Z-Image Turbo: Fast Uncensored Image Generation in ComfyUI

Z‑Image Turbo in ComfyUI is a fast, efficient, and uncensored AI image generator designed for low VRAM setups. This 6B‑parameter model delivers high-quality, photorealistic images quickly, making it perfect for hobbyists and professionals alike. In this tutorial, you’ll learn how to set up and use Z‑Image Turbo to create stunning AI images with minimal memory usage and maximum speed.

Before starting, make sure your system meets the hardware and software requirements to run Z‑Image Turbo in ComfyUI. This model is optimized for efficiency and can generate high-quality uncensored AI images even on modest GPUs. For most users, a 6-12 GB VRAM GPU is more than enough to run Z‑Image Turbo at standard resolutions with smooth performance. Cloud GPUs, like RunPod, also work well for lower-end setups.

Requirement 1: ComfyUI Installed

You’ll need ComfyUI installed either locally or on a cloud GPU service.

• Local Windows installation: Follow this guide:
  👉 How to Install ComfyUI Locally on Windows

• Cloud GPU (e.g., RunPod): If your GPU is limited, you can run ComfyUI in the cloud using a persistent network volume. Step-by-step instructions are available here:
  👉 How to Run ComfyUI on RunPod with Network Volume

Requirement 2: Update ComfyUI

Keeping ComfyUI updated ensures full compatibility with the latest workflows, nodes, and features.

For Windows Portable Users:

1. Open the folder: ...\ComfyUI_windows_portable\update

2. Double-click update_comfyui.bat

For RunPod Users:

ts
1 cd /workspace/ComfyUI && git pull origin master && pip install -r requirements.txt && cd /workspace

💡Keeping ComfyUI updated guarantees you have the latest features, bug fixes, and node compatibility.

Requirement 3: Download Models for Z‑Image Turbo

Download the following Z‑Image Turbo model files and place them in the correct directories inside ComfyUI:

Verify Folder Structure

Confirm that your folders and files are organized like this:

ts
1📁 ComfyUI/
2└── 📁 models/
3     ├── 📁 diffusion_models/
4     │     └── z_image_turbo_bf16.safetensors
5     ├── 📁 text_encoders/
6     │     └── qwen_3_4b.safetensors
7     └── 📁 vae/
8           └── ae.safetensors

Once all files are properly placed and organized, your environment is ready. With a Low VRAM GPU, you can comfortably generate uncensored AI images at standard resolutions without performance issues. Next, we’ll move on to downloading and loading the Z‑Image Turbo workflow in ComfyUI.

Now that your system and models are ready, it’s time to load the Z‑Image Turbo workflow into ComfyUI. This workflow contains all the necessary nodes, configurations, and settings to run Z‑Image Turbo efficiently for fast, uncensored image generation.

Step 1: Download the Workflow File

Start by downloading the workflow JSON file designed specifically for Z‑Image Turbo. This file includes all nodes, samplers, and model references pre-configured for smooth operation.

👉 Download Z‑Image Turbo ComfyUI Workflow JSON

Step 2: Load the Workflow in ComfyUI

Once downloaded:

1. Launch ComfyUI.

2. Drag and drop the JSON workflow file onto the canvas.

3. The workflow will automatically populate all required nodes, including the diffusion model, text encoder, VAE, samplers, and output nodes.

Now that your workflow is loaded, let’s run your first Z‑Image Turbo image generation. The great thing about this workflow is how simple it is — everything is handled in a single node.

Step 1: Add Your Prompt

In the Z‑Image Turbo node, type the prompt describing the image you want to generate. Be as detailed or creative as you like. For example, you can specify style, lighting, subject, or environment.

💡 Tip: Since Z‑Image Turbo is uncensored, you can freely explore creative or adult prompts.

Step 2: Configure Steps, Models & Image Size

• Steps: Set to 8 for fast and high-quality generation.

• Models: Select all the models you downloaded earlier:

  • z_image_turbo_bf16.safetensors (Diffusion Model)

  • qwen_3_4b.safetensors (Text Encoder)

  • ae.safetensors (VAE)

• Width & Height: Set the image dimensions to 1280 × 720 for a 16:9 aspect ratio.

That’s it! There’s no need for multiple nodes or complex configuration. With these settings, your Z‑Image Turbo workflow is ready to generate fast, uncensored, high-quality AI images.

Step 3: Run the Workflow

Click the Run button on the Z‑Image Turbo node to generate your image. In just a moment, your high-quality, uncensored AI image will appear. Take a look at the output and, if needed, tweak your prompt or steps and run it again. The workflow is fast and flexible, so you can iterate quickly until you achieve the exact result you want.

Prompt: Extreme close-up of a massive dragon soaring through the sky, wings spread wide, mid-air, head and snarling jaws dominating the frame. Fire blasts from its mouth, glowing embers and sparks trailing behind, swirling in the wind. Scales shimmer with sunlight, cracked and scorched textures highly detailed. Motion blur on wings and fiery breath emphasizes speed and dynamic flight. Clouds and smoke swirl around, distant medieval city rooftops barely visible below. Volumetric lighting and shadows highlight depth and intensity. Hyper-detailed 8K textures, cinematic aerial perspective, epic chaotic fantasy energy, airborne and terrifying close-up.

✨ This model is a beast — even on a 12 GB VRAM GPU, it generates stunning images quickly, making testing and experimentation effortless.

Here are some examples we generated while testing Z‑Image Turbo — this model is incredibly fast and versatile:

Example 1

Example 2

Example 3

Example 4

🔥 Alibaba is seriously cooking with these models! Can’t wait for Z-Image-Base & Z-Image-Edit to drop!

In this tutorial, you’ve learned how to set up and use Z‑Image Turbo in ComfyUI for fast, uncensored AI image generation. With its 6B parameters, low VRAM requirements, and single-node simplicity, this model makes creating high-quality images quick, efficient, and fun.

Whether you’re experimenting with fantasy, sci-fi, realistic portraits, or fully creative prompts, Z‑Image Turbo delivers stunning results while running smoothly even on a 6-12 GB VRAM GPU. Its speed and versatility make it perfect for rapid iteration and testing new ideas.

Now that your workflow is configured and your models are ready, you can explore your creativity freely, generate multiple variations, and truly leverage the full power of this uncensored AI image generator.