Models / Grok Imagine / Image to video
Grok Imagine image to video prompting guide
Last checked 2026-10-11Grok Imagine Video 1.5 (xAI) · grok-imagine-video-1.5, 1.5 Lite, grok-imagine-video (edit/extend)
How to prompt Grok Imagine in image-to-video (start frame) mode. Every point links its source; community tips are marked. Your agent gets the same guide through the Atlas MCP (get_guide).
Prompt structure
motion from image→camera→pacing→audio
- No dedicated prompting guide published; describe subject, camera, pacing and sound in plain language. source ↗
What the text should describe
- Send image (+ optional prompt) for image-to-video; output follows the image's aspect ratio (aspect_ratio ignored). 1.5 renders native 1080p. Adding last_frame, keyframes or reference_images turns it into reference-to-video with the image as pinned first frame. source ↗
- t2v internally generates a first frame then animates it — in i2v you supply that frame, so the prompt only needs motion, camera, pacing and sound. source ↗
Responds well to
- t2v first generates a frame from your prompt then animates it, so the opening frame description matters. source ↗
Duration and limits
- Duration 1–15 s (default 8). 1.5 native 1080p for t2v/i2v; r2v up to 720p. i2v follows the image's aspect ratio. Editing keeps source length (max 8.7 s), 720p. source ↗
Negative prompt
Supported via .
Next
All Grok Imagine modesGrok Imagine model, prices & shotsFrom $0.02/s · pricesSeedance image to videoKling image to videoVeo image to videoRunway image to video