Bytedance Seedance 2.0 Fast Image To Video API Documentation

Bytedance Seedance 2.0 Fast Image To Video API Documentation

Playground

Seedance 2.0 Fast (Image-to-Video) generates cinematic videos from reference images and text prompts with native audio-visual synchronization, director-level control, and exceptional motion stability — optimized for faster generation at lower cost. Built on Seed’s unified multimodal architecture.

Features

Seedance 2.0 Fast is the speed-optimized version of Seed’s latest video generation model. The Image-to-Video mode generates cinematic videos from reference images and text prompts — faster and at 33% lower cost than the standard version, preserving the input image’s subject and composition while adding expressive motion with native audio.

Key Features

• Speed-optimized generation Faster processing for quick turnaround, perfect for iteration and prototyping.

• 33% lower cost $0.80 per 5 seconds vs $1.20 for the standard version.

• Image-faithful generation Preserves the reference image’s subject identity, composition, and style.

• Multi-image reference support Guide generation with up to 4 reference images.

• Native audio-visual synchronization Generates video with synchronized audio in a single pass.

• Director-level control Camera movement, lighting, and character performance controlled through prompts.

Parameters

How to Use

1. Upload a start image — provide an image to guide the video generation.
2. Write your prompt — describe the scene with cinematic detail.
3. Set duration — choose any duration from 4 to 15 seconds.
4. Run — submit and download your video.

Writing Effective Prompts

The input image sets the first frame — your prompt directs what happens from there. The clearer the motion and camera direction, the better the result.

1. Start from the frame

Describe the action that begins from your image: what the subject does, where it goes, how the camera moves. Don’t re-describe what’s already visible in the image — build on it.

The woman in the photo turns from the window and walks toward the camera; slow push-in, warm interior light.

2. Shot-by-shot timeline

For longer clips, break the motion into timed segments (1-second granularity), continuous, no gaps.

> 0-2s: She turns from the window, a faint smile forming. Camera holds. > 2-5s: She walks toward the lens and stops mid-frame; slow push-in, shallow focus. > 5-8s: She glances off-screen as light shifts from warm to cool. Handheld drift.

3. Consistency notes

Lock the look for the whole clip: camera style, lighting, palette, atmosphere, audio.

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

Pricing

Billing Rules

• Base rate (480p): $0.50 per 5 seconds
• 720p: 2x the 480p price
• 1080p: 5x the 480p price (2.5x the 720p price)
• 4k: 10x the 480p price (2x the 1080p price).
• Duration range: 4-15 seconds (continuous)

Best Use Cases

• Rapid Prototyping — Quickly iterate on image-to-video concepts.
• High-Volume Production — Cost-effective generation for large content libraries.
• Product Animation — Fast turnaround on product shot animations.
• A/B Testing — Generate multiple variations from the same reference image.

Pro Tips

• Use Fast for iteration, switch to standard Seedance 2.0 for final quality.
• Upload high-quality reference images for best subject preservation.
• Start with 5s to iterate, then extend once the look is right.

Notes

• Native audio generation included.
• Up to 4 reference images can be uploaded.
• Duration range: 4-15 seconds (continuous).
• Aspect ratio follows the input image composition.

Related Models

• Seedance 2.0 Image-to-Video — Standard version with highest quality.
• Seedance 2.0 Fast Text-to-Video — Fast text-guided video generation.
• Seedance 2.0 Text-to-Video — Standard text-guided video generation.

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",
  "image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
  "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-fast/image-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 "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${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' "${RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
  STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')

  case "${STATUS}" in
    completed) printf '%s\n' "${RESULT}" | jq '.outputs'; break ;;
    failed|cancelled|timeout|deleted) printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
    *) sleep 2 ;;
  esac
done

Parameters

Task Submission Parameters

Request Parameters

Response Parameters

Result Request Parameters

Result Response Parameters