This ComfyUI workflow leverages the Qwen-Image model to generate images with advanced multilingual text rendering and editing capabilities. At the core of this workflow is the 20B MMDiT model, which is renowned for its ability to handle complex text-to-image tasks across multiple languages. The workflow integrates specific nodes such as SaveImage and MarkdownNote to facilitate the process of generating and saving high-quality images. The e5cfe5ba-2ae0-4bc4-869f-ab2228cb44d3 node is pivotal in managing the data flow and ensuring the model's outputs are accurately captured and stored. This setup is particularly useful for applications requiring precise text integration into images, such as multilingual advertising or educational content creation.
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 "تشي وين-صورة: نص إلى صورة" (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("image_qwen_image_api.json");
const job = await client.run(wf);
await job.getOutputs("60")[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.
الأسئلة الشائعة
