This ComfyUI workflow is designed to transform a single image into a fully textured 3D model by generating three orthographic views. It leverages the power of the GeminiNanoBanana2 model to create accurate side and rear shots from your input image. These generated views are then processed using the TripoImageToModelNode to construct a 3D model. The workflow is structured into two main groups: Shots creation and 3D Model creation. The Shots creation group utilizes the LoadImage and BatchImagesNode to prepare and process the input image, while the 3D Model creation group employs the Meshy model to integrate these views into a coherent 3D structure. This workflow is particularly useful for artists and designers looking to quickly prototype 3D models from minimal input data.
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 "Generate 3D Model From Single Image" (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_mjm_image_to_3d_api.json");
const asset = client.assets.fromFile("input.png");
wf.setInput("1", "image", asset); // LoadImage
const job = await client.run(wf);
await job.getOutputs("25")[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
