Lonely cry

{
  "image_description": {
    "subject": {
      "type": "Young woman",
      "appearance": {
        "hair": "Shoulder-length wavy brunette hair",
        "face": "Slightly flushed, wet with tears, light smokey eyes makeup, bold red lipstick",
        "expression": "Heartbreaking imploring gaze directed at the viewer, visible emotional weight",
        "physique": "Voluminous, firm, and large breasts, shapely legs, sensual and provocative posture"
      },
      "clothing": {
        "dress": "Extremely short white bodycon dress, strapless, sleeveless, sweetheart neckline that visibly struggles to contain her large bust",
        "footwear": "Red patent leather stiletto high heels"
      },
      "pose": "Full body standing shot, one hand resting on the hip, the other hand slightly tugging the hem of the short dress, alluring yet vulnerable stance"
    },
    "environment": {
      "setting": "Modern dimly lit living room",
      "foreground": "Intricate patterned Persian-style rug",
      "background": [
        "Grey fabric sofa with patterned cushions",
        "Dark wood coffee table with a glass of water and a candle",
        "Modern tripod floor lamp projecting soft shadows",
        "Dark bookshelf in the distance"
      ]
    },
    "technical_specs": {
      "angle": "Slightly low-angle shot to emphasize height and presence",
      "lighting": "Soft directional light from the left, deep shadows, subtle highlights on skin and dress fabric",
      "camera_style": "Photorealistic, cinematic photography",
      "lens_effects": "Shallow depth of field, blurred background (bokeh)",
      "quality": "8k resolution, natural film grain, highly detailed textures",
      "aspect_ratio": "9:16 (Vertical format)"
    }
  }
}

Run this prompt on a real model without leaving the page. Every run is saved to your history for this prompt.

How to use

1. 1Copy the prompt as-is — no variables required.
2. 2Paste it into ChatGPT, Claude, Gemini, or any capable model.
3. 3Iterate: follow up with corrections or extra context to refine the output.