MuoGen · AI video model
Seedance 2.5 on MuoGen
Seedance 2.5 combines video durations up to 30 seconds with image, video and audio references in the MuoGen catalog.
Plan a video with image, video and audio references
Consider this model when your brief needs several kinds of references or an output longer than 15 seconds. Its reference counts and duration limits are separate constraints: check both before preparing your files.
Which settings are available?
| Model identifier | seedance-2.5 |
|---|---|
| Workflow | Video creation |
| Resolutions | 1080p, 720p, 480p |
| Initial resolution | 720p |
| Catalog video duration | 4–30 seconds |
| Catalog aspect ratios | 16:9, 9:16, 1:1, 4:3, 3:4, 21:9, adaptive |
| Accepted references | image: 30 maximum video: 10 maximum audio: 10 maximum |
| Maximum size per reference | image: 30 MB video: 200 MB audio: 15 MB |
| Maximum prompt length | 30000 characters |
| Audio on/off control | Exposed in the settings |
| Duration per video or audio reference | 2–30 seconds |
| Total reference duration | 30 seconds of video; separately, the same limit for audio |
These capabilities describe the settings exposed by MuoGen, not a guarantee of visual quality. Check the model and its settings in the workspace before preparing a request. Catalog checked on .
How do I prepare the prompt and references?
For a product scene, describe the product, setting, action and camera movement in separate sentences. Use image references for appearance, a video reference for the intended motion, and audio only when it contributes to the brief.
Example brief to adapt
A ceramic cup on a wooden table, warm window light. The camera moves slowly from left to right while steam rises. Keep the cup design consistent with the image reference.
This example is a preparation brief, not a generated result or a promise of output. Use only references you have the right to upload.
What limitations should I plan for?
Adding more references does not guarantee that every detail will be retained. State which reference controls the subject and which controls motion. The catalog also exposes a video extension workflow; extending and starting a new clip are different tasks.
Can I generate with this model today?
The catalog and settings are available to explore. Paid generation in the public browser workspaces is not yet open. When enabled, it will require a verified account and paid credits. Preparing a prompt or reading this guide does not start a generation.
Explore settings for Seedance 2.5
Compare and prepare your project
AI video preparation guide · MuoGen model catalog · Availability and frequently asked questions
- Seedance 2.5 Edit: Describe changes to an existing video
- Seedance 2.0: Prepare a short video with resolution and reference choices
- MiniMax H3: Plan a 4–15 second scene with multiple reference types
Updated: