Grok Imagine Video 1.5 Lite – Text to Video

Image Gen·grok-imagine·by xAI

Grok Imagine Video 1.5 Lite generates video from text prompts for visual storytelling. Turn scene ideas into short clips for creative projects and content.

Runtime (p50)
-
Estimated price
From $0.02
Call the API
prediction.sh
sh
curl -X POST \
  -H "Authorization: Bearer $EACHLABS_API_KEY" \
  -H "Content-Type: application/json" \
  --data '{
    "model": "xai-grok-imagine-video-1-5-lite-text-to-video",
    "input": {
        "prompt": "15-second aesthetic influencer vlog-style video of a young woman preparing iced matcha in a bright, minimal kitchen with soft natural morning light from a window. She has her hair in a loose bun and wears a cream knit sweater. Warm neutral tones, cream and sage green palette, cozy and calm atmosphere. Smooth, stable camera with subtle handheld feel, vertical 9:16 format.\\n\\n0–5s: Medium shot from the front at counter height. The woman stands at the kitchen counter and slowly whisks matcha in a ceramic bowl with a bamboo whisk, using calm, gentle circular motions. Her hands and the bowl are clearly visible, natural and well-proportioned.\\n5–10s: Medium close-up from the side. She slowly pours the bright green matcha into a tall clear glass filled with ice and milk, the green gently blending into the white. Slow, smooth motion.\\n10–15s: Medium shot. She picks up the glass with both hands, takes a small sip through a straw and smiles softly at the camera.\\n\\nRealistic and natural movement, anatomically correct hands with five fingers, consistent appearance of the woman throughout, soft depth of field, crisp details, authentic social media aesthetic, no text on screen.",
        "duration": 15,
        "resolution": "480p",
        "aspect_ratio": "16:9",
        "generate_audio": true
    },
    "webhook_url": ""
}' \
  https://api.eachlabs.ai/v1/prediction/

Related models

4 models
* FAQ

About Grok Imagine Video 1.5 Lite – Text to Video

01 / 03

What is Grok Imagine Video 1.5 Lite Text to Video?

Grok Imagine Video 1.5 Lite Text to Video is an xAI model that generates video from a written scene description. Describe the subject, setting, and intended movement in your prompt. This workflow starts from words rather than requiring an uploaded image as the visual starting point.