xAI has released Grok Imagine Video 1.5, its latest image-to-video model, which is now generally available through the Imagine API. The update brings improvements in motion, physics, and audio, with significantly faster generation speeds. The new version is also accessible via grok.com/imagine and the iOS and Android apps. The model is designed to enhance creative workflows with better performance and more intuitive features.
Grok Imagine Video 1.5 Fast nearly doubles the generation speed compared to the previous model, producing 6-second, 720p videos in about 25 seconds, down from 40+ seconds. Audio and speech are now generated in a single pass, resulting in clearer and better-synced dialogue. Additionally, movement and physics in videos are more stable, with fewer warps and more realistic weight and momentum. These enhancements aim to improve the overall quality and efficiency of video creation for users.
The release includes new features to boost productivity, such as Projects for organizing work, Multiple agents for parallel processing, and Search for quickly finding past creations. xAI emphasized that Grok Imagine Video 1.5 is now out of preview and fully available in the xAI API as grok-imagine-video-1.5.
Source: xai
