Grok Imagine R2V Model Integration

xAI Grok Imagine R2V is now available for reference-to-video generation with up to 7 reference images, 1-10 second durations, and multiple aspect ratios.

We integrated Grok Imagine R2V as a new video generation model for reference-to-video workflows.

Why This Matters

R2V helps teams generate more consistent UGC and brand videos by guiding the model with existing images instead of relying on text alone.

  • Reference-first generation: Use 1-7 reference images to control style, subjects, and composition.
  • Flexible durations: Generate clips from 1 to 10 seconds.
  • Common social formats: Supports 16:9, 9:16, 4:3, 3:4, and 1:1 in the product UI.
  • UGC-ready flow: Added as a selectable model in the AI Avatars UGC generator.

What's New

  • New video model: grok-imagine-r2v
  • End-to-end wiring in GenAI video generation, model catalog, and provider normalization
  • New Mastra tool mapping for agent-driven video generation
  • UGC dialog model selector with support for Grok Imagine R2V

References