← All models
ByteDance · Video model
Seedance 2.0 Fast
bytedance/seedance-2.0-fast- Video
Seedance 2.0 Fast is a video generation model from ByteDance. It supports text-to-video, image-to-video with first and last frame control, and multimodal reference-to-video. It prioritizes generation speed and lower cost...
Specifications
- Durations
- 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15 s
- Resolutions
- 480p, 720p
- Aspect ratios
- 1:1, 3:4, 9:16, 4:3, 16:9, 21:9, 9:21
- Sizes
- 480x480, 480x640, 480x854, 640x480, 854x480, 1120x480, 720x720, 720x960, 720x1280, 720x1680, 960x720, 1280x720, 1680x720
- Start from an image
- first frame, last frame
- Edit a video
- yes, pass input_videos
- Audio
- native, on by default
- Seed
- supported
Use it
POST /api/v1/videos · MCP generate_video · get_video · full reference
# 1. submit (202 with id, token, poll_url)
curl https://omnirail.org/api/v1/videos \
-H "Authorization: Bearer $OMNIRAIL_KEY" -H "Content-Type: application/json" \
-d '{"model":"bytedance/seedance-2.0-fast","prompt":"a paper boat drifting down a rainy street, slow dolly in","duration":4,"resolution":"480p","aspect_ratio":"16:9","generate_audio":false}'
# 2. poll every ~30 s until status is "completed"
curl https://omnirail.org/api/v1/videos/$JOB_ID -H "Authorization: Bearer $OMNIRAIL_KEY"