Z-Image Turbo

Z-Image Turbo

ComfyUI-ready files for the Z-Image-Turbo text to image model, packaged by Comfy-Org, with workflows for text to image, upscaling and ControlNet. Built on the Tongyi-MAI original.

Made by Comfy-Org on Hugging Face. These notes are Mindket's, written from its model page and model card; the model's own files and license are on Hugging Face.

About

What it is: This repository holds ComfyUI-ready copies of Tongyi-MAI's Z-Image-Turbo model, repackaged by Comfy-Org. It includes the diffusion model in BF16, INT8 ConvRot and NVFP4 forms, a distill patch LoRA, three Qwen 3 4B text encoders and the VAE. Four ready-made ComfyUI workflows are listed.

Who it suits: ComfyUI users who want to generate images from text with Z-Image-Turbo and pick the model precision that fits their graphics card.

Industry | Who uses it | How they use it | Example
Design | Designers | Generate concept images from written prompts | A poster draft from a description
Marketing | Content teams | Produce quick visuals and upscale them to 2K | A social image enlarged for a banner
Art | Artists | Guide generation with a ControlNet workflow | A pose-guided illustration
Software | Developers | Test image generation in a node editor | A workflow wired to a script

If you do not use ComfyUI, you can skip it, since these files are packaged for that tool.

Where to use it:

• ComfyUI on Windows, macOS or Linux with Python
• The four Comfy-Org workflow templates for text to image, Int8 text to image, 2K upscaling and Fun Union ControlNet

Use case | Who | What they get back
Text to image | Image makers | A picture generated from a prompt
Int8 text to image | Users with limited memory | The same workflow using the INT8 model file
2K upscaling | Designers | A larger version of an existing image
ControlNet | Artists | Images guided by a control input

How to set it up:

• ComfyUI installed on your computer
• Python, to run the Hugging Face download tool
• Room for the model files you choose

1. Install the Hugging Face hub tools with pip.
2. Download the repository with the hf command.
3. Put the diffusion model file in diffusion_models and the LoRA in loras.
4. Put a text encoder in text_encoders and ae.safetensors in vae.
5. Open one of the workflows in ComfyUI.

pip install -U huggingface_hub
hf download Comfy-Org/Z-Image-Turbo

How to use it: Open ComfyUI, load the text to image workflow, point its loader nodes at your files, type a prompt and run it. Choose the Int8 workflow if you use the INT8 file.

Tool | What it does
Z-Image-Turbo Text to Image | Workflow that generates an image from a prompt
Z-Image-Turbo Int8 Text to Image | The same workflow with the INT8 model
Image Upscale Z-Image-Turbo 2K | Workflow that enlarges an image, with before and after
Z-Image-Turbo Fun Union ControlNet | Workflow that guides generation with a control image

Example: You load the text to image workflow, type a short description of a scene and run it. ComfyUI returns one generated picture of that scene.

For newcomers and experts: Start with the BF16 model file and the plain text to image workflow, and keep the first prompt short. Try the other precisions once you want to save memory.

The model comes in three forms, BF16, INT8 ConvRot and NVFP4. Text encoders come in three forms too, a plain one and FP4 mixed and FP8 mixed versions. A distill patch LoRA sits in its own folder. ComfyUI loads each part separately.

Place files in ComfyUI folders
Open a Z-Image-Turbo workflow
Type a prompt
Run the nodes
An image comes out

Good to know:

• License: Apache 2.0
• Cost to run: none named
• Data it reaches: downloads files from Hugging Face, then runs on your own machine in ComfyUI
• Not for: use outside ComfyUI, since the card describes only ComfyUI file placement

On Hugging Face, 13 November 2026

• Library: diffusion-single-file
• Downloads in the last 30 days: 9,688,728
• Likes: 1,030
• License: apache-2.0
• Based on: Tongyi-MAI/Z-Image-Turbo
• Quantized versions: 1
• Fine-tunes: 4
• Tags: diffusion-single-file, comfyui

Links

• Model: https://huggingface.co/Comfy-Org/Z-Image-Turbo
• Files: https://huggingface.co/Comfy-Org/Z-Image-Turbo/tree/main

Get the model

Download its files with Hugging Face's command line:

pip install -U huggingface_hub
hf download Comfy-Org/Z-Image-Turbo

Then follow the usage in its model card. Nothing in this kit runs by itself.