Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →One product across 16 studio setups, surfaces and lighting, each with the prompt, so you can shoot any product without a studio.
.claude/skills/whatsuppiyush-ai-product-photography/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | 33% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 35% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 34% | 0% |
| case-12 | ✗→✓ | ▲ Improved | 39% | 0% |
| case-15 | ✗→✓ | ▲ Improved | 34% | 0% |
You do not need a studio, a lightbox or a product to get a clean product shot any more. This guide holds one product (a frosted-glass perfume bottle) across 16 setups, surfaces and lighting styles, so you can see exactly what each one does. Copy a prompt, swap in your own product, and you have an e-commerce hero, a lifestyle shot or a luxury ad. Everything is model-agnostic: the same setup words work on 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 product formula
[product], product photography, on [surface], [background], [lighting], [mood], sharp focusAdd 'e-commerce' for clean catalogue shots, 'luxury advertisement' for dramatic ones, or a real setting for lifestyle. 'Sharp focus' and a named surface are what separate it from a flat render.
_Clean e-commerce hero_
A minimalist frosted-glass perfume bottle, product photography, on a pure white seamless studio background, soft even lighting, sharp focus, clean e-commerce catalogue shot_Marble & daylight_
A minimalist frosted-glass perfume bottle, product photography, on a white marble surface, soft daylight, elegant, minimalist_Neon luxury_
A minimalist frosted-glass perfume bottle, product photography, lit by coloured neon, dark moody reflective background, luxury_Natural lifestyle_
A minimalist frosted-glass perfume bottle, product photography, on a mossy rock in a forest, natural dappled light, organicStudio & catalogue
Lifestyle & natural
Luxury & dramatic
Product lighting
Finishing words
From God of Skills: a curated, hand-tested directory of AI skills, prompts, templates and image style guides. Source: https://godofskills.com/guides/ai-product-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-03 | fail→fail | 7,476 | 4,095 | -45% | 1 | 1 | 0% | 1,328 | 1,823 | +37% | 0 | 0 | — |
case-01 | fail→fail | 10,331 | 6,995 | -32% | 1 | 1 | 0% | 1,770 | 2,238 | +26% | 0 | 0 | — |
case-02 | fail→pass | 8,403 | 5,307 | -37% | 1 | 1 | 0% | 1,504 | 1,995 | +33% | 0 | 0 | — |
case-04 | pass→pass | 7,755 | 4,105 | -47% | 1 | 1 | 0% | 1,386 | 1,866 | +35% | 0 | 0 | — |
case-05 | pass→pass | 8,555 | 4,741 | -45% | 1 | 1 | 0% | 1,314 | 1,944 | +48% | 0 | 0 | — |
case-06 | pass→pass | 8,061 | 4,284 | -47% | 1 | 1 | 0% | 1,438 | 1,820 | +27% | 0 | 0 | — |
case-07 | pass→pass | 8,749 | 4,461 | -49% | 1 | 1 | 0% | 1,353 | 1,787 | +32% | 0 | 0 | — |
case-08 | fail→pass | 8,509 | 4,411 | -48% | 1 | 1 | 0% | 1,401 | 1,885 | +35% | 0 | 0 | — |
case-09 | pass→pass | 8,170 | 4,324 | -47% | 1 | 1 | 0% | 1,477 | 1,835 | +24% | 0 | 0 | — |
case-10 | pass→pass | 8,504 | 3,644 | -57% | 1 | 1 | 0% | 1,407 | 1,725 | +23% | 0 | 0 | — |
case-11 | fail→pass | 8,273 | 4,019 | -51% | 1 | 1 | 0% | 1,356 | 1,823 | +34% | 0 | 0 | — |
case-12 | fail→pass | 7,689 | 5,444 | -29% | 1 | 1 | 0% | 1,308 | 1,812 | +39% | 0 | 0 | — |
case-13 | pass→pass | 8,992 | 4,310 | -52% | 1 | 1 | 0% | 1,407 | 1,774 | +26% | 0 | 0 | — |
case-14 | pass→pass | 7,530 | 3,861 | -49% | 1 | 1 | 0% | 1,208 | 1,635 | +35% | 0 | 0 | — |
case-15 | fail→pass | 8,076 | 4,724 | -42% | 1 | 1 | 0% | 1,384 | 1,854 | +34% | 0 | 0 | — |
case-16 | pass→pass | 9,062 | 6,316 | -30% | 1 | 1 | 0% | 1,385 | 2,054 | +48% | 0 | 0 | — |
case-17 | pass→pass | 8,445 | 5,144 | -39% | 1 | 1 | 0% | 1,368 | 1,836 | +34% | 0 | 0 | — |
case-18 | pass→fail | 7,701 | 3,972 | -48% | 1 | 1 | 0% | 1,353 | 1,653 | +22% | 0 | 0 | — |
case-19 | pass→pass | 7,106 | 3,322 | -53% | 1 | 1 | 0% | 1,171 | 1,606 | +37% | 0 | 0 | — |
case-20 | pass→pass | 3,931 | 4,837 | +23% | 1 | 1 | 0% | 666 | 1,874 | +181% | 0 | 0 | — |
case-21 | pass→pass | 11,651 | 11,273 | -3% | 1 | 1 | 0% | 2,021 | 2,708 | +34% | 0 | 0 | — |
case-22 | pass→pass | 11,646 | 9,756 | -16% | 1 | 1 | 0% | 2,039 | 2,604 | +28% | 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 +18 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 | +14% |
| gemini-3.6-flash | verified | 8/6/2026 | +14% |
Other measured skills in the registry, with their headline benchmark lift.