Seedance 2.5 Workflows in ComfyUI

This guide shows how to run the Seedance 2.5 workflows in ComfyUI. For what the model is and what it does best, see the Seedance 2.5 overview.

​

Available workflows

​

Text to video (T2V)

Generate a 30-second cinematic video from a text prompt, with synchronized sound and music. The node supports 480p, 720p, and 1080p output resolution. A dedicated 1080p variant of this workflow is also available:

​

Image to video (I2V)

Animate a single image into a 1080p video clip with synchronized sound, music, and dialogue. The workflow supports clips up to 30 seconds across any aspect ratio, and takes a single image as its input.

​

First-last-frame to video (FLF2V)

Provide a starting frame and an ending frame, and Seedance 2.5 generates the motion and transitions between them, locking both endpoints.

​

Reference to video (R2V)

Use reference images, video clips, or audio to control character consistency, visual style, and motion rhythm in a single output with synchronized sound and lip-synced dialogue.

​

Video editing

Edit existing video clips by describing changes in natural language. Replace objects, swap backgrounds, change scenes, or transfer styles while preserving the original composition and motion. You can also extend an existing clip forward or backward. Connect the clip as the reference video, set the task_type option to extend, and describe the continuation in the prompt, for example “extend forward”, “extend backward”, or “continue”. The output contains only the newly generated segment at the duration you set, and its aspect ratio follows the source clip.

​

Get started

1. Update ComfyUI to the latest version
2. Go to Template Library, search for Seedance 2.5