
image-to-video
Idle
Your request will cost $0.8 per run.
For $10 you can run this model approximately 12 times.
One more thing:
Seedance 2.0 Fast is the speed-optimized version of ByteDance 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.
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.
| Parameter | Required | Description |
|---|---|---|
| images | Yes | Reference images for style/character guidance (max: 4) |
| prompt | Yes | Detailed description of the cinematic scene |
| duration | No | Video length: 5 (default), 10, or 15 seconds |
| Duration | Cost |
|---|---|
| 5 s | $0.80 |
| 10 s | $1.60 |
| 15 s | $2.40 |