IP
生成
Superhero Era Transformation Split Portrait preview image
主參考影像

Superhero Era Transformation Split Portrait

A complex logic-based prompt that uses reference images to transform a character into two versions (normal and superhero) across different historical eras.

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.

2545/4000
Continue on Dovoo

提示詞

可直接複製的提示

Masterpiece quality 9:16 aspect ratio
@image1 = {argument name="reference character" default="primary character reference"}
Preserve the referenced characters’ face shape, hairstyle, hair color, eye color, correct number of limbs and fingers, personality, body language, signature color palette, outfit motifs, species traits, accessories, silhouette, body shape, body proportions, and overall character vibe. If the character has a mask, do not change it. If the character does not have a head, do not invent one. Do not lose character recognizability. Do not turn the character into a generic person or unrelated design. Do not overcrowd the composition. Do not introduce extra characters or duplicates. Do not break anatomy unless clearly justified by transformation concept. Do not make the scene visually confusing or unreadable. Do not explicitly list or name the hidden influences used. Do not let environment overpower the character.
Use your Python environment (Code Interpreter) to generate a pseudo-random number. Do not guess or rely on your language modeling weights to pick the number. 
Please follow these exact constraints:
1. Range: Between [1] and [4], inclusive.
2. Type: [Integer]
3. Execution: Import the 'random' or 'secrets' library to compute the result.
4. Output: Do not provide the final random number(s) as the output. Do not include conversational filler. Use the number to select the setting from the list below.
1. Wild West
2. Edwardian England
3. 1920’s Jazz Era
4. Medieval
Draw two versions of @image1. Draw a diagonal line separating both versions. The line’s color, shape, and material effect will be determined by the visual personality of @image1. @image1 will be On the left, standing in a parlor fitting to the chosen setting and wearing a formal outfit, also fitting the chosen setting, by a fireplace. The outfit must adhere to the visual personality of @image1. The expression and posture will one of peaceful contentment. This setting will be midday.
The right side will have @image1 wearing a superhero costume fitting to the chosen setting. The costume must be intricate, elegant, designed for maximum stealth, adhere to the visual personality of @iamge1, and have a powerful aura. They will be outdoors at night, and they will be stalking potential criminals. @image1 will use weapons or magic fitting to their character and visual personality. If @image1 is a child, they will use magic and ensure their costume is appropriate and cute. The expression and posture will one of a stealthy assassin.

提示變數

提示符號中可編輯的參數佔位符及其預設值。

1
多變的
reference character
預設
primary character reference

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。
Superhero Era Transformation Split Portrait for GPT Image 2 | Image Prompt Gallery