ByteDance Seedance 2.5
ByteDance's flagship multimodal video model — native synchronized audio, clips up to 30 seconds, and large reference sets for character and scene consistency.
Seedance 2.5 is a cloud video-generation model from ByteDance. It produces short video clips from a text prompt, a starting image, or by interpolating between a first and last frame. Clips run up to 30s at 1080p with a synchronized audio track. It also supports seed control and reference images. It runs through Runware, Replicate, OpenRouter, and ByteDance using your own API key, from about $0.2304 per second of output.
- Released
- 2 months ago (Jul 2026)
- Pricing
- $0.2304 per second
- Max resolution
- 1080p
- Aspect ratios
- 21:9, 16:9, 4:3 +3 more
- Clip length
- Up to 30s
- Audio
- Synchronized track
- Image-to-video
- Start & end frame + reference images
- Seed control
- Supported
Examples
Generated with Seedance 2.5 via Runware. The same two prompts run against every video model in the catalog (one landscape, one portrait), so the only thing that changes between two models’ clips is the model.
Camera motion, scene coherence over time
Fluid motion, fine detail, temporal stability
ByteDance
ByteDance's AI labs ship the Seedream image models and the Seedance video models, among other Doubao-branded research.
www.bytedance.com ↗