IP
生成
Ancient Chinese Cinematic Still preview image
主參考影像

Ancient Chinese Cinematic Still

A complex image-to-image prompt for transforming personal portraits into cinematic stills from an Eastern wuxia film.

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。
上傳圖片生成

Free 1K preview

Generate one preview image instantly, no sign-up required.

Free text preview doesn’t preserve reference-image consistency.

2555/4000
Continue on Dovoo

提示詞

可直接複製的提示

Use my uploaded portrait photo as the only identity reference. Preserve only my real facial features, face shape, skin tone, hairstyle, hairline, and overall personal vibe. Do not use the face of the person in the reference image. All other elements — including visual style, clothing, scene, composition, lighting, and mood — should follow the reference photo.

Generate an ultra-realistic cinematic vertical portrait. The subject is standing in a {argument name="setting" default="traditional Chinese palace courtyard"}, photographed from a low angle, in a half-body close-up. The person is slightly turned to the side, with the head naturally facing off to one side, not looking at the camera, showing a calm, restrained, story-driven expression. The background features ancient palace eaves, red walls, stone railings, and traditional roof structures, creating a sense of historical Chinese architecture.

The subject wears a {argument name="clothing" default="deep black traditional robe or black Chinese-style outer garment"}, with subtle fabric texture and an overall dark color palette. {argument name="lighting" default="Sunlight comes from the front-side direction"}, illuminating part of the face and creating strong light-and-shadow contrast, with one side of the face lit and the other side naturally falling into shadow. The hair is gently blown by the wind, with loose strands moving naturally, but it must still preserve the hairstyle characteristics of my uploaded portrait and should not be changed into someone else’s hairstyle.

The overall style should feel like a realistic cinematic still, with authentic photographic texture, shallow depth of field, slight film grain, muted colors, high-contrast lighting, and a subtle vintage tone. The skin must look real and natural, with normal skin texture. Do not over-smooth the skin. No plastic look, no anime look. The image should be clean and premium, with no text, no watermark, and no logo. Vertical 9:16, high detail.

Negative Prompt:

watermark, logo, text, Chinese characters, Doubao watermark, AI watermark, anime, cartoon, illustration, plastic skin, overly smooth skin, doll-like face, fake face, face swap look, distorted facial features, wrong identity, different person, bad eyes, unnatural hair, messy hair clumps, overexposed face, Show every face clearly with natural, detailed facial features, low quality, extra fingers, deformed hands, modern building, modern clothes, sci-fi style, fantasy armor, excessive beauty filter, unnatural lighting, pasted face, collage look

提示變數

提示符號中可編輯的參數佔位符及其預設值。

3
多變的
setting
預設
traditional Chinese palace courtyard
多變的
clothing
預設
deep black traditional robe or black Chinese-style outer garment
多變的
lighting
預設
Sunlight comes from the front-side direction

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. 1. Copy the prompt and preserve its structure for the first test.
  2. 2. Replace the subject, context, and publishing channel.
  3. 3. Change one camera, lighting, or style variable per iteration.
  4. 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。

6

重用和來源註釋

預覽案例後,請謹慎使用此提示。

  1. 1.複製提示或直接在 Dovoo 中使用生成按鈕開啟提示。
  2. 2.根據您的實際使用情況調整變數、寬高比和參考影像。
  3. 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。