SkyReels V4 Reference to Video is a fast AI reference-to-video generation model that creates high-quality videos from reference images or a reference video and a text prompt using the SkyReels V4 omni-video workflow. Ready-to-use REST inference API for character-consistent videos, product visuals, branded storytelling, social media clips, advertising creatives, concept videos, and professional reference-based video generation workflows with simple integration, no coldstarts, and affordable pricing.
Idle
$0.1per run·~10 / $1
Use the input image as the first frame. Preserve the same female model, facial identity, hair, pose style, purple dress, studio background, and lighting. Animate the woman raising the toner bottle in her hand and presenting it elegantly to the camera. She looks toward the lens with a calm confident beauty-expression, slightly smiles, and holds the toner bottle near her cheek in a premium skincare advertising pose. She gently rotates the bottle so the front label is visible, then pauses in a polished hero pose. Add subtle blinking, breathing, delicate hand movement, and soft hair movement. Keep the product centered and easy to see. High-end beauty commercial style, realistic motion, stable identity, smooth animation, no flicker, no deformed hands, no extra limbs, no text.
Skywork AI SkyReels V4 Reference-to-Video generates videos from reference images, with optional reference video guidance for stronger motion and scene control. It supports standard and fast modes, multiple resolutions, optional sound effects, and prompt-driven generation for character consistency, product motion, scene transfer, and other reference-based video workflows.
Reference-guided video generation
Use up to 3 reference images to guide identity, appearance, style, or scene elements.
Optional reference video support
Add up to 1 reference video when you want stronger motion or temporal guidance.
Two generation modes
Choose std for higher-quality output or fast for quicker, lower-cost generation.
Multiple resolutions
Supports 480p, 720p, and 1080p to balance quality and budget.
Flexible aspect ratios
Choose 16:9, 9:16, or 1:1 depending on your target platform.
Production-ready workflow Suitable for character-driven video, product clips, stylized motion design, and reference-based storytelling.
| Parameter | Required | Description |
|---|---|---|
| prompt | Yes | The prompt describing the generated video. Reference tags are added automatically when missing. |
| images | No | Reference image URLs. Upload up to 3 images. |
| ref_videos | No | Optional reference video URL. Upload at most 1 video. |
| aspect_ratio | No | Aspect ratio of the generated video. Supported values: 16:9, 9:16, 1:1. Default: 16:9. |
| duration | No | Duration of the generated video in seconds. Range: 3–15. Default: 5. |
| resolution | No | Output video resolution. Supported values: 480p, 720p, 1080p. Default: 1080p. |
| sound | No | Whether to generate sound effects with the video. Default: false. |
| mode | No | Quality/performance mode. Supported values: std, fast. Default: std. fast mode currently requires sound=false. |
3 images to guide identity, look, or scene consistency.1 video if you want stronger motion or temporal guidance.16:9, 9:16, or 1:1.3 and 15 seconds.480p, 720p, or 1080p depending on quality and cost needs.std for higher quality or fast for quicker generation.fast, keep sound=false.A cinematic fashion shot with smooth camera movement, elegant character motion, soft studio lighting, premium commercial pacing, and stable identity across the sequence.
Pricing depends on duration, resolution, mode, and whether you use a reference video.
| Resolution | Per Second | 5s Cost |
|---|---|---|
| 480p | $0.11 | $0.55 |
| 720p | $0.14 | $0.70 |
| 1080p | $0.35 | $1.75 |
| Resolution | Per Second | 5s Cost |
|---|---|---|
| 480p | $0.08 | $0.40 |
| 720p | $0.11 | $0.55 |
| 1080p | $0.275 | $1.375 |
| Resolution | Per Second | 5s Cost |
|---|---|---|
| 480p | $0.18 | $0.90 |
| 720p | $0.25 | $1.25 |
| 1080p | $0.625 | $3.125 |
| Resolution | Per Second | 5s Cost |
|---|---|---|
| 480p | $0.15 | $0.75 |
| 720p | $0.20 | $1.00 |
| 1080p | $0.50 | $2.50 |
| Resolution | 3s | 5s | 10s | 15s |
|---|---|---|---|---|
| 480p | $0.33 | $0.55 | $1.10 | $1.65 |
| 720p | $0.42 | $0.70 | $1.40 | $2.10 |
| 1080p | $1.05 | $1.75 | $3.50 | $5.25 |
| Resolution | 3s | 5s | 10s | 15s |
|---|---|---|---|---|
| 480p | $0.24 | $0.40 | $0.80 | $1.20 |
| 720p | $0.33 | $0.55 | $1.10 | $1.65 |
| 1080p | $0.825 | $1.375 | $2.75 | $4.125 |
| Resolution | 3s | 5s | 10s | 15s |
|---|---|---|---|---|
| 480p | $0.54 | $0.90 | $1.80 | $2.70 |
| 720p | $0.75 | $1.25 | $2.50 | $3.75 |
| 1080p | $1.875 | $3.125 | $6.25 | $9.375 |
| Resolution | 3s | 5s | 10s | 15s |
|---|---|---|---|---|
| 480p | $0.45 | $0.75 | $1.50 | $2.25 |
| 720p | $0.60 | $1.00 | $2.00 | $3.00 |
| 1080p | $1.50 | $2.50 | $5.00 | $7.50 |
durationstd and fastref_videos input increases the ratesound does not affect pricing directlyfast mode currently requires sound=falsefast mode for quick iteration before moving to std.fast mode for rough iteration, then switch to std for final-quality output.sound=false in fast mode.prompt is required.images supports up to 3 reference images.ref_videos supports up to 1 reference video.duration supports 3–15 seconds.resolution defaults to 1080p.mode defaults to std.fast mode currently requires sound=false.duration, resolution, mode, and whether a reference video is included.Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/skywork-ai/skyreels-v4/reference-to-video with your input as JSON. The endpoint returns a prediction id. Start polling the result endpoint around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. On completed, read output values from data.outputs. Examples for Skyreels v4 Reference To Video below.
set -euo pipefail
: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"
REQUEST_BODY=$(cat <<'JSON'
{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"aspect_ratio": "16:9",
"duration": 5,
"resolution": "1080p",
"sound": false,
"mode": "std"
}
JSON
)
# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
-X POST "https://api.wavespeed.ai/api/v3/skywork-ai/skyreels-v4/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
doneconst submitUrl = "https://api.wavespeed.ai/api/v3/skywork-ai/skyreels-v4/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 ${apiKey}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"aspect_ratio": "16:9",
"duration": 5,
"resolution": "1080p",
"sound": false,
"mode": "std"
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = task.urls?.get ||
`https://api.wavespeed.ai/api/v3/predictions/${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));
}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",
"aspect_ratio": "16:9",
"duration": 5,
"resolution": "1080p",
"sound": False,
"mode": "std"
}
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-v4/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 v4 Reference To Video is a Skywork Ai model for video generation from images, exposed as a REST API on WaveSpeedAI. SkyReels V4 Reference to Video is a fast AI reference-to-video generation model that creates high-quality videos from reference images or a reference video and a text prompt using the SkyReels V4 omni-video workflow. Ready-to-use REST inference API for character-consistent videos, product visuals, branded storytelling, social media clips, advertising creatives, concept videos, 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.
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-v4-reference-to-video.
Skyreels v4 Reference To Video starts at $0.10 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.
Key inputs: `prompt`, `images`, `aspect_ratio`, `resolution`, `duration`, `mode`. 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-v4-reference-to-video.
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.
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.