Video model · ByteDance
Seedance 2.5
Generate, edit, and extend video with multimodal references
What is Seedance 2.5?
Seedance 2.5 supports text, images, video, and audio references for video generation. Connect a single video and describe a continuation to extend the scene, or combine references to guide a new generation.
Capabilities
- Generate video from a text prompt
- Animate a still image into video
- Keep characters and products consistent with reference images
- Restyle and transform existing footage
Seedance 2.5 on Melius
Melius runs Seedance 2.5 alongside every other major image, video, audio, and text model, so you can use it alongside other models in your workflow — all on one infinite canvas. You only pay for what you generate.
Frequently asked questions
What is Seedance 2.5?
Seedance 2.5 supports text, images, video, and audio references for video generation. Connect a single video and describe a continuation to extend the scene, or combine references to guide a new generation.
How do I use Seedance 2.5 on Melius?
Melius is a node-based canvas: add a video node, pick Seedance 2.5 from the model picker, and connect it to whatever should feed it or follow it. You only pay for what you generate.