
日本恐怖遊戲《街頭倒影》
這個提示會產生一張黑暗的超寫實生存恐怖遊戲截圖,畫面中一名男子在雨中的日本城市街道上面對著扭曲的幽靈倒影。
這是一個動漫與遊戲的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 動漫與遊戲 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.
1623/4000
提示詞
可直接複製的提示
A cinematic Japanese psychological horror game screenshot at night, shown from a third-person over-the-shoulder perspective behind a young man wearing a dark hooded jacket, standing under a convenience store awning and staring into a large front window. In the glass, instead of a normal reflection, there is a terrifying humanoid figure with an unnaturally elongated oval head, long straight black hair hanging down both sides, a pale expressionless face, and a dark coat, standing directly opposite him. Beyond the reflection is a wet urban street in Japan with glossy rain-soaked asphalt, sparse pedestrians holding umbrellas, dim storefronts, vending machines, parking signs, and tall buildings bending inward in a surreal warped perspective toward a dark swirling vortex in the sky at the end of the street. The convenience store window ledge displays exactly 5 visible magazine covers lined up side by side and exactly 8 instant food items or cup noodles stacked on the lower right. Add subtle in-game UI text in Japanese: exactly 2 objective lines in the upper left, and exactly 2 small action prompts in the lower left. Include readable Japanese street posters and shop signs, such as a large red staff recruitment sign on the upper right and a yellow points campaign sign on the lower right. Lighting is extremely dark, moody, and realistic, with reflections, deep shadows, damp textures, and a faint cold glow from interior lights and street lamps. Style: ultra-realistic survival horror video game, unsettling, grounded, detailed, cinematic, high contrast, eerie silence, no exaggerated action, no bright colors.
Best for
- - 動漫與遊戲 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。





