Grok Imagine lets you combine up to 14 references in a single video generation
XFreeze · x · 2026-09-03
Grok Imagine shipped a major update: a single video generation can now take up to 14 references. Images, voices, characters, and styles can all be combined in one prompt — just tag each with "@" and Grok uses them together in the same video.
The upgrade targets consistency and character control, enabling far more directed video generation rather than pure text-to-video luck.
Related event: Grok Imagine Now Supports Up to 14 References in a Single Video(2 posts)→
More from Multimodal
- SolarWM: open data and scalable training for long-horizon video world models — CUHKSZ · 2026-09-03
- World's first fully AI video streaming service launches, built on MiniMax h3 max turbo — jfischoff · 2026-09-03
- Muse Spark 1.3 generates a Minecraft clone from a single prompt — and the result holds up — alexandr_wang · 2026-09-03
- Scale CEO Praises Muse Spark 1.3's Interactive 3D Japanese Garden Scene as Huge Leap — alexandr_wang · 2026-09-03
- A dime per generation: Muse Spark 1.3 renders Minecraft for 10 cents — alexandr_wang · 2026-09-03
- Microsoft releases VibeVoice-ASR-Streaming-7B open streaming speech recognition model — Acceptable-Cycle4645 · 2026-09-03