
Candid Late-Night Kitchen Snapshots
A prompt designed to generate realistic, candid-style smartphone photos of a person looking for snacks in a refrigerator late at night.
Dette er et GPT Image 2 -eksempel på en prompt for Portræt og karakter . Brug den kopieringsklare prompt nedenfor til at generere lignende visuelle elementer, og gennemgå Awesome GPT Image 2 Prompts -kreditering samt kommercielle brugsrettigheder før genbrug.
Free 1K preview
Generate one preview image instantly, no sign-up required.
Hurtig
Klar til kopiering
A vertical realistic smartphone snapshot of a residential kitchen late at night. An adult woman is opening the refrigerator looking for food; the overall feel is like a life moment suddenly captured by a roommate standing nearby.
{argument name="subject" default="Random number of people, random positions, random fridge contents, random actions, and random camera angles; the character might be squatting to rummage through the fridge, bending over to check, staring blankly with a drink, looking back at the camera, blocking the fridge light with a hand, or holding a pile of snacks."}
Random camera angles: interior fridge perspective, ultra-close-up wide angle, low angle, side-rear snapshot, door gap obstruction, half-face crop, overexposed fridge light, mirror reflections, slight motion blur; randomly selected.
The fridge randomly contains {argument name="items" default="drinks, leftovers, eggs, plastic containers, sauces, half a watermelon, takeout boxes, ziplock bags, strange snacks"}; each image highlights only a few realistic items.
The kitchen background randomly features a sink, trash can, magnetic stickers, dining table, unorganized shopping bags, washed cups, or hanging towels.
The cool white light from the fridge is the main light source, surrounding environment is dark, realistic smartphone auto-exposure, partial high exposure on the character's face, slight noise and compression, true-to-life texture.
Key focus: randomization of fridge contents, character actions, camera positions, and expressions; a slightly absurd but reasonable object is allowed, maintaining overall realism.
Signature in bottom left: '● DeepBlue'.
n=10Promptvariabler
Redigerbare argumentpladsholdere fundet i prompten med deres standardværdier.
Best for
- - Portræt 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: Tekst til billede
- - 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 sager i denne kategori
Prioriteret efter kategori, kompatibilitet med inputtilstande, kvalitet og lavere risiko.






Genbrug og kildenoter
Brug denne prompt sikkert efter at have gennemgået sagen.
- 1.Kopier prompten, eller åbn den direkte i Dovoo med genereringsknappen.
- 2.Juster variabler, billedformat og referencebilleder til din egen brug.
- 3.Før udgivelse eller betalt brug skal du verificere kilderettigheder, krav til kreditering og risici forbundet med branding eller lighed.