10

基于身份的玫瑰园肖像
Enlarge

基于身份的玫瑰园肖像

Prompt
Use my uploaded portrait only as the identity reference for the person’s facial features, face shape, hairstyle, hair color, skin tone, and overall real-person appearance. Do not copy the face or identity from the reference image.

Recreate the uploaded person in a {argument name="setting" default="romantic rose-garden portrait"} inspired by the reference photo. The person is seated gracefully on a pale stone garden path, surrounded closely by dense blooming pink roses, soft green leaves, and layered floral bushes. Use a natural seated pose with the legs folded comfortably to one side, relaxed shoulders, elegant hands, and a calm, gentle expression while looking toward the camera.

Choose an outfit automatically based on the uploaded person’s appearance, hairstyle, body proportions, and personal style. The clothing should feel flattering and harmonious with the romantic garden setting, using soft {argument name="colors" default="blush pink, ivory, cream, or pastel tones"}, with tasteful floral, chiffon, lace, ribbon, or layered fabric details. Do not force one specific dress design. Keep the outfit realistic, refined, and physically believable.

Soft diffused daylight, subtle backlight through the flowers, delicate shadows, dreamy pastel color grading, shallow depth of field, softly blurred background roses, romantic editorial photography, realistic fabric texture, natural hair strands, realistic skin pores, accurate anatomy, natural hands and fingers, lifelike body proportions, high facial identity accuracy, professional full-body portrait, square composition.

Keep the uploaded person clearly recognizable and photorealistic. No artificial beauty filter, no excessive skin smoothing, no plastic skin, no doll-like face, no anime or illustration style, no CGI appearance, no watermark, no logo, no text.

Negative Prompt:

anime, manga, illustration, 3D render, CGI, doll face, plastic skin, waxy skin, excessive retouching, over-smoothed face, fake facial features, identity change, copied reference face, distorted anatomy, incorrect body proportions, extra fingers, fused fingers, malformed hands, stiff pose, floating limbs, overly revealing outfit, exaggerated accessories, oversaturated pink, harsh lighting, blurry face, low resolution, watermark, logo, text, signature
Category
Posters & Typography
Model
GPT Image 2
Creator
Shinning
Views1
Source ID
25535
Published
Jun 13, 2026

Guide

About "基于身份的玫瑰园肖像"

What is this prompt for?

"基于身份的玫瑰园肖像" AI image prompt for GPT Image 2 (Posters & Typography). 这是一个复杂的提示词,用于利用参考图像在浪漫梦幻的玫瑰园场景中重现特定人物的身份。 Copy it on Picva and recreate the look in one cl…

The full copyable prompt and example visuals above are ready for AI image generation or one-click recreate in Picva.

How to use this prompt

  1. Step 1

    Open the prompt detail

    Review the example visuals, category, and full prompt text for "基于身份的玫瑰园肖像".

  2. Step 2

    Copy the prompt

    Copy the prompt body from this page, or load it directly in Studio.

  3. Step 3

    Pick a model (GPT Image 2)

    Prefer GPT Image 2. If you switch models, keep subject and composition and tweak style terms.

  4. Step 4

    Generate and export

    Recreate the look in Picva, or export into your workflow for editing and publishing.

FAQ

What is the "基于身份的玫瑰园肖像" prompt?
It is an AI image-generation prompt for GPT Image 2 in the Posters & Typography category. This page includes the full prompt text, example visuals, and a one-click recreate path in Picva.
How do I use this prompt to generate an image?
Copy the prompt from this page, or use Generate / Studio. Paste it into a compatible image model, or recreate the look in Picva with optional reference images.
Which model is this prompt for?
This page lists GPT Image 2. Most descriptive prompts also transfer to nearby image models such as GPT Image, Flux, or Midjourney with light style tweaks.
Can I use the result commercially?
You can usually copy the prompt for creation, but commercial use of the final image depends on the model terms, reference-image rights, and the generated content. Follow the source author and platform rules.