
Realistic Cafe Portrait Prompt for GPT Image 2
A detailed prompt for generating a realistic iPhone-style photo of a woman in a cafe using GPT Image 2, focusing on faithful character reproduction from a reference image and specific lighting/composition details.
Dette er et tilfelle av en GPT Image 2 -ledetekst for Portrett og karakter . Bruk den kopieringsklare ledeteksten nedenfor for å generere lignende visuelle elementer, og gjennomgå Awesome GPT Image 2 Prompts -attribusjonen pluss kommersielle bruksrettigheter før gjenbruk.
Free 1K preview
Generate one preview image instantly, no sign-up required.
Free text preview doesn’t preserve reference-image consistency.
Spørsmål
Klar til kopiering
Shot on an iPhone. The woman’s appearance should be 100% faithful to the uploaded reference photo, sitting at a café table outdoors under an autumn tree, centered in the frame. Her body is facing forward, her head slightly tilted, with one cheek gently resting on one hand while the other hand is relaxed on the table, holding the stem of a wide red-wine glass with a very thin, long, delicate stem and thin glass walls. Only a small amount of wine remains at the bottom. She is wearing a voluminous black trench coat with structured shoulder pads and oversized long sleeves covering her fingers, with a black turtleneck underneath. Hair exactly matching the uploaded photo. White tablecloth, elegant white plates, a classic European-style building façade in the background, with an autumn tree filling the upper part of the frame. True-to-life iPhone realism, subtle natural film grain, authentic skin texture and lighting. Do not blur the background; maintain realistic environmental detail throughout the scene. Short square French-tip manicure. 9:16 vertical format. She is wearing narrow black rimless cat-eye sunglasses. Overcast daytime with no direct sunlight. Slightly slower shutter speed for a subtle natural motion/film feel while keeping the subject realistic and recognizable.
Best for
- - Portrett og karakter 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: Bilde til bilde
- - 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.
Flere saker i denne kategorien
Prioritert etter kategori, kompatibilitet med inndatamodus, kvalitet og lavere risiko.
Gjenbruk og kildenotater
Bruk denne ledeteksten på en trygg måte etter at du har forhåndsvist saken.
- 1.Kopier ledeteksten eller åpne den direkte i Dovoo med genereringsknappen.
- 2.Juster variabler, sideforhold og referansebilder for ditt eget brukstilfelle.
- 3.Før publisering eller betalt bruk, kontroller kilderettigheter, krav til kreditering og risikoer knyttet til merkevare eller likhet.





