Seedance 2.0
ByteDanceSpecialized
Vision
About this model
Seedance 2.0 is a video generation model from ByteDance. It supports text-to-video, image-to-video with first and last frame control, and multimodal reference-to-video. It is particularly strong at preserving character consistency,...
Performance Tier
Specialized
Seedance 2.0 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 plansPremium
Highest cost level. A long conversation can quickly use up your included usage or your balance.
Capabilities
Context Length—
Max Output Tokens—
Inputtext, image
Outputvideo
Release DateApril 15, 2026
Recommended Use Cases
Creative Writing
Strengths
- Text-to-video and image-to-video handled by a single unified model
- Strong motion consistency across 4–15 second clips
- Native audio generation synchronized with the visual output
- Supports 480p, 720p, 1080p and 4K with 16:9, 9:16, 1:1 and other aspect ratios
Limitations
- Video generation only, with no text output, chat turn or tool calling
- Maximum duration of 15 seconds per generation
Frequently asked questions
Resources
This model may use your data for training
