What is the Z-Image Turbo model used for in this workflow?

The Z-Image Turbo model is used to convert text prompts into high-quality images, making it ideal for generating detailed visual content from descriptions.

How do I download the generated image?

Once the image is generated, locate it in the SaveImage node section. Right-click on the image and select 'Download' to save it to your device.

Can I add notes or instructions within the workflow?

Yes, you can use the MarkdownNote node to add annotations or instructions, which can help in organizing the workflow or providing additional context.

Is this workflow suitable for beginners?

Absolutely! This workflow is designed as an introductory guide to text-to-image generation, making it perfect for those new to AI-driven image creation.

1.1 Starter - Text to Image - ComfyUI Workflow

This ComfyUI workflow, titled '1.1 Starter - Text to Image,' is designed to introduce users to the basics of generating images from text prompts. It leverages the Z-Image Turbo model, known for its efficiency and quality in rendering detailed images from textual descriptions. The workflow includes key nodes such as the 932f407c-4ab6-4cd4-8567-d338b0eb6e18 for processing the text input and generating the image, a MarkdownNote for adding annotations or instructions, and a SaveImage node for saving the final output. By connecting these nodes, users can seamlessly transform text into a visual representation and download the results directly from the interface.

Technically, the workflow operates by taking a text input, processing it through the Z-Image Turbo model, and producing an image that reflects the input description. The MarkdownNote node allows users to add context or instructions within the workflow, enhancing usability and understanding. The SaveImage node is crucial for exporting the generated image, making it easy for users to download and utilize the output. This workflow is particularly useful for beginners looking to explore AI-driven image generation, offering a straightforward and intuitive process to create and save images based on text prompts.

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.

gsc_starter_1.json

Fetching workflow JSON…

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 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");

The 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.

SDK docs Get an API key

FAQ

Frequently Asked Questions