xAI shipped a significant update to Grok Imagine Video 1.5 on July 31, 2026, adding four capabilities: text-to-video generation, native 1080p output, voice reference, and multi-reference scene control with up to seven simultaneous visual anchors per generation. Text-to-video and native 1080p are generally available on grok.com/imagine, iOS, and Android. Voice reference is rolling out first to SuperGrok Heavy and SuperGrok Plus subscribers in the United States, with broader rollout within days; developers must request API access through xAI's sales team. The new text-to-video mode removes the prior requirement of a starting image by pairing xAI's image generation pipeline with the image-to-video engine. The 1080p addition is technically significant because Aurora is an autoregressive system that generates frames sequentially; scaling from 720p to 1080p multiplies pixel tokens per frame by roughly 2.25 times. xAI has not published a technical explanation for 1080p handling, but API pricing shows 480p video costs $0.08 per second, 720p costs $0.14 per second, and 1080p costs