Imagine Video 1.5 with References

xAI’s Imagine Video 1.5 is the latest iteration of their video generation model, now supporting text, image, and voice references to improve consistency and quality. Users can generate videos up to 1080p resolution directly from text prompts without needing a starting image. The model allows up to seven references per generation, enabling control over characters, scenes, and actions. Voice references ensure consistent audio for characters across scenes. These features are initially available in the US for SuperGrok Heavy and SuperGrok Plus users on grok.com/imagine and iOS, with a rollout to all tiers soon. The API supports image references, text-to-video, and native 1080p generation, with voice reference support available upon request. This integration allows developers to create cinematic videos with precise control over visual and audio elements, enhancing the video generation experience on multiple platforms.