Skywork AI Skyreels V3 Reference To Video API Documentation

Skywork AI Skyreels V3 Reference To Video API Documentation

Playground

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.

Features

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

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.

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

• Skywork AI SkyReels V3 Standard Single Avatar — Standard single-avatar talking video generation.
• Skywork AI SkyReels V3 Pro Single Avatar — Higher-quality single-avatar speaking video generation.
• Skywork AI SkyReels V3 Standard Multi Avatar — Multi-avatar workflow in the Standard product line.
• Skywork AI SkyReels V3 Pro Multi Avatar — Higher-tier multi-avatar generation for more advanced character scenes.

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",
  "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 "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