Grok Imagine 1.5

• Starts from your image, so your subject stays your subject
• Spoken lines come out strikingly natural
• 480p to 1080p, scenes from 1 to 15 seconds
• Fast generations, often under a minute

Grok Imagine 1.5 is xAI's premium image-to-video model. Give it a starting image (EpicVids generates or accepts one as your first frame) and a prompt, and it animates the scene with sound and speech that sounds remarkably human. It is the model to reach for when a character needs to talk and feel alive on screen.

Pricing on EpicVids

Longer videos are several scenes stitched into one film, so the total is the per-scene price times the scene count. Portrait 9:16 costs the same as landscape. Native audio is included in the price.