ByteDance: Seedance 2.0
bytedance/seedance-2.0
Seedance 2.0 is a video generation model from ByteDance. It supports text-to-video, image-to-video with first and last frame control, and multimodal reference-to-video. It is particularly strong at preserving character consistency, visual style, and camera movement from reference material. The number of tokens is given by (height of output video * width of output video * duration * 24) / 1024
Example outputs summary for ByteDance: Seedance 2.0
- Text to Video: a slow cinematic push-in on a glowing neon sign that reads "OpenRouter" in the window of a cozy coffee shop on a rainy night, rain streaking down the glass, reflections rippling on wet pavement — generated with ByteDance: Seedance 2.0
- Image to Video: Bring this photo to life: a slow cinematic push-in on the storefront as its sign flickers warmly and people stroll past in the blue-hour dusk. — generated with ByteDance: Seedance 2.0
- Image + Audio to Video: Bring this storefront photo to life as a short ad: a slow push-in at dusk as people stroll past, with the reference voiceover as narration. — generated with ByteDance: Seedance 2.0
- Video to Video: Turn this scene into a snowy winter night: snow falling and settling on the sidewalk and bicycle, frost creeping across the windows, keeping the original camera move and the glowing OpenRouter sign. — generated with ByteDance: Seedance 2.0
Not currently available through EU in-region routing. In-region routing docs