Seedance 2.5 prompt recreates a hood-mounted action cam demolition derby with first-frame consistency
techhalla · x · 2026-10-10
techhalla shared a copy-paste Seedance 2.5 text-to-video prompt for a raw county-fair demolition derby shot as if by an action camera bolted to the hood of a battered 1970s sedan.
- Camera setup: wide-angle lens with barrel distortion, the car stays rigidly fixed in frame while the arena lurches around it; dusk sodium floodlights, churned mud ringed with concrete blocks, packed grandstand, mud flecks on the lens, and rolling-shutter wobble on every impact.
- Consistency trick: use a provided image as the exact first frame and lock character and vehicle details from it — the driver (woman in her 30s with a dented red open-face helmet, goggles, dark braid, grease-stained coveralls), the sedan interior, roll cage, a rusty pickup, and a yellow taxi — maintained throughout.
- Audio design: unsilenced V8 screaming, crowd roar, and sheet metal crunching.
The author invites others to copy and tweak the prompt.
More from Multimodal
- ElevenLabs' Chimera pairs Eleven v4 voice with Seedance video to make character images speak — AIwithGhotai · 2026-10-23
- Open-Source Tennis Models Plus Claude Turn Video Into a World-Class Coach — tweetsatpreet · 2026-10-23
- Berkeley's StyleStream 2.0 cuts streaming voice conversion latency to 520ms, 2x faster — Berkeley · 2026-10-23
- AuroraTTS-100K: a sub-100K-parameter English TTS running 1120x real-time on GPU — Tall_Abrocoma_3533 · 2026-10-23
- FreeMatching turns an image generator into a generalizable dense correspondence matcher — kwangmoo_yi · 2026-10-23
- How Claude edits videos: jacob_posel shares his skill-based workflow — jacob_posel · 2026-10-23