Content

This article introduces the usage of Z-Image-Turbo in conjunction with ComfyUI.

Advantages of Z-Image-Turbo:

  1. Strong Chinese prompt-following and Chinese character generation capabilities.
  2. Requires only 8 inference steps for image generation. With a compact 6B parameter count, it can run on consumer-grade hardware (16GB VRAM) using quantization.

Due to network restrictions in certain regions that prevent the use of ComfyUI-Manager for automatic downloads, all file downloads are provided for manual installation.

Prerequisites

Configure ComfyUI. You will need to install ControlNet components. Additionally, you can install the llama-cpp-vlm extension to enable image-to-text interrogation based on Qwen3-VL. To view the generated text output, install comfyUI-custom-scripts.

  1. ControlNet Repository: Here
  2. Llama-cpp-vlm Repository: Here
  3. ComfyUI-custom-scripts Repository: Here

Note: The download link for the llama-cpp-python.whl plugin required by Llama-cpp-vlm is listed below along with the Qwen3-VL model download link.

Model Download Summary

  1. Z-image-turbo Triad: The download link includes both full-precision and quantized versions. During execution, you can select the quantized versions for diffusion_models and text_encoders to minimize VRAM usage. Place them into the ComfyUI directory as shown in the image: Download Link

directory-1

  1. ControlNet Base Model: ** Download Link**

directory-2

  1. ControlNet Human Pose Control Model: Requires body_pose_model.pth, hand_pose_model.pth, and facenet.pth: Download Link

directory-3

  1. ControlNet Depth Control Model: Download Link

directory-4

  1. Qwen3-VL Model + Wheel files for required plugins: Download Link and Wheel Download Please verify your system version and Python version before downloading.

directory-5

Common Workflow Setups

  1. Text-to-Image (txt2img)

workflow-1

  1. Image-to-Image (Canny Edge Detection)

workflow-2

  1. Image-to-Image (Human Pose Detection)

workflow-3

  1. Image-to-Image (Depth Detection)

workflow-4

  1. Image-to-Image (Inpainting / Masked Generation)

workflow-5

  1. Qwen3-VL Interrogation to Text-to-Image

workflow-6

Ready-to-Use Image Workflow Templates (Import directly after downloading)

Click here

  1. Basic Version

image-1

  1. ControlNet Version

image-2

  1. Qwen3-VL Interrogation Version

image-3