Seedance 2.5 in Action: Generating Cinematic Shots with Image Prompts

techhalla · x · 2026-08-07

The author shares a complete workflow for generating high-octane videos using the Seedance 2.5 model. By providing an AI-generated photo as a character reference alongside a detailed cinematic prompt, it successfully locks the exact appearance of the character (bald, bearded, black sunglasses, hoodie).

The prompt specifies the scene (golden-hour sunset on a modern city street) and camera dynamics: a 0-1s intense low-angle medium close-up with a sedan barreling forward, transitioning into a 1-6s extreme super slow-motion shot. This demonstrates how to leverage reference images for consistent character generation across complex sequences.

Related event: Seedance 2.5 Generates 30-Second Continuous Action Scenes in One Go(4 posts)→

Original post →

More from Multimodal

Multimodal channel →