Trust in Rob – Home
AI SummaryCurated from 4 authoritative sources

xAI’s image-to-video model is out of preview and now takes text, image, and voice references — up to seven images per clip — with native 1080p and text-to-video.

xAI has launched Grok Imagine Video 1.5 as its best image-to-video stack yet: sharper motion and physics, native synced audio, faster generation, then a July update that adds multi-reference control, voice consistency, text-to-video, and native 1080p.

The path was quick. On June 3, 2026, xAI put grok-imagine-video-1.5-preview on the API for image-to-video up to 720p from a still frame plus a motion prompt. On June 16 it went generally available as grok-imagine-video-1.5 on the Imagine API, with Video 1.5 Fast on grok.com/imagine and the Grok iOS and Android apps. xAI says sound effects, ambience, and dialogue land in the same pass as the picture; motion holds weight and momentum better over a clip; and Fast almost doubles speed — about 25 seconds for a 6-second 720p video, down from 40+ seconds before.

The bigger product story is references. On July 31, 2026, Imagine Video 1.5 gained text, image, and voice references. You no longer need a single starting frame only: describe the shot for text-to-video, or feed references to lock identity. Image and voice references started in the US for SuperGrok Heavy and SuperGrok Plus on web and iOS, then roll out to all tiers. Multi-reference lets each image pin one thing — face, product, or location. Keep the character and change the set, keep the set and swap the character, or hold both and only change the action. Up to seven reference images per generation. Pass a character image plus a voice reference and both stay consistent across scenes — same face, same voice.

Native 1080p is supported for text-to-video and image-to-video on grok.com/imagine, iOS, and Android. In the xAI API, image references, text-to-video, and native 1080p are live on grok-imagine-video-1.5; voice reference support is available on request. Workflow extras on Grok Imagine include Projects, multiple agents running prompts in parallel, and library search for past clips.

Read more: Imagine Video 1.5 with References, Grok Imagine Video 1.5 GA, 1.5 Preview, and the video generation docs.

Original Sources

Disclaimer

This is an AI-summarized article from authoritative sources. If you want your content removed, please .

Share

Related Articles

Gemini 4 Argon Is Now Available in the Gemini App
Google

Gemini 4 Argon Is Now Available in the Gemini App

Google opened Gemini 4 Argon to Google AI Pro and Ultra subscribers on October 13, 2026, inside the Gemini app.

Meta Introduces Muse Wonder and Muse Wonder Full
Artificial Intelligence

Meta Introduces Muse Wonder and Muse Wonder Full

Meta released Muse Wonder and Muse Wonder Full on October 12, 2026, and calls them its most capable models yet for personal and professional agent work.

OpenAI Introduces Dots, Always-On Agents Powered by GPT-6 Astra
Artificial Intelligence

OpenAI Introduces Dots, Always-On Agents Powered by GPT-6 Astra

Named ChatGPT agents that keep working between chats, with a cloud computer on Pro and Business Premium where the rollout has started.

WEEKLY DIGEST

Expert Insights Delivered Directly to Your Inbox.

Curated tech insights, practical automation tips and strategies to reclaim your time — delivered to your inbox.