Seedance 2.0 Reference to Video creates cinematic videos with native audio from your own reference images, videos, and audio, keeping characters, products, motion, and sound consistent while a prompt directs the new shot. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Idle
$0.24per run·~41 / $10
Use the man and the black bowler hat from <Image 1>. Preserve his exact face, hairstyle, glasses, clothing, body proportions, hat design, and shop environment. The tiny cloud above the hat begins raining directly into it. He looks down in confusion and slowly tilts the hat. A tiny flash of lightning appears inside the bowl of the hat, making him quickly pull it back in surprise. The camera starts with the same clean medium composition as <Image 1> and slowly pushes closer toward the man and the hat. Keep the main subject clear throughout the shot, simple composition, playful magical realism, natural acting, cinematic lighting.
The woman in @Image 1 walks between the tables of @Image 2, runs a hand along a chair, stops by the window and says: "I could stay here all day." Smooth tracking shot, warm natural light.
Use the woman from <Image 1> and the white wolf from <Image 2>. Preserve their exact identities, clothing, hairstyle, weapon, fur pattern, collar, medallion, proportions, and distinctive details. The monster hunter walks through an abandoned mountain village covered in morning fog. The white wolf suddenly appears on a rooftop above her, watching silently. She reaches toward her sword but stops when the wolf jumps down and places the silver medallion from its collar at her feet. She picks it up and notices the same symbol engraved on her sword. The wolf turns and begins walking toward a ruined chapel. She follows. The camera starts low behind broken wooden carts, moves into a tense two-shot during their encounter, then follows both characters through the fog. Dark Western fantasy, cinematic atmosphere, realistic creature movement, detailed materials, restrained suspense.
Seedance 2.0 Reference-to-Video guides generation with your own reference images, videos, and audio. Keep characters, products, scenes, motion, and soundtrack consistent while a prompt directs the new shot, with native synchronized audio and director-style control over camera, lighting, and pacing. The same reference inputs are also accepted by Seedance 2.0 Text-to-Video.
Unified multimodal architecture A single model that handles text, image, audio, and video inputs for comprehensive creative flexibility.
Native audio-visual synchronization Generates video with synchronized audio in a single pass — no separate audio generation needed.
Director-level control Granular control over camera movement, lighting, shadows, and character performance through natural language prompts.
Production-grade cinematic quality Hollywood-grade visual fidelity with dramatic lighting, professional color grading, and smooth natural motion.
Exceptional motion stability Industry-leading motion coherence with stable subjects, consistent physics, and fluid transitions.
Strong instruction adherence Accurately follows detailed scene descriptions, shot compositions, and creative direction.
| Parameter | Required | Description |
|---|---|---|
| prompt | Yes | Detailed description of the cinematic scene |
| aspect_ratio | No | Output format: 16:9 (default), 9:16, 4:3, 3:4, 1:1, 21:9 |
| duration | No | Video length in seconds: 4-15 (default: 5) |
| resolution | No | Output resolution: 480p, 720p (default), 1080p, or 4k |
| enable_web_search | No | Enable web search for real-time information (default: false) |
| generate_audio | No | Generate synchronized audio for the output video (default: true) |
| reference_images | Conditional | Reference image URLs to guide style, characters, or composition |
| reference_videos | Conditional | Reference video URLs (up to 3). Each reference video is normalized to at least 2 seconds, each clip and the combined input are capped at 15 seconds, and the normalized combined input duration is rounded up to a whole second for billing. |
| reference_audios | Conditional | Reference audio URLs (total length must not exceed 15 seconds) |
Pricing is calculated upfront using your selected duration, plus reference-video charges when applicable.
Output-only pricing:
| Resolution | Per second | 5 seconds | 10 seconds | 15 seconds |
|---|---|---|---|---|
| 480p | $0.12 | $0.60 | $1.20 | $1.80 |
| 720p | $0.24 | $1.20 | $2.40 | $3.60 |
| 1080p | $0.60 | $3.00 | $6.00 | $9.00 |
| 4k | $1.20 | $6.00 | $12.00 | $18.00 |
Prices scale linearly with requested generation duration from 4 to 15 seconds.
Normalized reference-video duration and requested generation duration use the same per-second rate:
| Resolution | Per second |
|---|---|
| 480p | $0.075 |
| 720p | $0.15 |
| 1080p | $0.375 |
| 4k | $0.75 |
Each reference video is normalized to at least 2 seconds, each clip and the combined input are capped at 15 seconds, and the normalized combined input duration is rounded up to a whole second for billing.
Example: 5 seconds of normalized reference input plus 5 seconds of output costs $0.75 at 480p, $1.50 at 720p, $3.75 at 1080p, or $7.50 at 4k.
Notice: Use @Image 1, @Image 2, @Audio 1, etc. to reference your uploaded assets. Number each type separately, in upload order.
Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/bytedance/seedance-2.0/reference-to-video with your input as JSON. The endpoint returns a prediction id. Start polling the result endpoint around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. On completed, read output values from data.outputs. Examples for Seedance 2.0 Reference To Video below.
set -euo pipefail
: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"
REQUEST_BODY=$(cat <<'JSON'
{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"aspect_ratio": "16:9",
"resolution": "720p",
"duration": 5,
"enable_web_search": false,
"generate_audio": true
}
JSON
)
# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
-X POST "https://api.wavespeed.ai/api/v3/bytedance/seedance-2.0/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="https://api.wavespeed.ai/api/v3/predictions/$PREDICTION_ID/result"
# 2. Poll until the prediction finishes.
while true; do
RESPONSE=$(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' "$RESULT" | jq '.outputs'; break ;;
failed|cancelled|timeout|deleted) printf '%s\n' "$RESULT" | jq . >&2; exit 1 ;;
*) sleep 2 ;;
esac
doneconst submitUrl = "https://api.wavespeed.ai/api/v3/bytedance/seedance-2.0/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 ${apiKey}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"aspect_ratio": "16:9",
"resolution": "720p",
"duration": 5,
"enable_web_search": false,
"generate_audio": true
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = `https://api.wavespeed.ai/api/v3/predictions/${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", "deleted"].includes(result.status)) throw new Error(JSON.stringify(result));
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",
"resolution": "720p",
"duration": 5,
"enable_web_search": False,
"generate_audio": True
}
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/bytedance/seedance-2.0/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 = 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", "deleted"}:
raise RuntimeError(result)
time.sleep(2)Seedance 2.0 Reference To Video is a ByteDance model for reference-guided video generation, exposed as a REST API on WaveSpeedAI. Seedance 2.0 Reference to Video creates cinematic videos with native audio from your own reference images, videos, and audio, keeping characters, products, motion, and sound consistent while a prompt directs the new shot. Ready-to-use REST inference API, best performance, no coldstarts, 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 Python, JavaScript, and cURL examples for submitting requests and polling results. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/bytedance/bytedance-seedance-2.0-reference-to-video.
Seedance 2.0 Reference To Video starts at $0.24 per run or per second. 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`, `aspect_ratio`, `resolution`, `duration`, `reference_images`, `enable_web_search`. 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/bytedance/bytedance-seedance-2.0-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 (ByteDance). Check the provider's applicable terms and WaveSpeedAI's Terms of Service before commercial use.