Full Prompt Revealed for Seedance 2.5 Flash's Two-Image Fight Scene Generation
aziz4ai · x · 2026-11-16
Following up on the Seedance 2.5 flash (Dreamina) fight video generated from 2 random images, the author shared the full prompt. Key techniques:
- Opening: "Begin IMMEDIATELY in the middle of an explosive close-range fight" — explicitly banning introductions, staring, or slow buildup
- Action detail: Bruce Lee-inspired rapid strikes, spinning kicks, elbows, knees, blocks, counters, throws and acrobatic evasions, with authentic martial-arts mechanics and physical weight
- A structured "ESCALATING ACTION CHOREOGRAPHY" section: the fighter in green counterattacks fiercely before being overwhelmed by superior speed and precision, escalating to near-superhuman spectacle
This "start in medias res + staged escalation" prompt structure transfers well to other action video generation.
Related event: Seedance 2.5 Flash Turns Two Random Images into Kung Fu Fight(2 posts)→
More from Multimodal
- Seedance 2.5 Flash Generates Intense Fight Scene From Just 2 Random Images — aziz4ai · 2026-11-16
- Runway CEO Predicts Fully AI-Generated Cultural Phenomenon by 2027 — c_valenzuelab · 2026-11-16
- Stunning AI-generated motion-blur portraits with a film-photography feel — azed_ai · 2026-11-16
- A Bauhaus functionalist prompt template for geometric poster-style AI art — LudovicCreator · 2026-11-16
- Vivix W1 video model: 100 ten-second ads for about $5 at $0.005 per second — Aiden_Tech_Ai · 2026-11-16
- User Shares Coral Reef Creation Labeled 'Qwen 4 Max (xhigh)', an Unannounced Model Name — intellectronica · 2026-11-16