意外提取iPhone自拍照片
透過從 ChatGPT 螢幕截圖中提取和擴展下方照片，同時移除所有 UI 元素，產生一張獨立的逼真失敗自拍。
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.
Free text preview doesn’t preserve reference-image consistency.
915/4000
提示詞
可直接複製的提示
Using REFERENCE_1 as the source, isolate the lower accidental selfie photo and turn it into the final standalone image: remove the ChatGPT interface, text bubble, download icon, and input bar completely, then uncrop/extend the snapshot so it fills the frame as a vertical iPhone-style photo. Follow the intent described in REFERENCE_0: make it look like an ordinary, slightly failed, unplanned selfie taken while pulling a phone from a pocket, with a careless low angle, messy composition, slight motion blur, uneven lighting, mild overexposure from the room lights, and a very realistic casual phone-camera feel. Keep the same indoor room, ceiling light, wall lamp, and subject from the lower photo, but show more of the face, neck, dark shirt, and a thin chain necklace, with a blurry finger partially covering the lower-left foreground. Avoid making it look posed, polished, cinematic, or intentionally composed.
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: 圖生圖
- - 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。