This ComfyUI workflow transforms a single frontal image into a detailed 3D model using advanced AI techniques. The workflow leverages the power of the Hunyuan3D model and the Qwen-Image-Edit model to reconstruct the back view of the subject, ensuring a consistent and realistic 3D representation. The process begins with the TencentImageToModelNode, which interprets the input image and prepares it for 3D modeling. The QwenMultiangleCameraNode then generates multiple angles of the subject, which are crucial for creating a comprehensive 3D model. The Preview3D node allows users to visualize the model before finalizing it, ensuring that any adjustments can be made prior to saving the output. This workflow is particularly useful for applications in virtual reality, gaming, and digital content creation, where accurate and high-quality 3D models are essential.
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 "Single Image to 3D model" (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("templates_shane_single_image_to_3d_model_api.json");
const asset = client.assets.fromFile("input.png");
wf.setInput("119", "image", asset); // LoadImage
const job = await client.run(wf);
await job.getOutputs("118")[0].toFile("output.png"); // SaveImageThe 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
