This ComfyUI tutorial workflow turns a single image into a high‑fidelity 3D asset using Meshy 7.1’s Ultra 4K geometry mode. Starting with LoadImage, your reference photo flows into MeshyImageToModelNode, which requests a dense reconstruction at Ultra 4K (4096³) so fine surface detail—like stitching, wood grain, or scales—becomes real mesh geometry, not just texture. The result is a detailed, production‑ready model ideal for props, products, and hero assets where close‑up fidelity matters.
After the base mesh is generated, the pipeline branches into post steps: MeshyRefineNode for cleanup/topology polishing, MeshyTextureNode for PBR texturing, and optional rigging/animation via MeshyRigModelNode and MeshyAnimateModelNode. Save3DAdvanced wraps up the process by exporting to formats like GLB/GLTF, OBJ, or FBX with control over scale and axis. The Meshy Toolset group (enable it with Ctrl+B) keeps the workflow modular—run only the nodes you need, skip what you don’t, and iterate quickly from one reference image to a polished 3D asset.
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 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");SDK 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）。
