Z-Image-Turbo Model Setup Guide
a. Model Links and Storage Locations
Chunked loading is recommended as it better aligns with ComfyUI's standard workflow.
1. Chunked Loading Weights (Recommended)
For chunked loading, it is recommended to directly download the Z-Image weights provided by ComfyUI official. Please organize the files according to the following directory structure:
Core Model Files:
| Component | File Name |
|---|---|
| Text Encoder | qwen_3_4b.safetensors |
| Diffusion Model | z_image_turbo_bf16.safetensors |
| VAE | ae.safetensors |
| tokenizer(Qwen3-4B) | tokenizer |
ControlNet Model Files:
| Name | Hugging Face | Model Scope | Description |
|---|---|---|---|
| Z-Image-Turbo-Fun-Controlnet-Union | 🤗Link | 😄Link | ControlNet weights for Z-Image-Turbo, supporting multiple control conditions including Canny, Depth, Pose, MLSD, etc. |
| Z-Image-Turbo-Fun-Controlnet-Union-2.1 | 🤗Link | 😄Link | Upgraded ControlNet weights for Z-Image-Turbo with additions at more layers and longer training time, supporting multiple control conditions including Canny, Depth, Pose, MLSD, etc. |
Storage Location:
📂 ComfyUI/
├── 📂 models/
│ ├── 📂 text_encoders/
│ │ └── qwen_3_4b.safetensors
│ ├── 📂 diffusion_models/
│ │ └── z_image_turbo_bf16.safetensors
│ ├── 📂 vae/
│ │ └── ae.safetensors
│ ├── 📂 Fun_Models/
│ │ └── Qwen3-4B/
│ └── 📂 model_patches/
│ └── Z-Image-Turbo-Fun-Controlnet-Union.safetensors
2. Preprocessing Weights (Optional)
If you want to use the control preprocessing nodes, you can download the preprocessing weights to ComfyUI/custom_nodes/Fun_Models/Third_Party/.
Required Files:
| File Name | Download Link | Purpose |
|---|---|---|
yolox_l.onnx |
Download | YOLO Detection Model |
dw-ll_ucoco_384.onnx |
Download | DWPose Pose Estimation Model |
ZoeD_M12_N.pt |
Download | ZoeDepth Depth Estimation Model |
Storage Location:
📂 ComfyUI/
├── 📂 models/
│ └── 📂 Fun_Models/
│ └── 📂 Third_Party
│ ├── yolox_l.onnx
│ ├── dw-ll_ucoco_384.onnx
│ └── ZoeD_M12_N.pt
3. Full Model Loading (Optional)
If you prefer full model loading, you can directly download the diffusers weights.
Required Files:
| Name | Hugging Face | Model Scope | Description |
|---|---|---|---|
| Z-Image-Turbo | 🤗Link | 😄Link | Official full weights for Z-Image-Turbo |
For full model loading, use the diffusers version of Z-Image Turbo and place the model in ComfyUI/models/Fun_Models/.
Storage Location:
📂 ComfyUI/
├── 📂 models/
│ └── 📂 Fun_Models/
│ └── 📂 Z-Image-Turbo
b. ComfyUI Json Workflows
1. Chunked Loading (Recommended)
Z Image Turbo Text to Image and Control
Z Image Turbo Text to Image and Control with Pose Detect
Z Image Turbo Text to Image and Control with Depth Detect
Z Image Turbo Text to Image and Control with Canny Detect
Z Image Turbo Image to Image with Inpaint