Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →12 food-photography styles, from dark-and-moody to bright-and-airy to flat-lay, each with the prompt.
.claude/skills/whatsuppiyush-ai-food-photography/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-15 | ✗→✓ | ▲ Improved | 18% | 0% |
| case-01 | ✗→✓ | ▲ Improved | 11% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 128% | 0% |
| case-08 | ✗→✓ | ▲ Improved | -3% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 28% | 0% |
Food photography is a genre with its own rules: it is mostly about light, styling and angle. This guide covers the 12 approaches that actually sell food, from the dark-and-moody restaurant look to the bright-and-airy brunch look to the overhead flat-lay. Copy a prompt, swap in your dish, and you have a menu hero, a delivery-app thumbnail or a recipe-blog shot. Model-agnostic across Midjourney, GPT Image, Flux and Nano Banana.
Works in: Midjourney, GPT Image, Flux, Nano Banana, Stable Diffusion.
When the user asks for an image prompt in this style, compose one using the formulas and vocabulary below. Fill each slot with a concrete choice, then return the finished prompt. Prefer naming a real camera/lens, a light, and a colour or film treatment, which is what makes the output read as a real photograph rather than an AI render.
The food formula
[dish], food photography, [lighting style], [angle], [freshness cue], appetising, sharp focusThe lighting style does most of the work: 'dark moody side light' vs 'bright airy natural light'. The freshness cue (steam, splash, condensation) is what makes it look real rather than plastic.
_The restaurant look_
A rustic bowl of pasta, food photography, dark moody dramatic side light, deep shadows, rustic table, steam, appetising, sharp focus_Dark & moody_
A rustic bowl of pasta, dark moody food photography, dramatic single side light, deep shadows, rustic table_Bright & airy_
A stack of pancakes with berries and syrup, bright and airy food photography, soft natural window light, white marble_Overhead flat-lay_
A colourful grain bowl, overhead flat-lay food photography, styled ingredients around it, soft even lightThe three core looks
Setting & mood
Appetite cues
From God of Skills: a curated, hand-tested directory of AI skills, prompts, templates and image style guides. Source: https://godofskills.com/guides/ai-food-photography?ref=claude-skill
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-14 | pass→pass | 10,462 | 6,481 | -38% | 1 | 1 | 0% | 1,619 | 1,768 | +9% | 0 | 0 | — |
case-15 | fail→pass | 8,580 | 6,249 | -27% | 1 | 1 | 0% | 1,524 | 1,796 | +18% | 0 | 0 | — |
case-01 | fail→pass | 9,901 | 6,464 | -35% | 1 | 1 | 0% | 1,638 | 1,826 | +11% | 0 | 0 | — |
case-02 | fail→fail | 9,302 | 5,734 | -38% | 1 | 1 | 0% | 1,639 | 1,784 | +9% | 0 | 0 | — |
case-03 | pass→pass | 8,412 | 5,779 | -31% | 1 | 1 | 0% | 1,477 | 1,755 | +19% | 0 | 0 | — |
case-04 | pass→pass | 17,168 | 14,545 | -15% | 1 | 1 | 0% | 2,967 | 3,181 | +7% | 0 | 0 | — |
case-05 | pass→pass | 19,776 | 15,595 | -21% | 1 | 1 | 0% | 3,134 | 3,325 | +6% | 0 | 0 | — |
case-06 | pass→pass | 4,743 | 2,925 | -38% | 1 | 1 | 0% | 836 | 1,301 | +56% | 0 | 0 | — |
case-07 | fail→pass | 3,504 | 4,014 | +15% | 1 | 1 | 0% | 629 | 1,434 | +128% | 0 | 0 | — |
case-08 | fail→pass | 9,089 | 4,913 | -46% | 1 | 1 | 0% | 1,573 | 1,533 | -3% | 0 | 0 | — |
case-09 | pass→pass | 6,402 | 5,793 | -10% | 1 | 1 | 0% | 1,091 | 1,740 | +59% | 0 | 0 | — |
case-10 | fail→fail | 8,458 | 5,365 | -37% | 1 | 1 | 0% | 1,526 | 1,583 | +4% | 0 | 0 | — |
case-11 | fail→pass | 8,722 | 5,638 | -35% | 1 | 1 | 0% | 1,290 | 1,650 | +28% | 0 | 0 | — |
case-12 | pass→pass | 8,385 | 5,627 | -33% | 1 | 1 | 0% | 1,491 | 1,645 | +10% | 0 | 0 | — |
case-13 | pass→pass | 7,816 | 4,085 | -48% | 1 | 1 | 0% | 1,317 | 1,450 | +10% | 0 | 0 | — |
case-16 | pass→pass | 6,899 | 5,777 | -16% | 1 | 1 | 0% | 1,185 | 1,696 | +43% | 0 | 0 | — |
case-17 | fail→pass | 8,790 | 5,499 | -37% | 1 | 1 | 0% | 1,448 | 1,651 | +14% | 0 | 0 | — |
case-18 | pass→pass | 8,385 | 4,955 | -41% | 1 | 1 | 0% | 1,340 | 1,570 | +17% | 0 | 0 | — |
case-19 | pass→pass | 9,151 | 6,155 | -33% | 1 | 1 | 0% | 1,642 | 1,769 | +8% | 0 | 0 | — |
case-20 | pass→pass | 9,065 | 4,506 | -50% | 1 | 1 | 0% | 1,499 | 1,524 | +2% | 0 | 0 | — |
case-21 | pass→pass | 8,248 | 5,611 | -32% | 1 | 1 | 0% | 1,296 | 1,718 | +33% | 0 | 0 | — |
case-22 | fail→fail | 5,393 | 4,552 | -16% | 1 | 1 | 0% | 871 | 1,484 | +70% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +27 percentage points is the difference between those two pass rates over the 22 comparable cases. 1 case got worse with the skill loaded, and it is included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
| Model | Method | Date | Lift |
|---|---|---|---|
| gemini-3.6-flash | verified | 8/9/2026 | +22% |
| gemini-3.6-flash | verified | 8/6/2026 | +50% |
Other measured skills in the registry, with their headline benchmark lift.