SpaceXAI Adds Multi-Reference and 1080p to Imagine Video 1.5
On July 31, 2026, SpaceXAI upgraded Imagine Video 1.5 with text-, image-, and voice-reference conditioning (up to seven image references), native 1080p generation, and text-to-video—rolling out first to SuperGrok Heavy and Plus in the US on grok.com/imagine and iOS, with API support for image refs and 1080p on grok-imagine-video-1.5.
TLDR
SpaceXAI on July 31, 2026 shipped Imagine Video 1.5 with References—a major capability update to last month’s Imagine Video 1.5. Creators can condition generation with text, image, and voice references (up to seven image refs per generation), run text-to-video without a starter frame, and export native 1080p. Consumer rollout: US SuperGrok Heavy and Plus first on grok.com/imagine and iOS, expanding to all tiers over subsequent days. API: model id grok-imagine-video-1.5 with image references, text-to-video, and 1080p live; voice reference available on request.
What shipped
| Capability | Detail (x.ai primary) |
|---|---|
| Product | Imagine Video 1.5 with References |
| References | Text + image + voice; up to 7 image refs |
| Consistency | Hold face and voice across scenes; swap character vs scene independently |
| Text-to-video | Prompt-only generation (pairs image gen + I2V pipeline) |
| Resolution | Native 1080p for T2V and I2V |
| Consumer access | US SuperGrok Heavy / Plus day one; all tiers rolling out |
| Surfaces | grok.com/imagine, iOS, Android (T2V/1080p called out as GA on those) |
| API model | grok-imagine-video-1.5 |
Prior Imagine Video 1.5 (June) improved motion/physics/audio; this release is the reference-consistency and resolution step—competing with multi-ref video stacks (Runway, Luma, Google Omni-class video, etc.).
Product-line placement
Distinct from Grok 4.5, Build Mode, and Voice Think Fast 2.0. Continues the Grok Imagine media line (image + video APIs). June’s 1.5 base model post is not dual-filed; July 31 is the references / 1080p product ship.
Why this story matters
Video generation is shifting from one-shot clips to character-consistent production (same face, same voice, controllable scenes). Multi-ref + 1080p is table stakes for creator and marketing workflows. Watch API pricing/duration limits, voice-ref general availability, identity-leak / deepfake policy enforcement, and quality vs Runway Gen-4.x / Luma on independent preference boards.