portrait prompt for generating a softly lit young woman with braids and glasses enjoying a popsicle at a wooden cafe table.
這是一個肖像與人物的GPT Image 2範例。請使用下方可直接使用的提示資訊產生類似的視覺素材,並在重複使用前查看Awesome GPT Image 2 Prompts署名和商業用途授權資訊。
需要完整的提示符號集?請使用 肖像與人物 主題中心提供更多相關範例,或打開 GPT Image 2 提示庫 有關完整範例索引、可重複使用結構和來源歸屬的資訊。
Free 1K preview
Generate one preview image instantly, no sign-up required.
1532/4000
提示詞
可直接複製的提示
Create a warm, photorealistic lifestyle portrait of a young East Asian woman named {argument name="character name" default="Half Done"} sitting sideways on a wooden chair at a wooden table in a softly lit cafe or sunroom. She has long dark brown to black hair in two loose braids, wispy straight bangs, fair skin, round thin metal eyeglasses, large natural eyes, and a gentle smiling expression as she looks directly at the viewer. She is holding a pale yellow popsicle in one hand near her mouth, with her other arm relaxed on the tabletop. Her outfit is a loose oversized {argument name="shirt color" default="white"} T-shirt with a subtle pastel graphic on the chest and light sage green shorts. The composition is a vertical 3:4 portrait, waist-to-knees framing, with her seated at the right side of the table and her legs angled toward the lower left. The setting includes exactly 5 main visible furniture and decor elements: a wooden table, a wooden chair, a softly blurred window on the left, a leafy green houseplant near the window, and shelves or kitchenware in the background. Use golden-hour sunlight streaming from the left, soft haze, shallow depth of field, creamy bokeh, realistic skin texture, delicate highlights on the glasses, natural shadows, and a calm nostalgic atmosphere. Add a small handwritten-style watermark reading {argument name="watermark text" default="HALF_DONE"} in the lower right corner. Avoid anime styling, exaggerated features, extra people, extra hands, distorted glasses, or cluttered text.提示變數
提示符號中可編輯的參數佔位符及其預設值。
多變的
character name
預設
Half Done
多變的
shirt color
預設
white
多變的
watermark text
預設
HALF_DONE
Best for
- - 肖像與人物 visual exploration
- - Image generation and reference-image edits
- - Reusable briefs that keep source attribution visible
Change these parts
- - Subject, product, character, or scene
- - Aspect ratio, camera, lighting, and background
- - Brand, text, color, and output constraints
Recommended model and settings
- - Model: gpt-image-2
- - Input mode: 文生圖
- - Aspect ratio: source
- - Commercial status: review original source
How to use this prompt
- 1. Copy the prompt and preserve its structure for the first test.
- 2. Replace the subject, context, and publishing channel.
- 3. Change one camera, lighting, or style variable per iteration.
- 4. Inspect the output, source, text, and rights before reuse.
Limitations, source, and reuse cautions
- - Generated output is an editable draft, not factual, legal, or rights evidence.
- - Review the linked source, people, brands, logos, text, and third-party media before commercial use.
內容來自Awesome GPT Image 2 Prompts 。必須註明出處。商業用途狀態為allowed ;付費使用前請查看來源版權資訊。
此類案例更多
按類別、輸入模式相容性、品質和低風險進行優先排序。
重用和來源註釋
預覽案例後,請謹慎使用此提示。
- 1.複製提示或直接在 Dovoo 中使用生成按鈕開啟提示。
- 2.根據您的實際使用情況調整變數、寬高比和參考影像。
- 3.發布或付費使用前,請確認版權、署名要求以及品牌或肖像權風險。





