Seedance 2.0 Fast 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 prioritizes generation speed and lower cost over maximum output quality. The number of tokens is given by (height of output video * width of output video * duration * 24) / 1024
ByteDance: Seedance 2.0 Fast の出力例の概要
- 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. — ByteDance: Seedance 2.0 Fast で生成
- テキストから動画: 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 — ByteDance: Seedance 2.0 Fast で生成
- テキストから動画 2: 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. — ByteDance: Seedance 2.0 Fast で生成
- Image + Audio to Video: Bring this storefront photo to life as a short ad, keeping its framing and the OpenRouter sign: a slow push-in at dusk as people stroll past, with the reference voiceover as narration. — ByteDance: Seedance 2.0 Fast で生成
現在、EU 域内ルーティングでは利用できません。 リージョン内ルーティングのドキュメント