MiniMax H3 Open Weights | Try in Video Generator →
Home/Explore/Skywork Ai/Skyreels V3/Reference To Video

Skyreels V3 Reference to Video | Fast Image-to-Video API

skywork-ai/

SkyReels V3 Reference to Video is a fast AI reference-to-video generation model that creates videos from 1 to 4 reference images and a text prompt. Ready-to-use REST inference API for character-consistent videos, product visuals, branded storytelling, social media clips, advertising creatives, and professional reference-based video generation workflows with simple integration, no coldstarts, and affordable pricing.

image-to-video
Input

Idle

$0.2per run·~50 / $10

Next:

ExamplesView all

Use Reference Image 1 as the main character identity, face, hairstyle, outfit, and overall appearance. Use Reference Image 2 as the environment, lighting, color mood, and background composition reference. Generate a natural 6-second vertical short-video style clip. The foreign female host sits at the desk near the window and speaks directly to the camera in a relaxed, friendly way. She makes subtle head movements, natural blinking, small facial expressions, and light hand gestures near the desk without covering her mouth. The camera has a very slight slow push-in, warm daylight remains stable, background stays softly blurred, and the mouth area remains clearly visible for lip-sync. Keep her identity consistent, keep the same outfit, keep realistic skin texture, avoid over-posing, avoid formal portrait style, make it feel like a real lifestyle creator video frame.

Related Models

README

Skywork AI SkyReels V3 Reference-to-Video

Skywork AI SkyReels V3 Reference-to-Video generates videos from one to four reference images and a natural-language prompt. It is designed for image-guided video creation where the reference images help preserve identity, appearance, style, or scene elements while the prompt controls motion, action, camera behavior, and overall direction.

Why Choose This?

  • Reference-guided video generation Use uploaded images to anchor characters, products, or visual style in the generated video.

  • Multi-image support Upload 1–4 reference images for stronger control over appearance and consistency.

  • Prompt-driven motion Describe the scene, action, camera movement, or avatar behavior in natural language.

  • Flexible aspect ratios Choose from 16:9, 9:16, or 1:1 depending on your target platform and composition needs.

  • Simple duration control Generate clips from 5 to 10 seconds with straightforward pricing.

  • Production-ready API Suitable for character-driven clips, product videos, stylized social content, and reference-based storytelling workflows.

Parameters

ParameterRequiredDescription
promptYesText prompt describing the scene, action, camera, or avatar behavior.
imagesYesReference image URLs. Upload 1–4 images.
aspect_ratioNoAspect ratio of the generated video. Supported values: 16:9, 9:16, 1:1. Default: 16:9.
durationNoGenerated video duration in seconds. Range: 5–10. Default: 5.

How to Use

  1. Upload your reference images — provide 1–4 images to guide identity, look, or scene consistency.
  2. Write your prompt — describe the motion, action, atmosphere, camera movement, or presentation style you want.
  3. Choose aspect ratio — use 16:9, 9:16, or 1:1 based on the final placement.
  4. Set duration — choose a clip length between 5 and 10 seconds.
  5. Submit — run the model and download the generated video.

Example Prompt

A cinematic product reveal with smooth camera movement, soft studio lighting, subtle reflections, premium commercial style, and stable visual consistency with the reference images

Pricing

Pricing is based on duration.

DurationCost
5s$0.20
6s$0.24
7s$0.28
8s$0.32
9s$0.36
10s$0.40

Best Use Cases

  • Character consistency — Keep the same person, face, or style across a generated clip.
  • Product videos — Use product photos as references for short commercial-style motion content.
  • Reference-based storytelling — Anchor visual identity while prompting new action or camera movement.
  • Social media creatives — Generate vertical, square, or widescreen short-form clips from still references.
  • Visual prototyping — Explore motion directions from a fixed set of images.

Pro Tips

  • Use clear, high-quality reference images for better visual consistency.
  • If identity matters, keep the reference images visually aligned in style and subject.
  • Be specific in the prompt about motion, camera movement, and mood.
  • Start with 5s to validate the concept, then extend to a longer duration if needed.
  • Use 9:16 for mobile-first content and 16:9 for widescreen layouts.

Notes

  • Both prompt and images are required.
  • images supports 1 to 4 reference images.
  • duration supports 5 to 10 seconds.
  • aspect_ratio defaults to 16:9.
  • Pricing depends only on duration.

Related Models

Note:This website uses AI models provided by third parties.

Skyreels v3 Reference To Video API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/skywork-ai/skyreels-v3/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 Skyreels v3 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",
    "images": [
        "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg"
    ],
    "aspect_ratio": "16:9",
    "duration": 5
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/skywork-ai/skyreels-v3/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/skywork-ai/skyreels-v3/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 ${apiKey}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
        "prompt": "A cinematic shot of a city at sunset, soft golden light",
        "images": [
                "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg"
        ],
        "aspect_ratio": "16:9",
        "duration": 5
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = task.urls?.get ||
  `https://api.wavespeed.ai/api/v3/predictions/${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",
    "images": [
        "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg"
    ],
    "aspect_ratio": "16:9",
    "duration": 5
}

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/skywork-ai/skyreels-v3/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)

Skyreels v3 Reference To Video API — Frequently asked questions

What is the Skyreels v3 Reference To Video API?

Skyreels v3 Reference To Video is a Skywork Ai model for video generation from images, exposed as a REST API on WaveSpeedAI. SkyReels V3 Reference to Video is a fast AI reference-to-video generation model that creates videos from 1 to 4 reference images and a text prompt. Ready-to-use REST inference API for character-consistent videos, product visuals, branded storytelling, social media clips, advertising creatives, and professional reference-based video generation workflows with simple integration, no coldstarts, and affordable pricing. You can call it programmatically or try it from the playground above.

How do I call the Skyreels v3 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/skywork-ai/skywork-ai-skyreels-v3-reference-to-video.

How much does Skyreels v3 Reference To Video cost per run?

Skyreels v3 Reference To Video starts at $0.20 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 Skyreels v3 Reference To Video accept?

Key inputs: `prompt`, `images`, `aspect_ratio`, `duration`. 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/skywork-ai/skywork-ai-skyreels-v3-reference-to-video.

How do I get started with the Skyreels v3 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 Skyreels v3 Reference To Video outputs commercially?

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