mozgi ← All prompts
Cinematic: realism, man, night city
GPT Image 2.0

Realism, man, night city, night, hoodie

Prompt

Create a breathtaking surreal cinematic digital artwork of a young adult man with short dark hair floating horizontally above a massive high-rise city rooftop at night, as if weightless or gently falling backward. Use a dramatic low-angle wide shot with a slightly tilted camera, placing the figure large in the foreground from shoes to head, arms relaxed and spread outward, coat flaring in the air. He wears a long dark charcoal overcoat, gray hoodie, dark pants, and white Nike-style sneakers. The face should be covered by a soft rectangular blur/matte placeholder while the rest of the body remains sharply rendered. Surround him with hundreds of warm glowing paper sky lanterns rising into a deep blue star-filled sky; include exactly 7 prominent large lanterns: one cropped at the top right corner, one large on the upper left, one mid-large near the upper right, one cropped on the far right edge, one near the lower left edge, one near the lower right skyline, and one centered above the figure. Add many smaller lanterns receding into the distance like golden embers. In the background, show a dense modern city skyline with illuminated skyscraper windows, rooftop machinery, mist, and wet reflective rooftop tiles. Include a bright moon partly veiled by dramatic clouds in the upper-left sky. Lighting should be cinematic and high contrast, mixing cool moonlight and blue city tones with warm orange lantern glow reflecting on the wet rooftop. Style: ultra-detailed surreal photorealistic digital art, epic scale, magical realism, volumetric clouds, atmospheric haze, sharp foreground details, depth of field, 8k concept-art quality. Use vertical 3:4. Avoid text, logos as main focus, extra people, cartoon styling, daylight, or a visible watermark.
Open in catalog
The rights to this prompt belong to its author @AiWithTariq. You are responsible for any commercial use — promoting AI tools, aggregators or Telegram bots: mozgi.io accepts no liability. Details →
Model
GPT Image 2.0
Format
3/4
Author
@AiWithTariq
Original
x.com ↗

Similar prompts

All prompts for GPT Image 2.0

Copied