Strawberry Milk Diner, made with GPT Image 2.5 Sunburst
Example made with GPT Image 2.5 Sunburst

Text to imageFashion

GPT Image 2.5 Sunburst fashion photo promptStrawberry Milk Diner

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

Prompt

Vertical 4:5 portrait frame. Two friends in matching cherry-red varsity jackets share a giant strawberry milkshake with two striped straws in a pale pink diner booth, one laughing with eyes closed, chrome napkin dispenser and a jukebox glow in the background, flash photography with a soft vintage film look, saturated candy colors, candid and fun, no readable 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. For a different mood, rewrite only the light: chrome napkin dispenser and a jukebox glow in the background.
  2. flash photography with a soft vintage film look sets the whole feel of the shot. Swap it for another camera style to change the vibe.
  3. The prompt ends with no readable text. Leave that in, or the model may add random lettering.

Portrait prompt guide

Why this portrait prompt works

Two companions sharing a strawberry milkshake inside a retro booth capture a lively, nostalgic fashion editorial aesthetic. The prompt balances tactile diner props with direct flash lighting to keep the subjects crisp against a warm interior backdrop. GPT Image 2.5 Sunburst renders the saturated reds and soft diner neon cleanly while preserving natural facial expressions and authentic vintage film grain.

  1. framing and wardrobe foundationVertical 4:5 portrait frame. Two friends in matching cherry-red varsity jackets

    It locks the vertical composition and establishes the shared collegiate style. Removing the jackets leaves wardrobe random, which weakens the synchronized retro fashion aesthetic.

  2. narrative centerpiece propshare a giant strawberry milkshake with two striped straws in a pale pink diner booth,

    This centers the interaction around a shared prop and defines the surrounding environment. Without the pink booth and milkshake, the models lose their physical interaction and diner context.

  3. expression and background depthone laughing with eyes closed, chrome napkin dispenser and a jukebox glow in the background,

    It breaks rigid portrait posing with an unposed reaction while adding classic diner set dressing behind them. Deleting the jukebox removes the colorful ambient glow behind the booth.

  4. lighting and stylistic finishflash photography with a soft vintage film look, saturated candy colors, candid and fun, no readable text.

    This commands the camera style to mimic direct on-camera flash with warm film grain while suppressing gibberish neon lettering on diner signage. Without it, lighting becomes flat digital studio light.

Keeping the same face

To maintain the same people across multiple diner scenes, define permanent physical traits and uniform garment accents that do not shift between generations.

Hairstyle and color specifications
Add explicit hair lengths, textures, and colors for both individuals so subsequent generations do not randomly swap between blonde, brunette, or curly hair.
Facial feature markers
Name distinct traits such as freckles across the nose, specific eye shapes, or strong cheekbone structure to anchor consistent facial geometry across different angles.
Varsity jacket lettering and trim
Specify exact patch letters, chest embroidery, and collar ribbing on the jackets so the matching clothing does not mutate into different outerwear designs between shots.

Three ways to make it yours

Mature retro couple

Adjusts the subjects to mature adults of South Asian heritage while keeping the diner setting and on-camera flash intact.

Prompt

Vertical 4:5 portrait frame. Two South Asian adults in their late thirties wearing matching cherry-red varsity jackets share a giant strawberry milkshake with two striped straws in a pale pink diner booth, one smiling broadly while resting a chin on hand, chrome napkin dispenser and a jukebox glow in the background, flash photography with a soft vintage film look, saturated candy colors, candid and fun, no readable text.

Bowling alley arcade

Shifts the backdrop from a booth to a retro bowling lane lounge while preserving the twin-jacket fashion styling and high-contrast flash.

Prompt

Vertical 4:5 portrait frame. Two friends in matching cherry-red varsity jackets share a tall cherry soda with two striped straws on a turquoise bowling alley bench, one laughing with head tilted back, glowing neon score monitors and bowling lanes in the background, flash photography with a soft vintage film look, saturated candy colors, candid and fun, no readable text.

Brothers diner hangout

Changes the duo to two Black men and swaps the booth color to pale mint to create contrast against the red outerwear.

Prompt

Vertical 4:5 portrait frame. Two Black male friends in matching cherry-red varsity jackets share a giant strawberry milkshake with two striped straws in a pale mint diner booth, one leaning forward with a joyful open laugh, chrome milkshake cups and a neon diner counter in the background, flash photography with a soft vintage film look, saturated candy colors, candid and fun, no readable text.

Model and settings

Keep the aspect ratio at 4:5, which matches standard editorial portrait framing and balances both seated subjects inside the booth. Set the generation quality to high so GPT Image 2.5 Sunburst correctly defines small details like striped straws, glass condensation, and jacket embroidery. If you want a wider diner establishing shot showing surrounding booths, switch the ratio to 16:9 while retaining the text-to-image mode.

  • Seedream 5.0 ProSwitch to Seedream 5.0 Pro if you want to upload existing photos of real people or specific jacket designs to maintain exact likenesses across multiple diner poses.
  • FLUX.2 ProChoose FLUX.2 Pro when you need precise control over the exact cherry-red and pastel pink color palette or want visible, authentic vintage diner signage rendered without distortion.

If the portrait comes out wrong

Faces appear unnaturally smooth, airbrushed, or plastic under the bright flash.
Insert natural skin texture, visible pores, and subtle film grain immediately after soft vintage film look in the prompt.
Hands resting near the glass display fused fingers or the straws merge together awkwardly.
Add hands resting flat on the table or remove manual grip by specifying both straws standing freely in the milkshake.
One jacket turns into a different garment or the red shades clash across the two subjects.
Replace matching cherry-red varsity jackets with identical wool cherry-red varsity jackets with white leather sleeves on both subjects.

Questions about this portrait prompt

Why are the neon diner signs in the background generating gibberish letters?

AI models frequently invent garbled letterforms when generating background cafe signage. The phrase no readable text in the prompt helps suppress messy lettering, but you can also replace glowing signs with softly blurred jukebox lighting to eliminate unreadable text entirely.

How do I stop both jackets from looking completely different?

When prompting two subjects, models can split costume details unevenly. Explicitly write identical twins of cherry-red varsity jackets with cream leather sleeves so the model applies the exact same materials, trims, and colors across both people.

Can I add a third friend to this diner booth setup?

Yes, but expand the scene description to three friends squeezed into a corner diner booth and consider switching your aspect ratio to horizontal. A vertical 4:5 frame often cramps three seated figures, causing faces or jackets to blend together.