Bytedance Seedance V1 Lite T2V 1080p API Documentation

Bytedance Seedance V1 Lite T2V 1080p API Documentation

Playground

Seedance v1 Lite is a Text-to-Video model for coherent multi-shot 1080p videos with smooth, stable motion and faithful prompt adherence. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Create stunning 1080p Full HD videos from text with Seedance V1 Lite. This powerful text-to-video model excels at cinematic storytelling, dynamic camera work, and complex scene transitions — perfect for professional video content from pure imagination.

Why It Looks Great

• 1080p Full HD: Professional-grade resolution for high-quality output.
• Flexible duration: Generate 2 to 12 seconds of video.
• Cinematic storytelling: Excels at multi-shot sequences and scene transitions.
• Dynamic camera work: Supports POV shots, close-ups, and camera movements.
• Text rendering: Can incorporate on-screen text and graphics.
• Prompt Enhancer: Built-in tool to refine your descriptions automatically.

Parameters

How to Use

1. Write your prompt — describe scenes, camera movements, and transitions in detail.
2. Use Prompt Enhancer (optional) — click to automatically enrich your description.
3. Set aspect ratio — choose the format that fits your needs.
4. Set duration — select 2-12 seconds based on your scene complexity.
5. Run — click the button to generate.
6. Download — preview and save your video.

Pricing

Per 5-second billing based on duration.

Best Use Cases

• Cinematic Storytelling — Create multi-shot sequences with scene transitions.
• Sci-Fi & Futuristic Content — Generate robots, digital overlays, and tech visuals.
• Music Videos — Produce visually complex sequences for audio content.
• Marketing & Ads — Create professional 1080p video for campaigns.
• Concept Visualization — Bring complex storyboards to life.

Example Prompts

• “The scene begins with a robot’s footsteps over rubble. The camera moves to its head — a close-up of scanning optical lenses. Switch to its POV: a digital overlay scanning the city’s outline. Final frame: graffiti on a wall reading ‘HUMANITY?’ freezes in view.”
• “Drone shot ascending over a futuristic city at night, neon lights reflecting on wet streets, then diving between skyscrapers”
• “A hand opens an ancient book, pages flip magically, golden light emerges, camera pushes into the glowing text”
• “Time-lapse of flowers blooming in a garden, morning dew evaporating, butterflies arriving, soft golden hour light”
• “First-person view walking through a haunted mansion, flickering candles, shadows moving, door creaking open ahead”

Pro Tips for Best Results

• Seedance excels at multi-shot storytelling — describe scene transitions explicitly.
• Use cinematic language: “camera moves to”, “switch to POV”, “final frame”.
• Include specific visual details: “scanning optical lenses”, “digital overlay”.
• Longer durations (8-12s) work best for complex multi-scene sequences.
• Describe text or graphics you want on screen in quotes.
• 16:9 aspect ratio is ideal for cinematic content; 9:16 for social media.

Notes

• Duration can be precisely set from 2 to 12 seconds.
• 1080p resolution provides professional broadcast-quality output.
• Complex multi-shot prompts work best with longer durations.
• Processing time scales with duration and scene complexity.

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",
  "aspect_ratio": "16:9",
  "duration": 5,
  "camera_fixed": false,
  "seed": -1
}
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-t2v-1080p" \
  -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

Response Parameters

Result Request Parameters

Result Response Parameters