Bytedance Seedance V1 Lite Reference To Video

Bytedance Seedance V1 Lite Reference To Video

Playground

Try it 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.

Features

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

ParameterRequiredDescription
promptYesText description of the video action and scene.
reference_imagesYesUp to 4 reference images of subjects to include (upload or URL).
durationNoVideo length in seconds (default: 5).
camera_fixedNoFix camera position for stable shots.
seedNoSet for reproducibility; leave empty for random.

How to Use

  1. Write a prompt describing the action and scene you want. Use the Prompt Enhancer for AI-assisted optimization.
  2. Add reference images — upload up to 4 images of subjects (people, animals, objects) to include in the video.
  3. Set duration — choose how long you want the video to be.
  4. Enable camera_fixed (optional) — check this for a stable, static camera shot.
  5. Set a seed (optional) for reproducible results.
  6. Click Run and wait for your video to generate.
  7. 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

DurationPrice
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.

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",
  "reference_images": [
    "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg"
  ],
  "duration": 5,
  "camera_fixed": false
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/bytedance/seedance-v1-lite/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

ParameterTypeRequiredDefaultRangeDescription
promptstringYes-The positive prompt for the generation.
reference_imagesarray<string>Yes-1 ~ 4 itemsA list of images to use as style references. At least 1 image is required. max 4 images.
durationintegerNo52 ~ 12The duration of the generated media in seconds.
camera_fixedbooleanNofalse-Whether to fix the camera position.
seedintegerNo--The random seed to use for the generation. -1 means a random seed will be used.

Response Parameters

ParameterTypeDescription
codeintegerHTTP status code (e.g., 200 for success)
messagestringStatus message (e.g., “success”)
data.idstringUnique identifier for the prediction, Task Id
data.modelstringModel ID used for the prediction
data.outputsarrayOutput values, usually URL strings; some models return text strings or structured result objects (empty when status is not completed)
data.urlsobjectObject containing related API endpoints
data.urls.getstringURL to retrieve the prediction result
data.statusstringStatus of the task: created, processing, completed, or failed
data.created_atstringISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”)
data.errorstringError message (empty if no error occurred)
data.timingsobjectObject containing timing details
data.timings.inferenceintegerInference time in milliseconds

Result Request Parameters

ParameterTypeRequiredDefaultDescription
idstringYes-Task ID

Result Response Parameters

ParameterTypeDescription
codeintegerHTTP status code (e.g., 200 for success)
messagestringStatus message (e.g., “success”)
dataobjectThe prediction data object containing all details
data.idstringUnique identifier for the prediction
data.modelstringModel ID used for the prediction
data.outputsarray<string | object>Array of generated outputs (empty when status is not completed). Items are usually URL strings, but may be text strings or structured result objects, depending on the model.
data.urlsobjectObject containing related API endpoints
data.urls.getstringURL to poll for the prediction result
data.statusstringStatus: created, processing, completed, or failed
data.created_atstringISO timestamp of when the request was created
data.errorstringError message (empty if no error occurred)
data.timingsobjectObject containing timing details
data.timings.inferenceintegerInference time in milliseconds
© 2026 WaveSpeedAI. All rights reserved.