bytedance/seedance-2.5/text-to-video
Seedance 2.5 (Text-to-Video) generates Hollywood-grade cinematic videos from text prompts with native audio-visual synchronization, director-level camera and lighting control, and exceptional motion stability.
Examples
A young woman prepares breakfast inside a quiet modern apartment early in the morning. She casually opens the curtains and freezes: an enormous silent spacecraft is hovering between the nearby skyscrapers. Her coffee cup slowly lowers from her hand as sunlight reflects from the ship across the room. The camera begins with an intimate domestic shot, follows her toward the window, then pulls behind her shoulder into a massive exterior reveal. Grounded science fiction, realistic scale, quiet awe, cinematic morning light.
Try this prompt →Rainy night, neon-lit city street. A young man in a dark jacket, clearly visible in the center of the frame from the first second, walks toward the camera holding an old leather suitcase, rain dripping from his hair. He stops, looks behind him, and slowly lifts the lid; warm golden light spills out and lights up his surprised face. Slow push-in, cinematic 35mm film look, realistic reflections on wet asphalt, natural acting.
Try this prompt →Specs
Similar models
Prices are per render and charged from your balance only when a render succeeds. Failed renders are refunded automatically. Examples show what the model can do; your result depends on your prompt and settings.