Seedream 5.0 Pro ya está aquí | Pruébalo en el Generador de Imágenes →

xAI Grok Imagine Video v1.5 Reference to Video

x-ai /

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.

image-to-video
Entrada

Inactivo

$0.09por ejecución·~11 / $1

Siguiente:

EjemplosVer todo

The magician throws glowing cards into the air, the cards transform into holographic birds flying around the street. People stop and watch in surprise. The camera circles around him while neon lights flicker and rain falls slowly, cinematic cyberpunk movie scene.

Modelos relacionados

README

xAI Grok Imagine Video V1.5 Reference-to-Video

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

ParameterRequiredDescription
promptYesText description of the desired motion, camera movement, and scene.
reference_imagesYes1-7 reference image URLs that guide the subject and style of the video.
durationNoOutput video duration in seconds. Range: 1-15. Default: 6.
aspect_ratioNoAspect ratio of the output video. Supported: 16:9, 1:1, 9:16, 3:2, 2:3. Default: 16:9.
resolutionNoOutput video resolution. Supported: 480p, 720p. Default: 720p.

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.

Pricing

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

ResolutionPrice per Second5s Example (1 image)
480p$0.08$0.41
720p$0.14$0.71

Each reference image adds $0.01.

Example Costs (1 reference image)

Resolution1s5s10s15s
480p$0.09$0.41$0.81$1.21
720p$0.15$0.71$1.41$2.11

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

Nota:Este sitio web utiliza modelos de IA proporcionados por terceros.

Grok Imagine Video v1.5 Reference To Video API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/x-ai/grok-imagine-video-v1.5/reference-to-video with your input as JSON. The endpoint returns a prediction id. Start polling the result endpoint around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. On completed, read output values from data.outputs. Examples for Grok Imagine Video v1.5 Reference To Video below.

HTTP example
set -euo pipefail

: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"

REQUEST_BODY=$(cat <<'JSON'
{
    "prompt": "A cinematic shot of a city at sunset, soft golden light",
    "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 "Content-Type: application/json" \
  -H "Authorization: Bearer $WAVESPEED_API_KEY" \
  -d "$REQUEST_BODY")

TASK=$(printf '%s' "$SUBMIT_RESPONSE" | jq 'if has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "$TASK" | jq -r '.id')
if [ -z "$PREDICTION_ID" ] || [ "$PREDICTION_ID" = "null" ]; 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' "$RESPONSE" | jq 'if has("data") then .data else . end')
  STATUS=$(printf '%s' "$RESULT" | jq -r '.status')
  case "$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
Node.js example
const submitUrl = "https://api.wavespeed.ai/api/v3/x-ai/grok-imagine-video-v1.5/reference-to-video";
const apiKey = process.env.WAVESPEED_API_KEY;
if (!apiKey) throw new Error('Set WAVESPEED_API_KEY');

async function requestJson(url, options = {}) {
  const response = await fetch(url, options);
  if (!response.ok) throw new Error(await response.text());
  return response.json();
}

// 1. Submit the prediction.
const body = await requestJson(submitUrl, {
  method: "POST",
  headers: {
    "Authorization": `Bearer ${apiKey}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
        "prompt": "A cinematic shot of a city at sunset, soft golden light",
        "reference_images": [
                "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg"
        ],
        "duration": 6,
        "aspect_ratio": "16:9",
        "resolution": "720p"
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = task.urls?.get ||
  `https://api.wavespeed.ai/api/v3/predictions/${task.id}/result`;

// 2. Poll until the prediction finishes.
while (true) {
  const resultBody = await requestJson(resultUrl, {
    headers: { "Authorization": `Bearer ${apiKey}` },
  });
  const result = resultBody.data ?? resultBody;
  if (result.status === "completed") {
    console.log(result.outputs);
    break;
  }
  if (["failed", "cancelled", "timeout"].includes(result.status)) throw new Error(JSON.stringify(result));
  if (!["created", "processing"].includes(result.status)) throw new Error("Unexpected status: " + result.status);
  await new Promise(resolve => setTimeout(resolve, 2000));
}
Python example
import json
import os
import time
from urllib.request import Request, urlopen

api_key = os.environ["WAVESPEED_API_KEY"]
headers = {"Authorization": f"Bearer {api_key}", "Content-Type": "application/json"}
payload = {
    "prompt": "A cinematic shot of a city at sunset, soft golden light",
    "reference_images": [
        "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg"
    ],
    "duration": 6,
    "aspect_ratio": "16:9",
    "resolution": "720p"
}

def request_json(url, data=None):
    request = Request(url, data=data, headers=headers, method="POST" if data else "GET")
    with urlopen(request) as response:
        return json.load(response)

# 1. Submit the prediction.
body = request_json("https://api.wavespeed.ai/api/v3/x-ai/grok-imagine-video-v1.5/reference-to-video", json.dumps(payload).encode())
task = body.get("data", body)
if not task.get("id"):
    raise RuntimeError("Submission response did not contain a prediction id")
result_url = task.get("urls", {}).get("get") or f"https://api.wavespeed.ai/api/v3/predictions/{task['id']}/result"

# 2. Poll until the prediction finishes.
while True:
    result_body = request_json(result_url)
    result = result_body.get("data", result_body)
    status = result.get("status")
    if status == "completed":
        print(result.get("outputs", []))
        break
    if status in {"failed", "cancelled", "timeout"}:
        raise RuntimeError(result)
    if status not in {"created", "processing"}:
        raise RuntimeError(f"Unexpected status: {status}")
    time.sleep(2)

Grok Imagine Video v1.5 Reference To Video API — Frequently asked questions

What is the Grok Imagine Video v1.5 Reference To Video API?

Grok Imagine Video v1.5 Reference To Video is a xAI model for video generation from images, exposed as a REST API on WaveSpeedAI. 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. You can call it programmatically or try it from the playground above.

How do I call the Grok Imagine Video v1.5 Reference To Video API?

POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID. Poll the result endpoint starting around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. The playground generates production-oriented Python, JavaScript, and cURL examples with timeouts, transient-error handling, and safe GET retries. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/x-ai/x-ai-grok-imagine-video-v1.5-reference-to-video.

How much does Grok Imagine Video v1.5 Reference To Video cost per run?

Grok Imagine Video v1.5 Reference To Video starts at $0.090 per run. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.

What inputs does Grok Imagine Video v1.5 Reference To Video accept?

Key inputs: `prompt`, `aspect_ratio`, `resolution`, `duration`, `reference_images`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/x-ai/x-ai-grok-imagine-video-v1.5-reference-to-video.

How do I get started with the Grok Imagine Video v1.5 Reference To Video API?

Sign up for a free WaveSpeedAI account to claim starter credits, copy your API key from /accesskey, then call the endpoint shown in the API tab of the playground. The playground also auto-generates a code sample in Python, JavaScript, or cURL for the parameters you've set.

Can I use Grok Imagine Video v1.5 Reference To Video outputs commercially?

Commercial usage rights depend on the model's license, set by its provider (xAI). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.

xAI Grok Imagine Video v1.5 Reference to Video | WaveSpeedAI