PPQS
WILD CORPUS · github_awesome

PQS 54 (C) - prompt from raw.githubusercontent.com

Source: raw.githubusercontent.com · Scraped 2026-05-04 · Scored 2026-05-04

Score

C
54 / 80
gemma4:latest · local · pqs-v2.0 · canonical
Clarity9 / 10
Specificity10 / 10
Context9 / 10
Constraints9 / 10
Output format8 / 10
Role definition7 / 10
Examples1 / 10
CoT structure1 / 10

The prompt

{
 "title": "The Glass Doppelgänger",
 "description": "A high-octane psychological thriller scene where a woman is engaged in a visceral physical combat with her own sentient reflection emerging from a shattered surface.",
 "prompt": "You will perform an image edit using the provided photo to create a high-budget movie frame. The scene features the subject in a fierce life-or-death struggle against a supernatural mirror entity. The image must be Ultra-Photorealistic, utilizing cinematic lighting and highly detailed textures. The style is that of a blockbuster film, shot on Arri Alexa with a shallow depth of field to emphasize the intensity. Ensure realistic physics for the flying glass shards.",
 "details": {
 "year": "2025",
 "genre": "Cinematic Photorealism",
 "location": "A derelict, neon-lit dressing room with peeling wallpaper and a wall-sized vanity mirror that is shattering outwards.",
 "lighting": [
 "Volumetric stage lighting from above",
 "Flickering fluorescent buzz",
 "Dramatic rim lighting highlighting sweat and glass texture"
 ],
 "camera_angle": "Dynamic low-angle medium shot, slightly Dutch tilted to enhance the chaos.",
 "emotion": [
 "Ferocity",
 "Desperation",
 "Adrenaline"
 ],
 "color_palette": [
 "Electric cyan",
 "Gritty concrete grey",
 "Deep shadowy blacks",
 "Metallic silver"
 ],
 "atmosphere": [
 "Violent",
 "Surreal",
 "Claustrophobic",
 "Kinetic"
 ],
 "environmental_elements": "Thousands of micro-shards of glass suspended in the air (bullet-time effect), dust motes dancing in the light beams, overturned furniture.",
 "subject1": {
 "costume": "crop top, mini skirt",
 "subject_expression": "A primal scream of exertion, eyes wide with intensity.",
 "subject_action": "fighting with mirror"
 },
 "negative_prompt": {
 "exclude_visuals": [
 "cartoonish effects",
 "low resolution",
 "blurry textures",
 "static pose",
 "calm demeanor"
 ],
 "exclude_styles": [
 "3D render",
 "illustration",
 "painting",
 "anime"
 ],
 "exclude_colors": [
 "pastel pinks",
 "sunshine yellow"
 ],
 "exclude_objects": [
 "magical glowing orbs",
 "wands",
 "animals"
 ]
 }
 }
}

This prompt was scraped from a public source. The score reflects the input as written, not the quality of any output it produced. The AI input quality problem is the gap between what people type and what the model can act on.