mozgi ← All prompts
Nighttime Japanese horror city: a man under a store awning gazes at a creepy reflection, wet streets, warped buildings
GPT Image 2.0

Nighttime Japanese horror city: a man under a store awning gazes at a creepy reflection, wet streets, warped buildings

Prompt

A cinematic Japanese psychological horror game screenshot at night, shown from a third-person over-the-shoulder perspective behind a young man wearing a dark hooded jacket, standing under a convenience store awning and staring into a large front window. In the glass, instead of a normal reflection, there is a terrifying humanoid figure with an unnaturally elongated oval head, long straight black hair hanging down both sides, a pale expressionless face, and a dark coat, standing directly opposite him. Beyond the reflection is a wet urban street in Japan with glossy rain-soaked asphalt, sparse pedestrians holding umbrellas, dim storefronts, vending machines, parking signs, and tall buildings bending inward in a surreal warped perspective toward a dark swirling vortex in the sky at the end of the street. The convenience store window ledge displays exactly 5 visible magazine covers lined up side by side and exactly 8 instant food items or cup noodles stacked on the lower right. Add subtle in-game UI text in Japanese: exactly 2 objective lines in the upper left, and exactly 2 small action prompts in the lower left. Include readable Japanese street posters and shop signs, such as a large red staff recruitment sign on the upper right and a yellow points campaign sign on the lower right. Lighting is extremely dark, moody, and realistic, with reflections, deep shadows, damp textures, and a faint cold glow from interior lights and street lamps. Style: ultra-realistic survival horror video game, unsettling, grounded, detailed, cinematic, high contrast, eerie silence, no exaggerated action, no bright colors.
Open in catalog
The rights to this prompt belong to its author @hanagasa_ai. 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
3/2
Author
@hanagasa_ai
Original
x.com ↗

Similar prompts

All prompts for GPT Image 2.0

Copied