One-Take Rainy Toll Booth: A Full AI Video Prompt for Korean Supernatural Mystery
umesh_ai · x · 2026-09-09
The author shares a complete prompt for AI video generation: a 30-second photorealistic Korean supernatural mystery sequence set at a remote mountain toll booth during heavy rain at 3 AM.
Key prompt techniques: demand one continuous unbroken shot with no cuts, no montage, no CCTV inserts, no teleporting camera; specify photorealistic live-action cinematography (realistic rain, wet asphalt reflections, practical fluorescent lighting, natural reactions, believable physics); keep supernatural surrealism subtle; and use negative instructions to exclude violence, gore, subtitles, watermarks, and an artificial CGI aesthetic. It opens with an epic establishing image: lightning revealing endless forested peaks above a tiny illuminated toll booth.
More from Multimodal
- Saudi dev crafts ChatGPT prompt for low-credit motion graphics, doable from a phone — aziz4ai · 2026-09-09
- Full text-to-video prompt template for raw found-footage alien planet vlogs — techhalla · 2026-09-09
- VoiceStudio open-sources a local ElevenLabs-style stack: voice clone, dubbing, 646 languages — thisguyknowsai · 2026-09-09
- OpenAI image-2.5 hands-on: sub-$0.01, 23s generations clearly beat Muse — tobowers · 2026-09-09
- GPT image model generates a 10-second GIF, sparking video-model takeover talk — rounak · 2026-09-09
- TapNow accuses influencer of stripping watermark to pass off signed artist's SD 2.5 AI film as rival product demo — TomLikesRobots · 2026-09-09