Seedance V1 Lite Reference to Video | Fast Image-to-Video API

Seedance V1 Lite — Reference-to-Video

Seedance V1 Lite Reference-to-Video is an advanced multi-reference video generation model from that creates videos featuring subjects from your reference images. Upload up to 4 reference images of people, animals, or objects, and the model generates a coherent video with those subjects interacting based on your prompt.

Why It Stands Out

Multi-reference support: Add up to 4 reference images to include multiple subjects in your video.
Subject preservation: Maintains the identity and appearance of subjects from reference images.
Prompt-guided action: Describe how subjects should interact or move in the generated video.
Prompt Enhancer: Built-in AI-powered prompt optimization for better results.
Camera control: Option to fix camera position for stable, static shots.
Flexible duration: Generate videos of varying lengths based on your needs.
Reproducibility: Use the seed parameter to recreate exact results.

Parameters

Parameter	Required	Description
prompt	Yes	Text description of the video action and scene.
reference_images	Yes	Up to 4 reference images of subjects to include (upload or URL).
duration	No	Video length in seconds (default: 5).
camera_fixed	No	Fix camera position for stable shots.
seed	No	Set for reproducibility; leave empty for random.

How to Use

Write a prompt describing the action and scene you want. Use the Prompt Enhancer for AI-assisted optimization.
Add reference images — upload up to 4 images of subjects (people, animals, objects) to include in the video.
Set duration — choose how long you want the video to be.
Enable camera_fixed (optional) — check this for a stable, static camera shot.
Set a seed (optional) for reproducible results.
Click Run and wait for your video to generate.
Preview and download the result.

Best Use Cases

Character Animation — Animate portraits or character images in custom scenes.
Pet Videos — Create fun videos featuring your pets in imaginative scenarios.
Social Media Content — Generate engaging videos with multiple subjects interacting.
Storytelling — Bring characters together in narrative video clips.
Marketing & Advertising — Create product videos featuring specific items or mascots.
Creative Projects — Combine different subjects in unique, creative compositions.

Pricing

Duration	Price
5 seconds	$0.18
10 seconds	$0.36
15 seconds	$0.54
20 seconds	$0.72

Total cost = $0.18 × (duration / 5)

Pro Tips for Best Quality

Use clear, high-quality reference images with subjects well-visible.
For best results, use front-facing or 3/4 angle reference photos.
Be specific in your prompt about how subjects should interact.
Enable camera_fixed for professional-looking static shots.
When using multiple subjects, describe their relative positions and actions clearly.
Fix the seed when iterating to compare different prompt variations.

Notes

Maximum of 4 reference images per generation.
Ensure uploaded image URLs are publicly accessible.
Processing time varies based on duration and current queue load.
Please ensure your content complies with usage guidelines.

Seedance v1 Lite Reference To Video API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/bytedance/seedance-v1-lite/reference-to-video with your input as JSON. The endpoint returns a prediction id; poll the prediction endpoint until status flips to completed, then read the output URL from data.outputs[0]. Examples for Seedance v1 Lite Reference To Video below.

HTTP example

# Submit the prediction
curl -X POST "https://api.wavespeed.ai/api/v3/bytedance/seedance-v1-lite/reference-to-video" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $WAVESPEED_API_KEY" \
  -d '{
    "prompt": "A cinematic shot of a city at sunset, soft golden light",
    "duration": 5,
    "camera_fixed": false,
    "seed": 0
}'

# Response includes a prediction id. Poll for the result:
curl -X GET "https://api.wavespeed.ai/api/v3/predictions/{request_id}/result" \
  -H "Authorization: Bearer $WAVESPEED_API_KEY"

# When status is "completed", read the output from data.outputs[0].

Node.js example

// npm install wavespeed
const WaveSpeed = require('wavespeed');

const client = new WaveSpeed(); // reads WAVESPEED_API_KEY from env

const result = await client.run("bytedance/seedance-v1-lite/reference-to-video", {
        "prompt": "A cinematic shot of a city at sunset, soft golden light",
        "duration": 5,
        "camera_fixed": false,
        "seed": 0
});

console.log(result.outputs[0]); // → URL of the generated output

Python example

# pip install wavespeed
import wavespeed

output = wavespeed.run(
    "bytedance/seedance-v1-lite/reference-to-video",
    {
    "prompt": "A cinematic shot of a city at sunset, soft golden light",
    "duration": 5,
    "camera_fixed": false,
    "seed": 0
}
)

print(output["outputs"][0])  # → URL of the generated output

Seedance v1 Lite Reference To Video API — Frequently asked questions

What is the Seedance v1 Lite Reference To Video API?

Seedance v1 Lite Reference To Video is a ByteDance model for video generation from images, exposed as a REST API on WaveSpeedAI. Seedance v1 Lite converts 1 to 4 reference images into high-quality videos with reference-to-video image-to-video generation. 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 v1 Lite 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 prediction endpoint until status flips to "completed", then read the output URL from the result. The playground generates a ready-to-paste code sample in Python, JavaScript, or cURL for whatever inputs you've set. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/bytedance/bytedance-seedance-v1-lite-reference-to-video.

How much does Seedance v1 Lite Reference To Video cost per run?

Seedance v1 Lite Reference To Video starts at $0.18 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 Seedance v1 Lite Reference To Video accept?

Key inputs: `prompt`, `duration`, `seed`, `reference_images`, `camera_fixed`. 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-v1-lite-reference-to-video.

How long does Seedance v1 Lite Reference To Video take to generate?

Average end-to-end generation time on WaveSpeedAI is around 63 seconds per request — measured across recent runs. Queue time scales with global demand; live status is visible in the prediction record.

Can I use Seedance v1 Lite Reference To Video outputs commercially?

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

サンプルすべて表示

関連モデル

README