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 Fast의 예시 출력 요약
- Text to video (Snowy night): 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 — ByteDance: Seedance 2.0 Fast으로 생성
- Text to video (Rainy night): 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 Fast으로 생성
- 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 Fast으로 생성
- 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. — ByteDance: Seedance 2.0 Fast으로 생성
- Image and 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 Fast으로 생성
현재 EU 역내 라우팅을 통해 사용할 수 없습니다. 리전 내 라우팅 문서