Seedance 2.5 Reference to Video API on WaveSpeedAI

Name: Seedance 2.5 Reference to Video
Brand: bytedance
SKU: bytedance/seedance-2.5/reference-to-video
Price: 0.36 USD
Availability: InStock

ExamplesView all

Use the woman, headphones, and studio from <Image 1>. Preserve her exact face, hairstyle, outfit, headphones, microphone, and original composition. She presses one ear cup closer and listens. A thin luminous waveform begins emerging physically from the headphones, floating through the air like a ribbon of light. The waveform moves toward the microphone and gently wraps around it. She follows it with her eyes, surprised but calm. The camera begins with the same clean framing as <Image 1> and slowly slides sideways to reveal the glowing waveform. Elegant science-fiction visual, clear subject, simple motion, polished cinematic lighting.

The woman in @Image 1 sits at a table in @Image 2, lifts her coffee, glances out the window, then turns to the camera and says: "Best part of my morning." Gentle handheld shot, warm daylight, soft cafe ambience.

Use the woman from <Image 1> and the black vintage coupe from <Image 2>. Preserve her exact face, hairstyle, red dress, jewelry, and body proportions, and preserve the vehicle’s body shape, black paint, headlights, chrome trim, wheels, and tinted windows. The woman leaves a glamorous evening party and walks alone toward the parked black coupe. Before she reaches it, the headlights turn on by themselves. She stops. The passenger door slowly opens. Instead of getting inside, she looks through the windshield and sees a bouquet of white flowers resting on the driver seat. Her expression changes when she recognizes them. The camera begins behind foreground party lights, tracks alongside her toward the car, then settles into a low cinematic angle for the reveal. Romantic mystery, elegant night cinematography, realistic reflections, restrained acting, sophisticated neo-noir atmosphere.

README

Seedance 2.5 Reference-to-Video

Seedance 2.5 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 2.5 Text-to-Video.

Why Choose This?

Reference-guided generation
Use reference images, videos, and audio to steer characters, products, composition, motion, and soundtrack.
Consistent subjects
Keep the same character, product, or scene across shots by attaching it as a reference.
Native audio generation
Generate synchronized audio together with the video in a single workflow.
Director-style prompt control
Control camera movement, lighting, performance, atmosphere, and visual style through prompts.
Flexible output settings
Choose aspect ratio, duration, resolution, and audio generation settings for different creative workflows.

Parameters

Parameter	Required	Description
prompt	Yes	Detailed description of the cinematic scene, action, camera movement, lighting, and mood.
aspect_ratio	No	Output aspect ratio: `16:9`, `9:16`, `4:3`, `3:4`, `1:1`, or `21:9`. Default: `16:9`.
duration	No	Video length in seconds. Range: `4–30`. Default: `5`.
resolution	No	Output resolution: `480p`, `720p`, `1080p`, or `4k`. Default: `720p`.
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 10). Each reference video is normalized to at least 2 seconds, each clip and the combined input are capped at 30 seconds, and the normalized combined input duration is rounded up to a whole second for billing.
reference_audios	Conditional	Reference audio URLs to guide soundtrack, ambience, or audio style. Total reference audio length must not exceed 30 seconds.

How to Use

Write your prompt — Describe the scene with cinematic detail, including subject, action, lighting, mood, camera movement, and style.
Choose aspect ratio — Use 16:9 for widescreen, 9:16 for vertical content, or another supported layout.
Set duration — Choose a video length from 4 to 30 seconds.
Choose resolution — Select 480p, 720p, 1080p, or 4k.
Add references optional — Use reference images for style or character guidance, reference videos for motion guidance, and reference audio for soundtrack direction.
Configure audio optional — Keep generate_audio enabled when synchronized audio is needed.
Submit — Generate the final video and retrieve the output URL.

Writing Effective Prompts

Most weak results come from thin prompts. Seedance reads a prompt like a shot list — the more you direct it, the more it delivers. Structure your prompt in three layers.

1. One-sentence summary

Open with a single line that fixes the essentials:

subject + setting + action + style + camera

A lone astronaut walks across a red desert at dusk, cinematic sci-fi, slow low-angle tracking shot.

2. Shot-by-shot timeline

For anything with a beginning, middle, and end, break the duration into timed segments (1-second granularity). Keep the timeline continuous — no gaps.

0-3s: The astronaut crests a dune, silhouetted against the setting sun. Slow push-in. 3-7s: They stop, turn to face the camera, and raise a hand to shield their eyes. Wind lifts red dust across the frame. 7-10s: Wide pull-back reveals a half-buried spaceship behind them. Warm rim light, long shadows.

Give each range enough to do but not too much — cramming a dozen actions into three seconds causes cuts or dropped beats.

3. Consistency notes

End with anything that should hold across the whole clip: camera style, lighting, color palette, atmosphere, audio.

Handheld feel throughout, shallow depth of field, warm golden-hour palette. Ambient wind and footsteps only — no music.

Camera language

Write these directly; the model understands them:

Shot size — extreme wide, wide, medium, medium close-up, close-up
Movement — push in, pull out, pan, track, follow, orbit, tilt up, handheld shake
Angle — low angle, overhead, eye-level, first-person
Techniques — one-shot / long take, dolly zoom, bullet time, speed ramp

For a niche term, add a plain-language gloss: "rack focus: the sharp foreground softens as the background comes into focus."

Referencing uploaded assets

When you attach images, videos, or audio, bind each one explicitly in the prompt by its upload order — @Image 1, @Video 1, @Audio 1 — and say what it's for. Don't rely on labels drawn inside the image itself.

