Seedance 2.0 - AI video generation

Generate high-quality video from text, images, video, and audio with synced audio, consistent characters, and cinematic camera control using Seedance 2.0 in ComfyUI

Seedance 2.0 is ByteDance’s next-generation multimodal video generation model, now available inside ComfyUI. It accepts text, images, video, and audio as unified inputs and produces high-quality video with synced audio, consistent characters, and cinematic camera motion in a single pass.

Key capabilities

• Multimodal in — Prompt with text plus images, video, and audio
• Audio-video sync — Generate video and audio together
• Directing control — Camera moves and shot pacing stay controllable
• Consistency — Keep characters and scenes stable across a clip
• Editing + extend — Edit footage or extend clips without starting over

With these capabilities, Seedance 2.0 fits a wide range of use cases including advertising, short-form drama, film previsualization, product showcases, virtual character content, and assets for games and animation.

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

Portable or self deployed 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 If you can’t find them in the template, your ComfyUI may be outdated. (Desktop version’s update will delay sometime)

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

Desktop or Cloud users

• The Desktop is base on ComfyUI stable release, it will auto-update when there is a new Desktop stable release available.
• 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.

Available workflows

Text to video (T2V)

Generate a video from a text prompt, with Seedance 2.0 handling scene, motion, and pacing.

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.

Reference to video (R2V)

Use reference images, video, or audio to guide look, motion, and rhythm while keeping results coherent.

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.

First-last-frame to video (FLF2V)

Provide a starting frame and ending frame, and Seedance 2.0 generates the motion and transitions between them.

Run FLF2V on Cloud

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

Download FLF2V workflow

Download the workflow JSON.

Using real-person and AI-generated portraits in ComfyUI for Seedance 2.0

Seedance 2.0 supports both real-person portraits (imagery of actual people you use as likeness or on-camera reference) and AI-generated portraits (fictional on-screen subjects produced by AI, not depicting a specific real individual). Which path you use determines whether you need ByteDance liveness and identity checks.

	AI-generated portrait	Real-person portrait
What it refers to	The subject looks like an AI-synthesized character; it must not correspond to an identifiable natural person	You use portrait or appearance footage of a real person
Identity verification	No extra check	One-time ByteDance liveness (through ByteDance Create Image/Video Asset)
Workflow	Any standard Seedance 2.0 workflow (T2V, R2V, FLF2V)	Seedance 2.0 Real Human workflow with the ByteDance Create Image/Video Asset node

AI-generated portrait

Use the Seedance 2.0 node like any other generator: upload your AI-generated character image (or an equivalent reference), wire it up, and run.

After submission the service classifies the asset. If it is flagged as protected real-person-related content, the node returns an error — switch to the real-person portrait workflow below instead. Once the backend treats it as an AI portrait and the check clears, use it directly as reference with no extra verification steps.

Real-person portrait

Use the Real Human workflow (requires ByteDance Create Image/Video Asset): real likeness needs one liveness verification to deter impersonation and unauthorized use of someone’s likeness, and to comply with evolving AI transparency requirements.

First use (verification required)

1. Upload portrait imagery via ByteDance Create Image/Video Asset.
2. Run the workflow — a verification link is generated.
3. Open the link on your phone or browser and finish liveness (typically under ~30 seconds).
4. After verification succeeds you receive two IDs:
   • Group ID — the verified individual; retain it when uploading the same person again.
   • Asset ID — bound to this portrait; connect it for video generation and reuse across runs.

New photo or video of the same person (no repeat liveness)

1. Upload a new photo or video of that person.
2. Enter the saved Group ID on ByteDance Create Image/Video Asset.
3. The system compares the new face data with the original verification record; when it matches, the new asset activates automatically.

Seedance 2.0 Real Human

Full walkthrough, verification flow, and Real Human workflow templates.