Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →One portrait across 14 film stocks, so you can see exactly what each film's colour does, each with the prompt.
.claude/skills/whatsuppiyush-ai-film-stock-emulation/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 6% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 41% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 9% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 32% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 27% | 0% |
Naming a film stock is the fastest way to set a whole colour palette in one word. But most people only know 'Portra'. This guide holds one portrait across 14 film stocks, so you can see exactly what each film's colour science does, warm Kodak skin tones, punchy Fuji saturation, gritty black-and-white, neon-haloed CineStill night. Copy a prompt, add the stock name to anything, and you have the look. It goes deeper than the film-stock section of the DSLR guide. 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 film-stock formula
[your scene], shot on [film stock], [one or two of its traits]Add a trait or two to commit the model: 'shot on Kodak Portra 400, warm skin tones, fine grain'. The stock name does most of the work; the traits sharpen it.
_Warm vs punchy_
A portrait of a woman by a bright window, natural light, shot on Kodak Portra 400 film, warm soft skin tones, fine grain_CineStill 800T_
A portrait of a woman by a bright window, natural light, shot on CineStill 800T film, tungsten night tones, neon halation, cinematic_Kodak Tri-X 400_
A portrait of a woman by a bright window, natural light, shot on Kodak Tri-X 400 black and white film, rich grain, classic contrast_Fuji Velvia_
A portrait of a woman by a bright window, natural light, shot on Fujifilm Velvia film, ultra-saturated punchy colours, vividKodak colour
Black & white
Fuji & cinema
Retro & experimental
From God of Skills: a curated, hand-tested directory of AI skills, prompts, templates and image style guides. Source: https://godofskills.com/guides/ai-film-stock-emulation?ref=claude-skill
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-20 | pass→pass | 11,523 | 8,116 | -30% | 1 | 1 | 0% | 1,955 | 2,226 | +14% | 0 | 0 | — |
case-01 | fail→pass | 10,405 | 5,682 | -45% | 1 | 1 | 0% | 1,780 | 1,893 | +6% | 0 | 0 | — |
case-02 | fail→pass | 6,605 | 3,947 | -40% | 1 | 1 | 0% | 1,147 | 1,619 | +41% | 0 | 0 | — |
case-03 | fail→pass | 9,063 | 4,120 | -55% | 1 | 1 | 0% | 1,485 | 1,619 | +9% | 0 | 0 | — |
case-04 | fail→pass | 7,472 | 5,068 | -32% | 1 | 1 | 0% | 1,313 | 1,739 | +32% | 0 | 0 | — |
case-05 | fail→pass | 6,610 | 3,214 | -51% | 1 | 1 | 0% | 1,153 | 1,459 | +27% | 0 | 0 | — |
case-06 | fail→pass | 7,803 | 4,970 | -36% | 1 | 1 | 0% | 1,360 | 1,822 | +34% | 0 | 0 | — |
case-07 | pass→pass | 8,775 | 3,805 | -57% | 1 | 1 | 0% | 1,503 | 1,607 | +7% | 0 | 0 | — |
case-08 | fail→pass | 8,226 | 3,939 | -52% | 1 | 1 | 0% | 1,346 | 1,591 | +18% | 0 | 0 | — |
case-09 | pass→pass | 8,026 | 3,847 | -52% | 1 | 1 | 0% | 1,389 | 1,551 | +12% | 0 | 0 | — |
case-10 | fail→pass | 9,797 | 3,825 | -61% | 1 | 1 | 0% | 1,530 | 1,562 | +2% | 0 | 0 | — |
case-11 | fail→pass | 7,080 | 4,177 | -41% | 1 | 1 | 0% | 1,130 | 1,497 | +32% | 0 | 0 | — |
case-12 | fail→pass | 9,160 | 4,001 | -56% | 1 | 1 | 0% | 1,306 | 1,602 | +23% | 0 | 0 | — |
case-13 | fail→pass | 7,523 | 4,799 | -36% | 1 | 1 | 0% | 1,292 | 1,635 | +27% | 0 | 0 | — |
case-14 | fail→pass | 7,767 | 4,138 | -47% | 1 | 1 | 0% | 1,246 | 1,593 | +28% | 0 | 0 | — |
case-15 | pass→pass | 8,411 | 3,319 | -61% | 1 | 1 | 0% | 1,345 | 1,437 | +7% | 0 | 0 | — |
case-16 | pass→pass | 7,593 | 4,835 | -36% | 1 | 1 | 0% | 1,201 | 1,733 | +44% | 0 | 0 | — |
case-17 | pass→pass | 10,671 | 4,333 | -59% | 1 | 1 | 0% | 1,685 | 1,642 | -3% | 0 | 0 | — |
case-18 | fail→pass | 7,618 | 1,823 | -76% | 1 | 1 | 0% | 1,207 | 1,241 | +3% | 0 | 0 | — |
case-19 | pass→pass | 4,933 | 2,975 | -40% | 1 | 1 | 0% | 906 | 1,394 | +54% | 0 | 0 | — |
case-21 | pass→pass | 18,138 | 14,005 | -23% | 1 | 1 | 0% | 3,129 | 3,255 | +4% | 0 | 0 | — |
case-22 | pass→fail | 12,942 | 7,746 | -40% | 1 | 1 | 0% | 2,362 | 2,133 | -10% | 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 +55 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 | +48% |
| gemini-3.6-flash | verified | 8/6/2026 | +14% |
Other measured skills in the registry, with their headline benchmark lift.