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 の出力例の概要
- 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 — SpaceXAI: Grok Imagine Video で生成
- 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 — SpaceXAI: Grok Imagine Video 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