97AI.PRO
← All models
✦

Seedance 2.5 Image to Video

seedance-2.5-image-to-videoCommercial use

Seedance 2.5 image-to-video animates a single opening frame. Use first_frame_url only (no reference_* fields) with aspect_ratio adaptive. Set first_frame_portrait_kind to skip for scene/background images to avoid portrait ingest.

💰Pricing: no reference video 31 credits / s (≈$0.1408), with reference video 1929 credits / 1M tokens (≈$8.7671), no reference video 70 credits / s (≈$0.3166), with reference video 1929 credits / 1M tokens (≈$8.7671), no reference video 172 credits / s (≈$0.7789), with reference video 2110 credits / 1M tokens (≈$9.589)
24H STATUS MONITORSuccess: 100%
No requests in the last 24h · Operational
Input
MODEL
Seedance 2.5 Image to Video
seedance-2.5-image-to-video
Single-frame image-to-video

Use first_frame_url only (no reference_* fields) with aspect_ratio adaptive. Mark portrait frames first_frame_portrait_kind: virtual; scene-only images use skip.

URL of the input image to animate, or asset://{assetId} after portrait ingest.

Portrait-library route: ingest hint for first_frame_url. Default skip (direct URL). Use virtual/real to upload portraits to the asset library.

Text prompt describing the video motion and style.

Generate synchronized audio with the video.

Return the generated video's last frame. Cannot be true when draft=true.

Output video resolution.

Must be adaptive — the direct route follows the input image aspect ratio for keyframe-driven tasks.

Video duration from 4 to 30 seconds, or -1 for automatic selection.

Video output format.

Enable online search for the generation.

Enable content safety checking.

Output
output type: video
Result will appear here.