"The knight in @Image 1 walks through the castle in @Image 2."
"Refer to @Video 1 for the camera movement only; keep its shot order."
"@Image 1 and @Image 2 are Character 1, voiced by @Audio 1."

When a reference is already accurate, just point to it — no need to re-describe it in detail.

Negative control

Positive descriptions work best, but you can suppress subtitles and audio:

"No subtitles."
"No BGM — ambient and action sounds only."
"No audio."

Weak vs. strong

	prompt
weak	`a cat playing`
strong	`A ginger cat pounces on a ball of yarn on a sunlit wooden floor. 0-2s: it crouches, tail flicking, eyes locked on the yarn. 2-5s: it springs forward and bats the yarn across the floor, then chases it out of frame. Low eye-level shot, slight handheld follow, warm afternoon light, shallow depth of field. Playful mood, soft ambient room tone, no music.`

Pricing

Without reference videos

Output-only pricing:

Resolution	Per second	5 seconds	10 seconds	15 seconds	30 seconds
480p	$0.18	$0.90	$1.80	$2.70	$5.40
720p	$0.36	$1.80	$3.60	$5.40	$10.80
1080p	$0.90	$4.50	$9.00	$13.50	$27.00
4k	$1.80	$9.00	$18.00	$27.00	$54.00

Prices scale linearly with output duration from 4 to 30 seconds.

With reference videos

Normalized reference-video duration and output duration use the same per-second rate:

Resolution	Per second
480p	$0.11
720p	$0.22
1080p	$0.55
4k	$1.10

Each reference video is normalized to at least 2 seconds, each clip and the combined input are capped at 30 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 $1.10 at 480p, $2.20 at 720p, $5.50 at 1080p, or $11.00 at 4k.

Best Use Cases

Cinematic video generation — Create polished video scenes from detailed text prompts.
Commercials and ads — Generate high-quality promotional clips, product scenes, and campaign visuals.
Social media content — Produce vertical, square, landscape, or ultra-wide short-form videos.
Concept visualization — Turn creative ideas into motion previews for pitching, planning, and storyboarding.
Reference-guided generation — Use images, videos, or audio to guide style, motion, characters, or soundtrack direction.
Music and audio-driven scenes — Generate clips with synchronized sound for music, ambience, or narrative moments.

Pro Tips

Write prompts like a film director, including subject, action, camera angle, lighting, atmosphere, and mood.
Use 16:9 for cinematic widescreen and 9:16 for vertical social content.
Include specific visual details such as lighting direction, color palette, environment, and camera movement.
Use reference images when character, product, or style consistency matters.
Use reference videos when motion, pacing, camera movement, or scene structure matters.
Use reference audio when soundtrack, ambience, or voice style matters.
Start with shorter durations for prompt testing, then increase duration once the direction is confirmed.
Use asset tags such as @Image 1, @Image 2, and @Audio 1 to reference uploaded assets in the prompt.
Reference video duration is rounded up, with a minimum of 2 seconds and a maximum of 30 seconds.

Related Models

Seedance 2.5 Image-to-Video — Generate video from a start image and prompt.
Seedance 2.5 Video Edit — Edit an existing video with a prompt.
Seedance 2.5 Video Extend — Extend an existing video with a new generated segment.
Seedance 2.0 Reference-to-Video — Previous-generation Seedance text-to-video model.

Seedance 2.5 Reference To Video API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/bytedance/seedance-2.5/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 Seedance 2.5 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",
    "aspect_ratio": "16:9",
    "resolution": "720p",
    "duration": 5,
    "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-2.5/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="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
done

Node.js example

const submitUrl = "https://api.wavespeed.ai/api/v3/bytedance/seedance-2.5/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 ${apiKey}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
        "prompt": "A cinematic shot of a city at sunset, soft golden light",
        "aspect_ratio": "16:9",
        "resolution": "720p",
        "duration": 5,
        "generate_audio": true
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = `https://api.wavespeed.ai/api/v3/predictions/${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));
}

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",
    "aspect_ratio": "16:9",
    "resolution": "720p",
    "duration": 5,
    "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-2.5/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 = 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 2.5 Reference To Video API — Frequently asked questions

What is the Seedance 2.5 Reference To Video API?

Seedance 2.5 Reference To Video is a ByteDance model for reference-guided video generation, exposed as a REST API on WaveSpeedAI. Seedance 2.5 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.

How do I call the Seedance 2.5 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 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-2.5-reference-to-video.

How much does Seedance 2.5 Reference To Video cost per run or per second?

Seedance 2.5 Reference To Video starts at $0.36 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.

What inputs does Seedance 2.5 Reference To Video accept?

Key inputs: `prompt`, `aspect_ratio`, `resolution`, `duration`, `reference_images`, `generate_audio`. 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-2.5-reference-to-video.

How do I get started with the Seedance 2.5 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 Seedance 2.5 Reference To Video outputs commercially?

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.

ExamplesView all

Related Models

README

Seedance 2.5 Reference-to-Video

Why Choose This?

Parameters

How to Use

Writing Effective Prompts

1. One-sentence summary

2. Shot-by-shot timeline

3. Consistency notes

Camera language

Referencing uploaded assets

Negative control

Weak vs. strong

Pricing

Without reference videos

With reference videos

Best Use Cases

Pro Tips

Related Models

Seedance 2.5 Reference To Video API — Quick start

Seedance 2.5 Reference To Video API — Frequently asked questions

More from ByteDance

More Reference to Video models