Grok Imagine (image & video generation)

Generally Available
xAI
xAI

Overview

xAI's image-and-video generation product, built into the Grok apps and API. Grok Imagine Video 1.5 launched May-June 2026 and topped the Image-to-Video Arena leaderboard on release; Musk declared the product 'done' on July 5, 2026, and a July 31 update added native 1080p output, voice/face-consistent references and up to seven-image multi-reference scene control. On August 7, 2026 xAI shipped Grok Imagine Image 2.0, rebuilding the image side around editing tools - a region-specific magic wand, precise segmentation, background removal, and multi-reference editing accepting up to five input images per generation.

Moved from preview to full general availability June 16, 2026; the July 31, 2026 update added 1080p text-to-video, image-to-video and reference-to-video generation with up to seven simultaneous visual anchors per clip; Image 2.0 shipped August 7, 2026 as the new Quality Mode on grok.com/imagine and in xAI's iOS and Android apps, with API access still pending.

Key Specs

Leaderboard Position
#1 on the Image-to-Video Arena leaderboard at launch, priced ~86% below OpenAI's Sora; Image 2.0 ranks #2 on the Arena text-to-image and image-edit leaderboards behind OpenAI's gpt-image-2
Video Output
Native 1080p, 6-15s clips with audio, up to 7 reference images per generation