
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.
This is a GPT Image 2 prompt case for Portrait & Character. Use the copy-ready prompt below to generate similar visuals, and review Awesome GPT Image 2 Prompts attribution plus commercial-use rights before reuse.
Free 1K preview
Generate one preview image instantly, no sign-up required.
Prompt
Copy-ready prompt
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=10Prompt variables
Editable argument placeholders found in the prompt, with their default values.
Best for
- - Portrait & Character 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: Text to Image
- - 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.
More cases in this category
Prioritized by category, input mode compatibility, quality, and lower risk.






Reuse and source notes
Use this prompt safely after previewing the case.
- 1.Copy the prompt or open it directly in Dovoo with the generation button.
- 2.Adjust variables, aspect ratio, and reference images for your own use case.
- 3.Before publishing or paid usage, verify source rights, attribution requirements, and brand or likeness risks.
Can I use this prompt commercially?
Commercial-use status is allowed. Review the original source, license, brand constraints, and legal requirements before paid usage.
Where does this case come from?
This case is imported from Awesome GPT Image 2 Prompts; keep attribution visible and check the source URL before reuse.