Leak says Grok Imagine is adding face, outfit, voice, and multi-reference video control
eyishazyer · x · 2026-07-28
A leak says Grok Imagine may be getting a major upgrade called “Imagine Omni.”
The reported features are aimed at video generation and consistency: locking a character’s face and outfit, adding a voice, and combining multiple references in a single video workflow.
If accurate, this would push Grok Imagine toward a more controlled, reference-driven multimodal creation tool rather than a simple text-to-video generator.
Related event: Leaks: xAI's Grok Imagine to Upgrade with Multimodal Controls(3 posts)→
More from Multimodal
- Open-source local AI tool generates slides, edits them visually, and exports PPTX — goodboydhrn · 2026-07-28
- Mage-Flow runs 13–18× faster than Krea 2 Turbo on an RTX 3060, but quality trails — SirMick · 2026-07-28
- MIT framework teaches vision-language models to generate more accurate CAD programs — bravo_abad · 2026-07-28
- Text like “33°C” is not touch, argues a critique of LLM embodiment claims — flowersslop · 2026-07-28
- A ready-made Seedance 2.0 prompt recreates a 1990s arcade scene — techhalla · 2026-07-28
- Developer builds a local photo assistant with OpenClaw and MiniCPM-V 4.6 — 面壁智能 · 2026-07-28