xAI has updated its Imagine Video 1.5 model to support text, image, and voice references, enabling users to generate videos up to 1080p resolution. The update allows for character consistency by locking faces and voices across scenes, with support for up to seven references per generation.
- Image and voice references are now available in the US for SuperGrok Heavy and SuperGrok Plus and iOS.
- Native 1080p generation is supported for both text-to-video and image-to-video workflows.
- Text-to-video capabilities allow users to generate videos from prompts alone without a starting image.
- The features are generally, iOS, and Android, with API access via the grok-imagine-video-1.5 model.
This update enhances creative control by allowing users to maintain consistent characters and settings while changing actions or scenes.