Seedance 2.0 Fast text-to-video capability example: multi-shot rhythm and native audio
A 10-second short film vividly demonstrates the core capability combination of Seedance 2.0 Fast in the text-to-video scenario: through a single prompt describing a multi-shot sequence from "early-morning city to corner café," it checks whether the model can maintain scene and lighting continuity across shots within a single generation, while simultaneously producing ambient sound aligned with the visuals. base uses the author's real non-media input parameters: prompt is a shot-script-style description, duration is set to 10 seconds (the schema allows 4–15 seconds; documentation indicates a single generation is on the order of about 15 seconds), resolution 720p, aspect_ratio 16:9, generate_audio on, web_search off. This work does not use first frame, last frame, or multimodal reference materials, so the sole media input is empty; assets produce no reference images or reference videos, relying entirely on text-driven generation. Use case: before integrating this model, developers can observe multi-shot coherence, motion amplitude, and audio-visual synchronization quality under pure text input, as a comparative sample for prompt structure and duration/resolution trade-offs.
Style Cinematic · multi-shot · Text-to-Video
Model Seedance 2.0
Prompt
A cinematic 10-second multi-shot sequence generated entirely from text: the first shot, at dawn, the camera slowly pushes forward in an aerial move, over a mist-wrapped city skyline, warm orange light passing between the buildings; the second shot, switching to street level, a cyclist glides across a wet sidewalk, the ground carrying reflections, shallow depth of field; the third shot, the camera follows into a small corner café, steam rising from a cup, the door closing behind, soft window light. The shots maintain a consistent early-morning color tone, with filmic motion blur, slight handheld drift in the street shot, and a locked-off framing indoors. Ambient city hum and distant traffic transition into quiet café interior room tone, with synchronized sound effects matching the on-screen action. 16:9 widescreen, clean and natural look, no text overlays.
Copy the full prompt and adapt it for your own generation.
Tags