Grok Imagine Video is SpaceXAI's fast, text-, image-, and reference-conditioned video generation model. It produces short videos (1–15 seconds, 24 fps) at 480p or 720p across seven aspect ratios - 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, and 2:3.
The model supports three generation modes: text-to-video from a prompt alone, image-to-video that animates a still input, and reference-to-video that grounds the output in up to seven reference images for consistent characters, styles, or settings.
SpaceXAI: Grok Imagine Video 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 SpaceXAI: Grok Imagine Video 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 SpaceXAI: Grok Imagine Video 生成
目前无法通过 EU 区域内路由使用。 区域内路由文档