Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →One model across 14 fashion-photography styles, from runway to streetwear to haute couture, each with the prompt.
.claude/skills/whatsuppiyush-ai-fashion-photography/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | 10% | 0% |
| case-12 | ✗→✓ | ▲ Improved | -12% | 0% |
| case-13 | ✗→✓ | ▲ Improved | 9% | 0% |
| case-14 | ✗→✓ | ▲ Improved | 12% | 0% |
| case-17 | ✗→✓ | ▲ Improved | 62% | 0% |
Fashion photography has as many looks as fashion itself. This guide holds one model across 14 fashion-photography styles, so the difference you see is the treatment, from a clean minimalist lookbook to a dramatic editorial to gritty street style. Copy a prompt, describe your own garment, and you have the shot. Works 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 fashion formula
[model + garment], fashion photography, [style], [setting], [lighting], [mood], sharp focusDescribe the garment in detail (fabric, cut, colour) since it is the subject. The style word (editorial / streetwear / couture) sets everything around it.
_Editorial vs street_
A fashion model wearing a stylish outfit, fashion photography, full body, high-fashion editorial, dramatic studio light, magazine, striking pose_Streetwear_
A fashion model in streetwear, urban street style photography, candid, city background, natural light_Runway_
A fashion model walking a runway, fashion show photography, dramatic runway lighting, motion_Minimalist lookbook_
A fashion model in a minimalist outfit, clean lookbook photography, neutral background, soft lightStudio & editorial
Street & real
Mood & era
From God of Skills: a curated, hand-tested directory of AI skills, prompts, templates and image style guides. Source: https://godofskills.com/guides/ai-fashion-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-01 | fail→fail | 12,278 | 7,075 | -42% | 1 | 1 | 0% | 1,895 | 1,794 | -5% | 0 | 0 | — |
case-02 | fail→fail | 12,161 | 4,903 | -60% | 1 | 1 | 0% | 1,918 | 1,495 | -22% | 0 | 0 | — |
case-03 | fail→fail | 11,801 | 5,198 | -56% | 1 | 1 | 0% | 1,685 | 1,516 | -10% | 0 | 0 | — |
case-04 | fail→pass | 10,958 | 7,165 | -35% | 1 | 1 | 0% | 1,669 | 1,829 | +10% | 0 | 0 | — |
case-05 | fail→fail | 7,472 | 5,382 | -28% | 1 | 1 | 0% | 1,203 | 1,594 | +33% | 0 | 0 | — |
case-06 | fail→fail | 6,190 | 5,337 | -14% | 1 | 1 | 0% | 993 | 1,581 | +59% | 0 | 0 | — |
case-07 | fail→fail | 9,059 | 5,666 | -37% | 1 | 1 | 0% | 1,363 | 1,617 | +19% | 0 | 0 | — |
case-08 | fail→fail | 8,832 | 5,096 | -42% | 1 | 1 | 0% | 1,409 | 1,534 | +9% | 0 | 0 | — |
case-09 | fail→fail | 9,987 | 6,545 | -34% | 1 | 1 | 0% | 1,766 | 1,764 | -0% | 0 | 0 | — |
case-10 | fail→fail | 9,291 | 3,734 | -60% | 1 | 1 | 0% | 1,384 | 1,325 | -4% | 0 | 0 | — |
case-11 | pass→fail | 9,824 | 4,661 | -53% | 1 | 1 | 0% | 1,454 | 1,421 | -2% | 0 | 0 | — |
case-12 | fail→pass | 12,327 | 6,397 | -48% | 1 | 1 | 0% | 1,962 | 1,728 | -12% | 0 | 0 | — |
case-13 | fail→pass | 9,079 | 4,762 | -48% | 1 | 1 | 0% | 1,392 | 1,514 | +9% | 0 | 0 | — |
case-14 | fail→pass | 10,983 | 6,014 | -45% | 1 | 1 | 0% | 1,473 | 1,645 | +12% | 0 | 0 | — |
case-15 | pass→pass | 9,037 | 4,064 | -55% | 1 | 1 | 0% | 1,523 | 1,366 | -10% | 0 | 0 | — |
case-16 | fail→fail | 11,002 | 7,648 | -30% | 1 | 1 | 0% | 1,739 | 1,998 | +15% | 0 | 0 | — |
case-17 | fail→pass | 7,141 | 6,917 | -3% | 1 | 1 | 0% | 1,215 | 1,968 | +62% | 0 | 0 | — |
case-18 | fail→pass | 13,608 | 5,445 | -60% | 1 | 1 | 0% | 2,323 | 1,676 | -28% | 0 | 0 | — |
case-19 | pass→pass | 9,873 | 6,690 | -32% | 1 | 1 | 0% | 1,582 | 1,842 | +16% | 0 | 0 | — |
case-20 | pass→pass | 9,926 | 7,550 | -24% | 1 | 1 | 0% | 1,642 | 1,894 | +15% | 0 | 0 | — |
case-21 | pass→pass | 10,637 | 5,188 | -51% | 1 | 1 | 0% | 1,887 | 1,464 | -22% | 0 | 0 | — |
case-22 | pass→pass | 9,908 | 5,918 | -40% | 1 | 1 | 0% | 1,485 | 1,671 | +13% | 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 +23 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 | 8/11/2026 | +36% |
| gemini-3.6-flash | verified | 8/6/2026 | +14% |
Other measured skills in the registry, with their headline benchmark lift.