Seedance 2.5 - AI video generation with audio

Generate 30-second videos with synchronized audio, multimodal reference control, and precise editing using Seedance 2.5 in ComfyUI

Seedance 2.5 is ByteDance’s new-generation video creation model, launched on July 31, 2026. Building on the unified multimodal audio-video joint-generation architecture of Seedance 2.0, it shifts the focus from generating a single clip to completing a full creative work, with major breakthroughs in long-form storytelling, multimodal reference, and editing.

The model generates up to 30 seconds of high-quality audio-video in a single pass, with improved shot transitions and scene changes for stronger continuity in longer videos. It supports multiple rounds of extension, so creators can build multi-minute content with a consistent audiovisual language, bringing a complete story to life in one take. Image, audio, and motion quality are all improved over the previous generation, resulting in more natural, polished visuals.

To use the Partner Nodes, you need to ensure that you are logged in properly and using a permitted network environment. Please refer to the Partner Nodes Overview section of the documentation to understand the specific requirements for using the Partner Nodes.

Local users

Make sure your ComfyUI is updated.

• Download ComfyUI
• Update Guide

Workflows in this guide can be found in the Workflow Templates. If you can’t find them in the template, your ComfyUI may be outdated.

If nodes are missing when loading a workflow, possible reasons:

1. You are not using the latest ComfyUI version (Nightly version)
2. Some nodes failed to import at startup

Cloud users

• Cloud will update after ComfyUI stable release.

So, if you find any core node missing in this document, it might be because the new core nodes have not yet been released in the latest stable version. Please wait for the next stable release.

Key capabilities

• 30-second generation: Produces high-quality, 30-second audio-video clips in a single pass with multi-round extension
• Audio-video sync: Generates video and audio together, including dialogue and lip-synced speech
• Fully upgraded multimodal referencing: Accepts up to 30 reference images, 10 video clips, and 10 audio clips for character consistency, visual style, and motion rhythm control
• Precise editing: Offers timestamp-level control for targeted edits of video and audio, plus green screen and reference-based editing
• Multi-round extension: Extends clips to build multi-minute content with consistent audiovisual language
• Versatile use cases: Suited for brand films, episodic series, e-commerce content, product showcases, and character-driven short series

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.

Run Text-to-Video on Cloud

Try the Text-to-Video workflow instantly on Comfy Cloud.

Download Text-to-Video workflow

Download the workflow JSON.

A dedicated 1080p variant of this workflow is also available:

Run 1080p Text-to-Video on Cloud

Try the 1080p Text-to-Video workflow instantly on Comfy Cloud.

Download 1080p Text-to-Video workflow

Download the workflow JSON.

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.

Run Image-to-Video on Cloud

Try the Image-to-Video workflow instantly on Comfy Cloud.

Download Image-to-Video workflow

Download the workflow JSON.

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.

Run FLF2V on Cloud

Try the First-Last-Frame-to-Video workflow instantly on Comfy Cloud.

Download FLF2V workflow

Download the workflow JSON.

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.

Run Reference-to-Video on Cloud

Try the Reference-to-Video workflow instantly on Comfy Cloud.

Download Reference-to-Video workflow

Download the workflow JSON.

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.

Run Video Editing on Cloud

Try the Video Editing workflow instantly on Comfy Cloud.

Download Video Editing workflow

Download the workflow JSON.

Get started

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