MODEL ID xai:grok-imagine@video
live

Grok Imagine Video

xAI
by xAI

Grok Imagine Video is a multimodal generative video model that produces short video clips with native audio from text descriptions or static images. It supports text-to-video and image-to-video generation with synchronized sound effects and dialogue, enabling developers to animate scenes with motion, camera dynamics, and audio in a single API workflow.

Grok Imagine Video
Text to Video

Moonlit Clockwork Carnival Alley

{
  "taskType": "videoInference",
  "taskUUID": "6378aa49-9f31-414a-8e00-3076dea79124",
  "model": "xai:grok-imagine@video",
  "positivePrompt": "A moonlit steampunk carnival tucked inside a narrow cobblestone alley, brass automatons performing for a small midnight crowd, glowing paper lanterns swaying overhead, a carousel horse mounted on mechanical rails gliding past the camera, curls of steam venting from copper pipes, sparkling puddles reflecting amber and cyan light. The camera begins with a slow dolly forward through hanging banners, then gently pans to reveal a violin-playing clockwork fox on a velvet crate while a tiny piston-driven drummer taps a lively rhythm nearby. A distant ferris wheel turns above the rooftops, gears clicking softly, carnival chimes ringing, murmuring spectators, fluttering fabric, footsteps on wet stone, occasional hiss of steam, and a warm female ringmaster voice off-screen saying, 'Step closer, the midnight wonders have only just awakened.' Cinematic, highly detailed, magical yet tactile, expressive lighting, atmospheric depth, dynamic motion, synchronized sound design.",
  "width": 1280,
  "height": 720,
  "duration": 8
}
{
  "taskType": "videoInference",
  "taskUUID": "6378aa49-9f31-414a-8e00-3076dea79124",
  "videoUUID": "c8b6b301-7a5e-4aa8-a3e5-0f4377da76ea",
  "videoURL": "https://vm.runware.ai/video/os/a16d07/ws/5/vi/c8b6b301-7a5e-4aa8-a3e5-0f4377da76ea.mp4",
  "cost": 0.56
}
Video to Video

Bioluminescent Reef Dreamscape

{
  "taskType": "videoInference",
  "taskUUID": "050f2911-487c-49eb-820f-e2e47f39ec6f",
  "model": "xai:grok-imagine@video",
  "positivePrompt": "Transform the reference video into a luminous fantasy undersea vision. The tunnel becomes an ancient submerged coral cathedral with glowing arches, drifting jellyfish lanterns, shimmering schools of silver fish, soft shafts of turquoise light, bioluminescent particles, and vast whale-song atmosphere. Preserve the original pacing and camera movement from the source video, but restylize the walking figure as a mysterious traveler in a flowing deep-sea cloak with reflective details. Add synchronized native audio: distant whale calls, bubbling water resonance, gentle current swells, soft footsteps echoing on wet stone, and a faint whispered line, 'The reef remembers.' Cinematic, dreamlike, richly detailed, immersive, high-end visual effects, coherent motion, natural scene continuity.",
  "inputs": {
    "referenceVideos": [
      "https://assets.runware.ai/assets/inputs/931713e7-94a4-46ff-b6a2-a450a9ab9e53.mp4"
    ]
  }
}
{
  "taskType": "videoInference",
  "taskUUID": "050f2911-487c-49eb-820f-e2e47f39ec6f",
  "videoUUID": "ff8ba334-00f7-4158-8296-6dbc1f2fd2d2",
  "videoURL": "https://vm.runware.ai/video/os/a17d13/ws/5/vi/ff8ba334-00f7-4158-8296-6dbc1f2fd2d2.mp4",
  "cost": 0.404
}
Text to Video

Stormy Lighthouse Rescue

{
  "taskType": "videoInference",
  "taskUUID": "ba22dba3-0b1d-44e1-ad81-b3eb720d91fe",
  "model": "xai:grok-imagine@video",
  "positivePrompt": "A cinematic night storm on a rocky coastline, waves crashing against black cliffs below a tall lighthouse. The camera begins with a wide aerial sweep through rain and sea mist, then pushes toward the lighthouse window glowing warm amber. Inside, a soaked coast guard captain grabs a radio and shouts, 'Hold on, we're coming for you!' Cut to the beam of the lighthouse slicing through sheets of rain as a rescue boat battles the surf below. Thunder rolls, wind howls, rain lashes metal railings, sirens pulse faintly in the distance, and the ocean roars with deep, immersive sound. Realistic water physics, dramatic lightning flashes, high contrast cinematic lighting, tense atmosphere, natural lip sync for the spoken line, polished blockbuster look.",
  "width": 1280,
  "height": 720,
  "duration": 8
}
{
  "taskType": "videoInference",
  "taskUUID": "ba22dba3-0b1d-44e1-ad81-b3eb720d91fe",
  "videoUUID": "ed30ad9a-6693-4ff3-8775-796ae3cd8fe7",
  "videoURL": "https://vm.runware.ai/video/os/a03d21/ws/5/vi/ed30ad9a-6693-4ff3-8775-796ae3cd8fe7.mp4",
  "cost": 0.56
}