The prompt
{
"category": "STUDIO_IPHONE_CANDID_AWKWARD_FRAMING",
"subject": {
"demographics": "Adult woman, 21-27, Turkish-looking, youthful vibe but adult.",
"hair": {
"color": "Dark brown",
"style": "Natural loose waves",
"texture": "Strands visible, slight flyaways"
},
"face": {
"eyes": "Bright, direct",
"skin_details": "High fidelity pores, no smoothing",
"makeup": "Clean natural"
},
"clothing": {
"outfit": "Simple black top (no logos)"
},
"accessories": {
"jewelry": ["Silver hoops"]
}
},
"pose": {
"type": "Close-up/half-body candid",
"orientation": "Slightly too-close crop, imperfect framing",
"hands": "One hand briefly in frame near hairline (fingers correct)",
"gaze": "Direct eye contact",
"expression": "Playful micro-smile"
},
"setting": {
"environment": "Plain studio wall",
"background_elements": [
"Subtle wall texture",
"No props"
],
"depth": "Face sharp, background soft"
},
"camera": {
"shot_type": "Phone-candid look in a clean space",
"angle": "Slightly above eye-level",
"focal_length_equivalent": "26mm phone feel",
"framing": "4:5 with awkward crop (slightly cutting hair/top space)",
"focus": "Eyes sharp"
},
"lighting": {
"source": "Soft diffused key light",
"direction": "Front/side gentle",
"quality": "Natural, not glossy"
},
"mood_and_expression": {
"tone": "Candid, playful, everyday",
"atmosphere": "Looks unplanned but still flattering"
},
"style_and_realism": {
"style": "Photoreal UGC",
"imperfections": "Tiny noise, imperfect composition"
},
"technical_details": {
"aspect_ratio": "4:5",
"noise": "Mild"
},
"constraints": {
"adult_only": true,
"no_text": true,
"no_logos": true,
"no_watermarks": true
},
"negative_prompt": [
"over-retouch", "beauty filter",
"plastic skin", "cgi",
"extra fingers", "warped hands",
"readable text", "logos", "watermark"
]
}
How to use this prompt
Copy the prompt above or click an "Open in" button to launch it directly in your preferred AI. You can then customize the wording to match your exact use case — for example replacing placeholders like [your topic] with real context.
Which AI model works best
ChatGPT, Claude, and Gemini all produce useful results for this type of prompt. Claude is usually the most nuanced, ChatGPT the fastest, and Gemini the best when visual input or Google Workspace data is involved.
How to customize this prompt
Adapt the prompt to your specific use case. Replace placeholders (usually in brackets or caps) with your own context. The more detail you provide, the more precise the response.
Common use cases
- Use directly in ChatGPT, Claude, or Gemini
- Adapt to your specific project or industry
- Use as a starting point for your own custom prompt
- Compare across models to find the best fit for your case
- Share with your team as a standard workflow
Variations
Adapt the tone (more casual, more technical), change the output format (bullet points vs. paragraphs), or add constraints (word limits, target audience).
Related prompts