X AI Grok Imagine Video V1.5 Reference To Video

X AI Grok Imagine Video V1.5 Reference To Video

Playground

xAI Grok Imagine Video v1.5 Reference to Video turns up to seven reference images and a natural-language prompt into short, stylized AI videos, with 480P / 720P output options and selectable aspect ratios for identity-consistent clips, character-driven videos, social media content, creative storytelling, and marketing workflows. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

xAI Grok Imagine Video V1.5 Reference-to-Video generates short videos from up to seven reference images and a natural-language prompt. It is designed for identity- and style-consistent motion generation, character-driven clips, stylized social media content, and other reference-guided video workflows.

Why Choose This?

• Reference-guided video generation Provide 1-7 reference images to guide the subject, identity, and style of the generated video.

• Prompt-based motion control Use text to describe motion, camera behavior, atmosphere, and how the scene evolves.

• Consistent subjects and style Keep a character, look, or aesthetic coherent across the clip by supplying multiple references.

• Flexible output settings Choose 480p or 720p, pick an aspect ratio, and set the clip length.

• Production-ready API Suitable for character content, concept visualization, ads, and stylized motion storytelling.

Parameters

How to Use

1. Upload reference images — provide 1-7 images that define the subject, identity, or style.
2. Write your prompt — describe the motion, scene, and camera behavior you want.
3. Set duration (optional) — choose how long the video should be.
4. Choose aspect ratio — match the target platform (e.g. 9:16 for vertical, 16:9 for landscape).
5. Choose resolution — use 480p for lower cost or 720p for higher quality.
6. Submit — run the model and download the generated video.

Example Prompt

The person from the references walks confidently through a rainy neon-lit street at night, cinematic framing, realistic skin texture, natural hair movement, subtle camera push-in

Pricing

Pricing depends on output duration, resolution, and the number of reference images.

Each reference image adds $0.01.

Example Costs (1 reference image)

Billing Rules

• 480p costs $0.08 per second
• 720p costs $0.14 per second
• Each reference image adds $0.01 (1-7 images supported)
• Pricing scales linearly with duration
• Billed duration is rounded up to the next whole second
• Minimum billed duration is 1 second
• Maximum billed duration is 15 seconds

Best Use Cases

• Identity-consistent video — Keep a character or subject coherent across a clip.
• Character-driven content — Animate a person or persona defined by reference images.
• Social media content — Create stylized animated visuals for posts and promos.
• Concept visualization — Explore motion directions anchored to a defined look.
• Creative prototyping — Test reference-guided motion ideas quickly.

Pro Tips

• Use clear, high-quality reference images for better identity and style stability.
• Provide multiple references of the same subject to strengthen consistency.
• Be specific in your prompt about camera movement, subject motion, and atmosphere.
• Match aspect_ratio to where the clip will be published.
• Use 480p for quick testing and 720p for better final-quality clips.

Notes

• prompt and reference_images are required.
• reference_images supports 1-7 images.
• duration supports 1-15 seconds.
• resolution defaults to 720p; aspect_ratio defaults to 16:9.
• Pricing depends on duration, resolution, and the number of reference images.

Related Models

• xAI Grok Imagine Video v1.5 Text-to-Video — Generate a video from a prompt alone.
• xAI Grok Imagine Video v1.5 Image-to-Video — Animate a single input image.

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task & Query Result

set -euo pipefail

export WAVESPEED_API_KEY="your-api-key"

REQUEST_BODY=$(cat <<'JSON'
{
  "prompt": "A cinematic ocean wave at sunrise, highly detailed",
  "reference_images": [
    "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg"
  ],
  "duration": 6,
  "aspect_ratio": "16:9",
  "resolution": "720p"
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/x-ai/grok-imagine-video-v1.5/reference-to-video" \
  -H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "${REQUEST_BODY}")

TASK=$(printf '%s' "${SUBMIT_RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "${TASK}" | jq -r '.id // empty')
if [ -z "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL=$(printf '%s' "${TASK}" | jq -r '.urls.get // empty')
if [ -z "${RESULT_URL}" ]; then RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"; fi

# 2. Poll until the prediction finishes.
while true; do
  RESPONSE=$(curl --silent --show-error --fail-with-body \
    "${RESULT_URL}" \
    -H "Authorization: Bearer ${WAVESPEED_API_KEY}")
  RESULT=$(printf '%s' "${RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
  STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')

  case "${STATUS}" in
    completed) printf '%s\n' "${RESULT}" | jq '.outputs'; break ;;
    failed|cancelled|timeout) printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
    created|processing) sleep 2 ;;
    *) printf 'Unexpected status: %s
' "${STATUS}" >&2; exit 1 ;;
  esac
done

Parameters

Task Submission Parameters

Request Parameters

Response Parameters

Result Request Parameters

Result Response Parameters