Elevator Mirror OOTD (full-body)

Extrem detaillierter JSON-Prompt für realistische Ganzkörper-Spiegelselfies im „Outfit of the Day“-Stil.

Der Prompt

{
  "category": "ELEVATOR_MIRROR_OOTD",
  "subject": {
    "demographics": "Adult woman, 21-27, Turkish-looking.",
    "hair": {
      "color": "Dark brown",
      "style": "Low ponytail or loose waves, casually arranged",
      "texture": "Real strands, slight frizz, flyaways present",
      "movement": "Hair rests naturally over coat collar"
    },
    "face": {
      "shape": "Soft oval",
      "eyes": "Expressive, natural catchlights",
      "nose": "Defined bridge",
      "lips": "Soft natural tint",
      "skin_details": "Pores visible, natural tone variation",
      "micro_details": "Baby hairs visible near temples"
    },
    "body_proportions": {
      "build": "Natural, fit",
      "posture": "Relaxed confident stance"
    },
    "clothing": {
      "outerwear": "Tailored long coat (no logos)",
      "inner": "Minimal top",
      "bottom": "Straight pants or jeans",
      "shoes": "Clean sneakers or ankle boots (no branding)",
      "texture": "Fabric weave visible; slight wrinkles at elbows"
    },
    "accessories": {
      "bag": "Small shoulder bag (no logos)",
      "jewelry": ["Small silver hoops"]
    }
  },
  "pose": {
    "type": "Full-body mirror selfie (phone not shown directly; mirror reflection implied)",
    "orientation": "Standing slightly angled",
    "head_position": "Chin slightly down, casual",
    "limbs": "One hand adjusting coat cuff; other hand relaxed near bag strap",
    "legs": "One knee slightly bent, weight shifted to one hip",
    "gaze": "Looking at mirror reflection, calm confident"
  },
  "setting": {
    "environment": "Elevator interior",
    "background_elements": [
      "Brushed metal walls",
      "Soft overhead panel lighting",
      "Subtle fingerprints/smudges on mirror for realism"
    ],
    "depth": "Everything fairly clear; slight background softness"
  },
  "camera": {
    "shot_type": "Full-body mirror shot",
    "angle": "Slight downward tilt typical of handheld",
    "focal_length_equivalent": "24-28mm wide",
    "framing": "4:5 IG feed, full body visible",
    "focus": "Face readable, outfit sharp, minimal distortion"
  },
  "lighting": {
    "source": "Overhead elevator lights",
    "direction": "Top-down soft but slightly harsh (realistic elevator look)",
    "highlights": "Metal reflections controlled",
    "shadows": "Soft shadows under chin, coat folds",
    "quality": "Everyday realistic"
  },
  "mood_and_expression": {
    "tone": "Minimalist chic, confident",
    "expression": "Neutral with micro-smile",
    "atmosphere": "Candid commute vibe"
  },
  "style_and_realism": {
    "style": "Photoreal social",
    "fidelity": "Fabric texture, metal reflections realistic",
    "imperfections": "Slight noise, imperfect framing"
  },
  "technical_details": {
    "aspect_ratio": "4:5",
    "noise": "Mild",
    "sharpness": "Face + outfit crisp"
  },
  "constraints": {
    "adult_only": true,
    "no_text": true,
    "no_logos": true,
    "no_watermarks": true,
    "single_subject_only": true
  },
  "negative_prompt": [
    "mirror glitches", "double reflections", "warped elevator",
    "extra limbs", "bad hands", "plastic skin",
    "readable text", "logos", "watermark",
    "cgi", "cartoon", "anime"
  ]
}

So nutzt du es

Den Prompt-Text kopieren (Button oben) und als System-Prompt bzw. erste Nachricht in ChatGPT, Claude oder einem lokalen Modell einfügen. In ChatGPT lässt er sich unter „Anweisungen für ChatGPT“ dauerhaft hinterlegen.

Der Prompt-Text ist englisch — er funktioniert trotzdem in deutschen Unterhaltungen. Für deutsche Antworten einfach am Ende ergänzen: „Antworte auf Deutsch.“

Im Detail

Dieser Prompt nutzt eine strukturierte JSON-Vorlage, um KI-Bildgeneratoren präzise über Demografie, Haar, Gesichtsdetails, Körperhaltung und Kleidung zu steuern – inklusive kleiner Realismus-Marker wie Poren, Flyaways oder Baby-Hairs. Das Format eignet sich für Fotografen, Mode-Content-Creator oder Marketer, die konsistente, fotorealistische Charakterbilder für Kampagnen oder Social-Media-Feeds erzeugen wollen, ohne jedes Detail neu in Fließtext zu formulieren. Der Vorteil gegenüber einfachen Text-Prompts: Die feste Struktur lässt sich leicht kopieren und für andere Szenen oder Charaktere anpassen, was Wiederholbarkeit und Kontrolle erhöht.

Praxis-Tipp

Kopiere die JSON-Struktur als Vorlage und ändere nur einzelne Felder (z. B. “hair.color” oder “clothing.outerwear”), um Variationen desselben Looks konsistent zu erzeugen.

Lizenz & Quelle

• Lizenz: CC0-1.0 (Public Domain)
• Quelle: awesome-chatgpt-prompts (GitHub)

Lade …