WHAT IT IS
Seedance is a video-generation model ByteDance released in December 2024, part of the Seed series. It supports text-to-video and image-to-video, produces clips of 5 or 10 seconds up to 1080p, and emphasises continuity across multiple shots and narrative quality. It is offered to developers through platforms such as Volcano Engine. The model does not release its weights.
Why it matters
It focused video generation on multi-shot continuity and narrative, representing the direction of short-video platform companies applying generative capabilities to content production.
Key specs
- Resolution
- Up to 1080p
- Duration
- 5 or 10 seconds
- Input
- Text, image
- Released
- 2024-12
- Open weights
- No
Capabilities
Related concepts
Diffusion Models
Learn a thousand tiny denoising steps, and you can build an image from pure noise
Multimodal Generation
One model that learns to speak, to draw, to move — even to model the 3D world
Training & Inference Infrastructure
Memory decides how large a model you can train, communication how long it takes — raw compute is rarely the bottleneck
Comparable products
Sora
2024Generates coherent video up to about a minute long from a description
Kling
2024A short-video model for both text-to-video and image-to-video
Hailuo
2024A short-video model focused on instruction following and camera language
Veo
2024Generates 1080p video clips with coherent shots