ByteDance: Seedance 2.0 Fast – ListenHub

ByteDance: Seedance 2.0 Fast

Text to video
Image to video
First/last frame
Reference video

Seedance's low-latency lane. It is what the shared endpoint uses when you omit `model`, which also makes it the video line's default.

The input surface is identical to Pro — text, image, first/last frame, reference video. The one difference is that it cannot produce 1080p.

Strengths

The default on the shared generate endpoint
Same inputs as Pro: text, image, first/last frame, reference video
480p and 720p, 4 to 15 seconds

Limitations

No 1080p
No 4:5 or 5:4
Rate limited to 5 RPM

Capabilities

Capability

Call it

# Set LISTENHUB_API_KEY firstcurl -X POST "https://api.marswave.ai/openapi/v1/video-generation/generate" \-H "Authorization: Bearer $LISTENHUB_API_KEY" \-H "Content-Type: application/json" \-d '{"model": "doubao-seedance-2-fast","content": [{"type": "text","text": "A cinematic aerial shot of a quiet coastal city at sunrise"}]}'

ByteDance: Seedance 2.0 Fast

Strengths

Limitations

Capabilities

Specs and limits

How it is billed

Alternatives

Text to video	Yes
Image to video	Yes
First/last frame	Yes
Reference video	Yes
Native audio	No
Lip sync	No
Motion transfer	No