The Last Adagio

{
  "title": "The Last Adagio",
  "description": "A hauntingly beautiful scene of a solitary ballerina performing in a flooded, abandoned grand library.",
  "prompt": "You will perform an image edit using the provided subject. Transform Subject 1 (female) into a survivor in a post-apocalyptic world. She is in a massive, decaying library where the floor is flooded with water. Light spills through the collapsed ceiling, illuminating dust motes and water reflections. The image must be photorealistic, utilizing cinematic lighting, highly detailed textures, shot on Arri Alexa with a shallow depth of field to focus on the subject while the background falls into soft bokeh.",
  "details": {
    "year": "Post-Collapse Era",
    "genre": "Cinematic Photorealism",
    "location": "A grand, abandoned library with towering shelves, crumbling architecture, and a floor flooded with still, reflective water.",
    "lighting": [
      "God rays entering from a collapsed roof",
      "Soft reflected light from the water",
      "High contrast cinematic shadows"
    ],
    "camera_angle": "Low angle, wide shot, capturing the reflection in the water.",
    "emotion": [
      "Melancholic",
      "Graceful",
      "Solitary"
    ],
    "color_palette": [
      "Desaturated concrete greys",
      "Muted teal water",
      "Vibrant crimson",
      "Dusty gold light"
    ],
    "atmosphere": [
      "Ethereal",
      "Lonely",
      "Quiet",
      "Majestic"
    ],
    "environmental_elements": "Floating pages from old books, dust particles dancing in light shafts, ripples in the water.",
    "subject1": {
      "costume": "A distressed, dirty white ballet leotard paired with pristine red gloves.",
      "subject_expression": "Serene, eyes closed, lost in the movement.",
      "subject_action": "dancing"
    },
    "negative_prompt": {
      "exclude_visuals": [
        "bright sunshine",
        "clean environment",
        "modern technology",
        "spectators"
      ],
      "exclude_styles": [
        "cartoon",
        "painting",
        "sketch",
        "3D render"
      ],
      "exclude_colors": [
        "neon green",
        "bright orange"
      ],
      "exclude_objects": [
        "cars",
        "animals",
        "phones"
      ]
    }
  }
}

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.