AI video model
Turn photos into living scenes with xAI's Grok Imagine 1.5: upload up to 7 reference images for identity-locked motion and get 1-15 second clips with sound at the lowest per-second price on the platform.
Compare Grok Imagine 1.5 with other video models — same workspace, one click to switch.
A glimpse of what people are creating with AI video models on CreateVision AI.
xAI's image-to-video model animates your photos into 1-15 second clips with sound, keeps the same person recognizable across every shot with up to 7 reference images, and costs less per second than any other video model on the platform.
Upload one photo — or up to seven — and Grok Imagine treats them as an identity anchor: the same face, body, and silhouette carry through every cut. It is the engine behind the viral "same actress, nine movie genres" montages, and it works just as well for keeping your product or character consistent.
Per-second pricing starts lower than any other model we host — low enough to iterate freely, test meme formats, and batch social clips without watching your balance. The exact credit cost shows before every generation, and failed runs refund automatically.
Clips arrive with generated audio — ambience, effects, and spoken lines written into your prompt — so a single generation gives you something you can publish directly to vertical or widescreen feeds.
Pick any length from 1 to 15 seconds at 480p or 720p, in auto, 1:1, 16:9, 9:16, 3:2, or 2:3 — auto simply follows your photo's framing. Short renders come back in about a minute, which makes rapid-fire creative testing practical.
One account, the full image and video generation workflow.
Start free with daily credits. Upgrade for premium models, faster generation, and 4K output.
Perfect for getting started
Billed annually · $240/year
Billed annually · $300/year
Grok Imagine 1.5 is xAI's image-to-video model. You upload 1-7 photos and describe the motion; it returns a 1-15 second clip with sound that keeps the people or subjects in your photos recognizable throughout.
No — Grok Imagine 1.5 always starts from at least one image. If you want pure text-to-video, use Seedance 2.0 Fast or Wan 2.7; you can also generate a still image first and then animate it here.
Per second of output at your chosen resolution (480p or 720p) — the lowest per-second rate of any video model on the platform. The exact cost shows before generation, and failed runs are automatically refunded.
Upload up to 7 reference images and mention them in your prompt (e.g. "Reference Image 1 as identity lock"). The model keeps that subject's face and silhouette consistent across every shot in the clip.
Yes — clips include generated sound. You can write spoken lines and sound cues directly into the prompt.
Credits are refunded automatically for failed video generations.
