Why can’t I connect real-human images or videos directly to ByteDance2ReferenceNode?

For real-human content, the provider requires verified assets. Use ByteDanceCreateImageAsset and ByteDanceCreateVideoAsset to upload and verify media first. Then, supply the resulting asset IDs (and Group ID) to ByteDance2ReferenceNode for generation.

What is the Group ID and how should I use it?

The Group ID groups assets that belong to the same person. It’s auto-generated when you first verify an image or video via the Create Image/Video Asset nodes. Save it and reuse it when uploading additional assets of the same person to help backend recognition and keep your library organized.

What are the asset limits for this workflow?

Per the provider limits: up to 9 image assets, 3 video assets, and 3 audio assets per identity group. Stay within these limits when preparing your verified media.

Do I need to verify again for future projects?

No, not for the same assets. Save your Group ID and asset IDs in the Save IDs for future reuse section. You can reference them directly in ByteDance2ReferenceNode for subsequent generations without re-uploading.

Seedance2.0 Real Human: Image to Video

Seedance2.0 Real Human: Image to Video is a compliant, identity-verified image-to-video workflow built with ByteDance partner nodes in ComfyUI. It guides you through creating verified real-human assets first, then generating a personalized video that transfers motion from a reference video to your identity photo. The verification step is handled by ByteDanceCreateImageAsset and ByteDanceCreateVideoAsset, which turn your uploaded portrait and reference video into reusable asset IDs and a shared Group ID that ties same-person assets together for backend recognition.

Once assets are approved and IDs are available, ByteDance2ReferenceNode performs the image-to-video generation using those IDs (instead of raw media) to meet the provider’s legal requirements. PreviewAny lets you quickly check intermediate info or the final clip, and SaveVideo writes the result to disk. LoadImage and LoadVideo handle local file inputs, while the MarkdownNote provides in-graph guidance. The workflow also includes a Save IDs for future reuse section so you can store and reuse your Group ID and asset IDs, avoiding repeat uploads for the same person. Asset limits apply (images up to 9, videos up to 3, audio up to 3).

API

Use this workflow from code

Every Comfy workflow is a JSON graph. The payload below is this workflow, exactly as ComfyUI runs it — fetch it from the URL, keep it in version control, or load it in ComfyUI and run it node by node.

d4b951896b54.json

Fetching workflow JSON…

Run it from TypeScript or Python with the Comfy SDK. The same code targets Comfy Cloud or a ComfyUI you host yourself — only the base URL changes.

// Install (beta)
npm i @comfyorg/sdk

// Run this workflow (TypeScript)
import { Comfy } from "@comfyorg/sdk";

const client = new Comfy({ apiKey: "comfyui-..." });
const wf = await client.workflows.fromFile("workflow_api.json");
const job = await client.run(wf);
await job.getOutputs("<output-node-id>")[0].toFile("output.png");

The SDK takes a workflow in API format: open this workflow in ComfyUI and use File → Export Workflow (API).

Comfy Cloud API access requires a plan with an API key.

SDK docs Get an API key

FAQ