Hyper-realistic top-down selfie giant city AI Image Prompt
Hyper-realistic cinematic selfie photography, 9:16 aspect ratio. A {argument name="subject" default="woman"} takes a selfie from an extreme top-down angle looking directly downward. One arm fully extended upward toward the camera (arm clearly visible in frame, no camera device visible), the other arm extended forward holding a {argument name="foreground camera" default="Canon camera"} as the dominant foreground element. Natural and relaxed facial expression, slight head tilt toward the selfie camera. Full body visible from head to toe, feet touching the ground. Forced perspective: the woman appears gigantic, with {argument name="background scale" default="city buildings"} reaching only to her knees, yet the scale feels physically believable. Urban intersection, pedestrian crosswalk, road markings, traffic signs, cars, bicycles, and pedestrians at normal human scale in the background. Natural daylight, clear sky, soft realistic shadows. No fantasy lighting. Maximum photorealism. Clear depth separation: Canon camera foreground, face, full body, city background. No AI-art look, no plastic skin, no facial distortion, no extra limbs, no text or watermarks.
Content: Subject (woman) + extreme top-down selfie angle + arm extended toward camera + other hand holding camera as foreground + forced perspective (giant scale) + city street background + natural daylight + hyper-realistic cinematic look + 9:16 vertical composition
Pros: Clear forced perspective with believable physical scale; well-defined depth separation between foreground, middle ground, and background.
Cons: Complex arm and camera positioning under extreme angle may be hard to generate accurately; forced perspective demands precise subject-background match to avoid scale inconsistency.
Reference image: No obvious reference-image dependency
Source materials are collected from publicly accessible web pages. Contact us if a rights issue needs review. Copyright & Privacy