ByteDance

Seedance 2.5

ByteDanceSpecialized
Vision

About this model

Seedance 2.5 is a video generation model from ByteDance. It is suited for long-form storytelling, multimodal reference-based generation, video editing, and video extension. It supports first-frame and first-and-last-frame control, up...

Performance Tier

Specialized

Seedance 2.5 is a specialized model from ByteDance : built for a specific domain.

Domain-specific model. Optimized for a particular task such as code generation, image creation, or web search.

Pricing

This model is included in Elosia plans
Premium

Highest cost level. A long conversation can quickly consume your monthly cap.

Capabilities

Context Length
Max Output Tokens
Inputtext, image
Outputvideo
Release DateAugust 7, 2026

Recommended Use Cases

Creative Writing

Strengths

  • Thirty seconds with native audio in a single generation, with no splice
  • First-frame and last-frame image conditioning, to anchor the opening and the closing of a shot
  • Per-second duration granularity, 27 values from 4 to 30 seconds, set on the request
  • Video accepted as input, so an existing clip can be edited or extended instead of regenerated from scratch

Limitations

  • Capped at 720p output, with no 1080p or 4K render available
  • ByteDance acknowledges limits on the physical plausibility of complex motion and on the stability of scenes with several interacting subjects. No independent evaluation has been published either

Frequently asked questions

Resources

This model may use your data for training

Similar Models