The 'HY 3D: Image to Model' workflow in ComfyUI is a powerful tool designed to convert 2D images into detailed 3D models, complete with geometry and PBR (Physically Based Rendering) textures. This workflow leverages the Hunyuan3D model, known for its advanced capabilities in interpreting image data and generating accurate 3D representations. The process begins with the LoadImage node, which allows users to upload their desired image. The core transformation is handled by the TencentImageToModelNode, which processes the image data and constructs a 3D model. This node utilizes sophisticated algorithms to ensure that the resulting model maintains high fidelity to the original image's features.
Once the model is generated, the SaveGLB node is used to export the model in the GLB format, which is widely supported for 3D assets and ensures easy integration into various applications. Additionally, the Preview3D node provides a real-time visualization of the model, allowing users to inspect the geometry and textures before finalizing the output. This workflow is particularly useful for artists and developers looking to quickly prototype 3D assets from existing 2D designs, offering a seamless transition from concept to 3D model.
API
從程式碼使用此工作流
每個 Comfy 工作流都是一個 JSON 圖。下方的 payload 就是此工作流，與 ComfyUI 執行時完全相同 — 你可以從此 URL 取得、放入版本控制，或在 ComfyUI 載入並逐節點執行。
使用 Comfy SDK 以 TypeScript 或 Python 執行。相同程式碼可用於 Comfy Cloud 或你自架的 ComfyUI — 只需更改 base URL。
// Install (beta)
npm i @comfyorg/sdk
// Run "混元3D：圖生模型" (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("api_hunyuan3d_image_to_model_api.json");
const asset = client.assets.fromFile("input.png");
wf.setInput("1", "image", asset); // LoadImage
const job = await client.run(wf);
await job.getOutputs("14")[0].toFile("output.png"); // SaveGLBSDK 需使用 API 格式的工作流：請在 ComfyUI 開啟此工作流，並使用 檔案 → 匯出工作流（API）。
常見問題
