Long Lunch, made with GPT Image 2.5 Sunburst
Example made with GPT Image 2.5 Sunburst

Text to imagePortraits

GPT Image 2.5 Sunburst portrait promptLong Lunch

The exact text-to-image prompt behind this picture, made with GPT Image 2.5 Sunburst.

Prompt

Vertical 4:5 portrait frame. Sun-drenched portrait of a woman in a loose white linen shirt at an outdoor lunch table under a grape vine, a lemon-print tablecloth, a half-finished plate of pasta and a glass of sparkling water, dappled vine shade falling across her smiling face, warm 35mm color negative film look, relaxed summer mood, no text.

Prompts are kept in their original English to help reproduce the example. Copy one as it is, or adapt it for your project.

Opens GPT Image 2.5 Sunburst with this prompt and the settings below filled in.

135 tested GPT Image prompts →

Settings

Mode
Text to image
Aspect ratio
4:5
Quality
high
Price
From 2 credits

The exact price shows before you generate.

Make your own version

  1. warm 35mm color negative film look sets the whole feel of the shot. Swap it for another camera style to change the vibe.
  2. The prompt ends with no text. Leave that in, or the model may add random lettering.

Where this idea comes from

Inspired by an idea from @iamaiistudio, collected in Evolink-AI/awesome-gpt-image-2-API-Prompts under CC0 1.0. PopNow wrote this prompt and made the example above.

Portrait prompt guide

Why this portrait prompt works

A relaxed woman enjoys an alfresco Mediterranean meal bathed in soft, patterned sunlight. GPT Image 2.5 Sunburst renders this scene with realistic physical details, capturing natural linen folds, glassware refractions, and subtle vine shadows. The combination of candid table props and 35mm film color grading prevents the portrait from looking overly staged or artificial.

  1. Framing and wardrobe stylingVertical 4:5 portrait frame. Sun-drenched portrait of a woman in a loose white linen shirt

    This anchors the portrait orientation and dresses the subject in simple, breathable clothing that reflects sunlight naturally. Removing the linen shirt prompt often defaults to generic modern casual wear that breaks the rustic holiday aesthetic.

  2. Setting and table dressingat an outdoor lunch table under a grape vine, a lemon-print tablecloth,

    It establishes the terrace lunch environment and introduces vibrant Mediterranean yellow accents through the patterned cloth. Without the grape vine, the generator loses the canopy overhead necessary to cast believable leaf shadows.

  3. Lived-in narrative propsa half-finished plate of pasta and a glass of sparkling water,

    These candid table props give the scene a spontaneous, storytelling quality rather than a posed food advertisement. Omitting the half-eaten meal yields an empty, sterile tabletop that makes the portrait feel stiff.

  4. Lighting and facial expressiondappled vine shade falling across her smiling face,

    This instructs the model to paint broken, organic light patterns directly onto her facial features. Removing this phrase results in flat, uniform daylight that flattens her cheekbones and diminishes depth.

  5. Film texture and cleanupwarm 35mm color negative film look, relaxed summer mood, no text.

    It softens digital sharpness with nostalgic, golden-hour film grain while suppressing accidental typography on menu items or decor. Dropping the film reference makes the render look like a clean, overly polished digital snapshot.

Keeping the same face

To keep the same woman across multiple shots in this sunny dining set, nail down precise facial features and physical characteristics before generating.

Facial structure and age
Specify an exact age range and bone structure, such as a 32-year-old woman with high cheekbones and soft laugh lines, rather than the generic term woman.
Hair color and style
Define her hairstyle clearly, like chestnut brown wavy hair tied loosely with loose tendrils, to prevent the model from cycling between blonde bobs and dark curls.
Eye color and skin undertone
Add consistent skin descriptions such as warm olive skin with light freckles and hazel eyes to preserve coloration under varying dappled light.

Three ways to make it yours

Autumn Vineyard Lunch

Changes the subject to an older man with cozy knitwear in an autumn setting while preserving the dappled film portrait structure.

Prompt

Vertical 4:5 portrait frame. Sun-drenched portrait of an elderly man with a silver beard in a knitted oatmeal cardigan at an outdoor lunch table under an arbor, a rustic checkered tablecloth, a wooden board of cheese and a glass of red wine, dappled leaf shade falling across his smiling face, warm 35mm color negative film look, relaxed autumn mood, no text.

Courtyard Coffee Break

Swaps the subject and props for a morning cafe narrative with floral shadows and navy linen.

Prompt

Vertical 4:5 portrait frame. Sun-drenched portrait of a young man with dark curls in an open linen navy shirt at an outdoor cafe table under a bougainvillea trellis, a blue ceramic tabletop, a half-eaten croissant and a ceramic espresso cup, dappled floral shade falling across his smiling face, warm 35mm color negative film look, relaxed summer mood, no text.

Seaside Seafood Lunch

Features a middle-aged woman in coastal daylight with oceanfront tabletop elements.

Prompt

Vertical 4:5 portrait frame. Sun-drenched portrait of a woman in her forties with braided dark hair in a terracotta cotton blouse at an outdoor seaside table under a canvas canopy, a striped nautical tablecloth, a grilled fish plate and a glass of iced tea, dappled sunlight falling across her smiling face, warm 35mm color negative film look, relaxed coastal mood, no text.

Model and settings

Keep the aspect ratio at 4:5 to preserve the classic editorial vertical framing that flatters human portraits and tabletop depth. Set the quality to high so GPT Image 2.5 Sunburst cleanly resolves complex fine textures like wine glass bubbles, food crumbs, and linen weave. If you switch to landscape scenes or desktop wallpapers later, shift the ratio to 16:9 while leaving the high quality enabled.

  • FLUX.2 ProSwitch to FLUX.2 Pro when you want strict photoreal skin micro-textures and precise hex color control over the lemon prints and linen tones.
  • Seedream 5.0 ProChoose Seedream 5.0 Pro if you want to feed multiple reference photos of an actual person or specific tableware to build a continuous dining series.

If the portrait comes out wrong

Waxy or plastic-looking skin on the face under bright highlights.
Add subtle skin pores, realistic fine facial lines and ensure warm 35mm color negative film look remains to soften artificial digital smoothing.
Dappled shadows appearing as muddy dark smudges across the face.
Change dappled vine shade falling across her smiling face to soft, gentle dappled vine shade with clear facial highlights.
Malformed hands resting near the pasta plate or wine glass.
Add hands resting naturally on the table or adjust the framing prompt to bust portrait, hands out of frame to avoid hand artifacts completely.

Questions about this portrait prompt

How do I make the background look more blurred or cinematic?

Insert shallow depth of field, 85mm f/1.8 lens bokeh right before the film description. This keeps the subject and her immediate meal crisp while softly blurring distant patio foliage and scenery.

Why is the lemon pattern dominating the entire image?

The model can overapply patterns if left unchecked. Change a lemon-print tablecloth to a subtle white linen tablecloth with faint lemon edge embroidery to keep the focus squarely on the portrait.

Can I swap the white linen shirt for another outfit without breaking the light?

Yes, replace loose white linen shirt with another breathable natural fabric like sky-blue chambray shirt or sage-green cotton top. Keep the garment loose so dappled shadows still fall naturally across folds.