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 的示例输出摘要
- 文本生成视频: a slow cinematic push-in on a contemporary neighborhood storefront on a snowy winter evening at blue hour, a warm-white neon sign in flowing cursive reading "OpenRouter" above the entrance, snowflakes drifting through the golden window light, fresh snow on the awning, ledges and sidewalk, frost at the corners of the glass, a cozy interior of wood shelves and plants, a snow-dusted bicycle by the door, quiet street with no people, no holiday decorations — 使用 ByteDance: Seedance 2.0 Fast 生成
- 文本生成视频 2: 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 — 使用 ByteDance: Seedance 2.0 Fast 生成
- 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. — 使用 ByteDance: Seedance 2.0 Fast 生成
- 文本生成视频 3: 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. — 使用 ByteDance: Seedance 2.0 Fast 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. — 使用 ByteDance: Seedance 2.0 Fast 生成
目前无法通过 EU 区域内路由使用。 区域内路由文档