Mixer AI
Seedance 2.0
A short scene with your character, motion and sound, with Mini, Fast and Pro versions to choose from.
When to choose it
Seedance 2.0 is useful when you know what a scene should feel like but words alone are not enough. Supply a character photo, a motion reference and a short brief. Use it for a product moment, pre-shoot planning or alternative takes of the same idea. Each clip runs from 4 to 15 seconds.
- Combine photos, video and audio, giving appearance, movement and sound their own references.
- First and last frames let you establish both the opening composition and the destination of the action.
Modes and settings
- Generate from text, first and last frames, or a set of references.
- In Mixer AI, Mini and Fast offer 480p and 720p; Pro adds 1080p and 4K.
- Reference mode accepts up to 9 photos, 3 videos and 3 audio files. Video and audio have separate total-duration limits.
Price in coins
| Version | Quality / size | Input | Coins / second |
|---|---|---|---|
| Mini | 480p | With video reference | ≈ 4.11 |
| Mini | 480p | Text or images | ≈ 6.5 |
| Mini | 720p | With video reference | ≈ 8.24 |
| Mini | 720p | Text or images | ≈ 13.44 |
| Fast | 480p | With video reference | ≈ 5.82 |
| Fast | 480p | Text or images | ≈ 9.93 |
| Fast | 720p | With video reference | ≈ 12.32 |
| Fast | 720p | Text or images | ≈ 20.24 |
| Pro | 480p | With video reference | ≈ 7.19 |
| Pro | 480p | Text or images | ≈ 11.81 |
| Pro | 720p | With video reference | ≈ 15.13 |
| Pro | 720p | Text or images | ≈ 24.77 |
| Pro | 1080p | With video reference | ≈ 37.27 |
| Pro | 1080p | Text or images | ≈ 61.32 |
| Pro | 4K | With video reference | ≈ 76.95 |
| Pro | 4K | Text or images | ≈ 125.04 |
Billing is per second, not per fixed-length clip. The rate is multiplied by the billable duration; the complete request total is rounded up to a whole coin once.
Without video input, billing uses the output duration. With a video reference, it uses input video time plus output time at the video-reference rate. Photos and audio do not add video seconds.
≈ marks a fractional rate rounded to two decimal places for display; billing uses full precision.
What you can make
- Work out a performance and camera path before filming.
- Build a short product scene from separate character and product references.
How to direct the result
- Give every file a job: this person, this product, this camera movement.
- Plan two or three connected actions for ten seconds, not an entire campaign story.
Example: a backpack in motion
10 seconds, one shot. The person in photo one walks left to right along a pale wall, wearing the backpack in photo two. Halfway through, they stop and turn their back to show the bag. Track beside them at shoulder height. Preserve the face, clothing, backpack shape and color. Soft daylight, footsteps and fabric rustling.
What to keep in mind
- Version and resolution are separate settings. Selecting Pro does not automatically select 1080p or 4K.
- Reference video adds billable time. A lower rate with video can still produce a larger total.
Sources
- Prices and availability — Mixer AI catalog, updated 2026-09-18.
- Official maker site: ByteDance
Model facts verified: 2026-09-10.
Guides and comparisons using this model
FAQ
Which version should I try first?
Start with Mini or Fast at 480p to check composition. Once the action works, compare Pro using the same brief.
Can one request produce 30 seconds?
No. The limit here is 15 seconds. Assemble a longer story from separate scenes or use a model with a longer duration.
Which version offers 4K?
Pro. Mini and Fast in Mixer AI offer 480p and 720p.
Do I need a photo?
No. Text mode starts without files. A photo helps when a specific appearance or composition matters.
Does a reference become the opening frame?
Not necessarily. References guide scene attributes; use Frame mode to anchor the opening image.
How do I reuse a character across clips?
Keep the reference photos, clothes and appearance description consistent. Check turns and occlusions; exact identity is not guaranteed.
What changes the price?
The coin rate per second depends on quality, mode and, for some models, sound. Multiply it by the billable duration. Where input video is charged, its duration also counts. The complete request total is rounded once.
Do I need a separate model subscription?
No. In Mixer AI, you top up one coin balance and use it for the tasks you need. You do not need a separate subscription to this model.