The HuMo Video Generation workflow is designed to create high-quality videos that synchronize a character's lip movements with audio input. This workflow leverages the HuMo model, specifically tailored for human-centric video generation. By integrating various input modalities—text, images, and audio—it allows for a rich and customizable video output. The core of this workflow includes nodes like CLIPTextEncode for text processing, LoadImage for reference imagery, and AudioEncoderEncode for audio input. These are combined with video-specific nodes such as CreateVideo and SaveVideo to produce the final output. The WanHuMoImageToVideo node is particularly crucial as it bridges static images and dynamic video generation, ensuring that the character's lip movements align with the audio track. This workflow is ideal for creating engaging video content where precise lip-syncing and visual customization are required.
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.
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 "HuMo Video Generation" (TypeScript)
import { Comfy } from "@comfyorg/sdk";
const client = new Comfy({ apiKey: "comfyui-..." });
// This workflow, exported in API format (see note below)
const wf = await client.workflows.fromFile("video_humo_api.json");
const asset = client.assets.fromFile("input.png");
wf.setInput("49", "image", asset); // LoadImage
wf.setInput("6", "text", "A young boy in sci-fi style clothing is talking to the camera in an alien desert."); // CLIPTextEncode
const job = await client.run(wf);
await job.getOutputs("59")[0].toFile("output.png"); // SaveVideoThe 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.
FAQ
