xAI releases Grok Imagine Video 1.5: supports synchronized audio and video generation, doubling the speed

robot
Abstract generation in progress
Golden Finance reports that xAI has officially released the image-and-text-to-video generation model Grok Imagine Video 1.5, and it has been fully rolled out across its API (grok-imagine-video-1.5), web platform (grok.com/imagine), and mobile clients.
The model enables integrated audio-and-video synchronized generation, producing sound effects, ambient sounds, and character dialogue simultaneously during a single inference, improving speech clarity and optimizing lip-sync. At the same time, the model improves its physics engine and motion consistency, enhancing the credibility of object movement and physical weight over long camera shots, and reducing visual artifacts such as distortions. In terms of generation speed, the lightweight Video 1.5 Fast reduces the time to generate a 6-second 720p video to about 25 seconds.
The web platform’s supporting workflows have also been updated in sync: a new Projects feature has been added to organize assets by category, supporting parallel runs with multiple agents (Multiple Agents) to execute multiple prompts, and providing semantic search (Search) in the media library. Digital artist David Thompson’s team used Grok Imagine 1.5 to produce the fully AI-generated movie trailer Odyssey.
View Original
This page may contain third-party content, which is provided for information purposes only (not representations/warranties) and should not be considered as an endorsement of its views by Gate, nor as financial or professional advice. See Disclaimer for details.
  • Reward
  • Comment
  • Repost
  • Share
Comment
Add a comment
Add a comment
No comments
  • Pinned