Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →16 kinds of portrait, from corporate headshot to editorial to cinematic, each with the prompt.
.claude/skills/whatsuppiyush-ai-portrait-styles/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-07 | ✗→✓ | ▲ Improved | 10% | 0% |
| case-08 | ✗→✓ | ▲ Improved | -1% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 2% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 14% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 7% | 0% |
"Portrait" covers everything from a clean LinkedIn headshot to a moody neon-lit editorial. This guide is the 16 kinds of portrait, so you can pick the one that fits the job, not just the model's best guess. It is the companion to the DSLR photography guide: that one teaches the camera and lens craft, this one is the styles you point it at. Copy a prompt, swap in your subject, done. 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 portrait formula
[subject], [portrait style], [lighting], [background], [mood], sharp focus, natural skin texture'Natural skin texture' fights the plastic AI-skin look on any portrait. The style word (corporate / editorial / beauty / cinematic) sets everything else.
_The professional headshot_
A portrait of a woman with dark hair, clean corporate headshot, neutral grey background, soft even lighting, friendly, sharp focus, natural skin texture_Black & white_
A portrait of a woman with dark hair, black and white portrait, dramatic contrast, timeless_Neon night_
A portrait of a woman with dark hair, neon night portrait, coloured city light, moody, urban, cinematic_Golden hour_
A portrait of a woman with dark hair, golden hour portrait, warm backlight, natural, dreamyProfessional & clean
Dramatic & moody
Creative & mood
From God of Skills: a curated, hand-tested directory of AI skills, prompts, templates and image style guides. Source: https://godofskills.com/guides/ai-portrait-styles?ref=claude-skill
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-07 | fail→pass | 8,042 | 3,996 | -50% | 1 | 1 | 0% | 1,371 | 1,511 | +10% | 0 | 0 | — |
case-08 | fail→pass | 9,844 | 5,126 | -48% | 1 | 1 | 0% | 1,691 | 1,680 | -1% | 0 | 0 | — |
case-01 | fail→fail | 10,971 | 5,158 | -53% | 1 | 1 | 0% | 1,782 | 1,685 | -5% | 0 | 0 | — |
case-02 | fail→pass | 11,369 | 6,586 | -42% | 1 | 1 | 0% | 1,972 | 2,010 | +2% | 0 | 0 | — |
case-03 | fail→pass | 9,367 | 5,137 | -45% | 1 | 1 | 0% | 1,465 | 1,675 | +14% | 0 | 0 | — |
case-04 | fail→pass | 10,065 | 4,806 | -52% | 1 | 1 | 0% | 1,543 | 1,647 | +7% | 0 | 0 | — |
case-05 | pass→fail | 9,304 | 4,580 | -51% | 1 | 1 | 0% | 1,603 | 1,694 | +6% | 0 | 0 | — |
case-06 | fail→pass | 7,943 | 4,722 | -41% | 1 | 1 | 0% | 1,320 | 1,597 | +21% | 0 | 0 | — |
case-09 | fail→pass | 8,242 | 4,489 | -46% | 1 | 1 | 0% | 1,368 | 1,587 | +16% | 0 | 0 | — |
case-10 | fail→pass | 8,121 | 4,697 | -42% | 1 | 1 | 0% | 1,388 | 1,528 | +10% | 0 | 0 | — |
case-11 | fail→fail | 9,764 | 4,253 | -56% | 1 | 1 | 0% | 1,667 | 1,545 | -7% | 0 | 0 | — |
case-12 | fail→fail | 7,733 | 3,664 | -53% | 1 | 1 | 0% | 1,264 | 1,506 | +19% | 0 | 0 | — |
case-13 | fail→pass | 8,138 | 4,840 | -41% | 1 | 1 | 0% | 1,275 | 1,637 | +28% | 0 | 0 | — |
case-14 | fail→pass | 8,421 | 3,852 | -54% | 1 | 1 | 0% | 1,373 | 1,465 | +7% | 0 | 0 | — |
case-15 | fail→pass | 8,671 | 5,095 | -41% | 1 | 1 | 0% | 1,491 | 1,613 | +8% | 0 | 0 | — |
case-16 | fail→pass | 10,258 | 5,840 | -43% | 1 | 1 | 0% | 1,524 | 1,707 | +12% | 0 | 0 | — |
case-17 | fail→pass | 8,002 | 5,200 | -35% | 1 | 1 | 0% | 1,214 | 1,647 | +36% | 0 | 0 | — |
case-18 | fail→pass | 9,325 | 3,435 | -63% | 1 | 1 | 0% | 1,423 | 1,301 | -9% | 0 | 0 | — |
case-19 | fail→pass | 8,291 | 4,062 | -51% | 1 | 1 | 0% | 1,508 | 1,527 | +1% | 0 | 0 | — |
case-20 | pass→pass | 10,482 | 10,446 | -0% | 1 | 1 | 0% | 1,910 | 2,560 | +34% | 0 | 0 | — |
case-21 | pass→pass | 6,724 | 5,348 | -20% | 1 | 1 | 0% | 1,084 | 1,676 | +55% | 0 | 0 | — |
case-22 | pass→pass | 16,368 | 14,882 | -9% | 1 | 1 | 0% | 2,658 | 3,029 | +14% | 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 +64 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 | 8/10/2026 | +41% |
| gemini-3.6-flash | verified | 8/6/2026 | +18% |
Other measured skills in the registry, with their headline benchmark lift.