Name	Description
Z-Image-Fun-Lora-Distill-2-Steps-2603.safetensors	A Distill LoRA for Z-Image that distills both steps and CFG. It requires only 2 steps instead of 8. Due to the random timesteps strategy, it is better adapted to sigmas below 0.500. The recommended sigma for the second step is between 0.800 and 0.500. A larger LoRA strength is recommended.
Z-Image-Fun-Lora-Distill-2-Steps-2603-ComfyUI.safetensors	ComfyUI version of Z-Image-Fun-Lora-Distill-2-Steps-2603.safetensors
Z-Image-Fun-Lora-Distill-4-Steps-2603.safetensors	A Distill LoRA for Z-Image that distills both steps and CFG. It requires only 4 steps instead of 8 steps. Due to the addition of a random timesteps strategy, it is better adapted to cases where sigmas are less than 0.500.
Z-Image-Fun-Lora-Distill-4-Steps-2603-ComfyUI.safetensors	ComfyUI version of Z-Image-Fun-Lora-Distill-4-Steps-2603.safetensors
Z-Image-Fun-Lora-Distill-8-Steps-2603.safetensors	A Distill LoRA for Z-Image that distills both steps and CFG. Compared to Z-Image-Fun-Lora-Distill-8-Steps-2602.safetensors, due to the addition of a random timesteps strategy, it is better adapted to cases where sigmas are less than 0.500.
Z-Image-Fun-Lora-Distill-8-Steps-2603-ComfyUI.safetensors	ComfyUI version of Z-Image-Fun-Lora-Distill-8-Steps-2603.safetensors

Name	Description
Z-Image-Fun-Lora-Distill-4-Steps-2602.safetensors	A Distill LoRA for Z-Image that distills both steps and CFG. Compared to Z-Image-Fun-Lora-Distill-8-Steps.safetensors, it requires only 4 steps instead of 8 steps, its colors are more consistent with the original model, and the skin texture is better.
Z-Image-Fun-Lora-Distill-4-Steps-2602-ComfyUI.safetensors	ComfyUI version of Z-Image-Fun-Lora-Distill-4-Steps-2602.safetensors
Z-Image-Fun-Lora-Distill-8-Steps-2602.safetensors	A Distill LoRA for Z-Image that distills both steps and CFG. Compared to Z-Image-Fun-Lora-Distill-8-Steps.safetensors, its colors are more consistent with the original model, and the skin texture is better.
Z-Image-Fun-Lora-Distill-8-Steps-2602-ComfyUI.safetensors	ComfyUI version of Z-Image-Fun-Lora-Distill-8-Steps-2602.safetensors
Z-Image-Fun-Lora-Distill-8-Steps.safetensors	This is a Distill LoRA for Z-Image that distills both steps and CFG. This model does not require CFG and uses 8 steps for inference.

• This is a Distill LoRA for Z-Image that distills both steps and CFG. It does not use any Z-Image-Turbo related weights and is trained from scratch. It is compatible with other Z-Image LoRAs and Controls.
• This model will slightly reduce the output quality and change the output composition of the model. For specific comparisons, please refer to the Results section.
• The purpose of this model is to provide fast generation compatibility for Z-Image derivative models, not to replace Z-Image-Turbo.

The 2602 model tends to produce blurry images with sigmas below 0.500, as the distillation model was not trained on certain steps. The 2603 model introduces a random timesteps strategy, making it better adapted to sigmas below 0.500.

As shown below, when using kl_optimal, many sigmas fall below 0.500. The 2603 model handles these cases correctly, while the 2602 model does not. Note that although kl_optimal is used in the figure, we still recommend using the simple scheduler for inference.

Z-Image-Fun-Lora-Distill-8-Steps-2602	Z-Image-Fun-Lora-Distill-8-Steps-2603

Z-Image-Fun-Lora-Distill-8-Steps-2602	Z-Image-Fun-Lora-Distill-4-Steps-2602	Z-Image-Fun-Lora-Distill-8-Steps

Output 25 steps	Output 8-Steps-2602	Output 4-Steps-2602

Output 25 steps	Output 8-Steps-2602	Output 4-Steps-2602

Output 25 steps	Output 8-Steps-2602	Output 4-Steps-2602

Output 25 steps	Output 8-Steps-2602	Output 4-Steps-2602

Pose + Inpaint	Output 25 steps	Output 8-Steps-2602	Output 4-Steps-2602

Pose + Inpaint	Output 25 steps	Output 8-Steps-2602	Output 4-Steps-2602

Pose	Output 25 steps	Output 8-Steps-2602	Output 4-Steps-2602

Canny	Output	Output 8-Steps-2602	Output 4-Steps-2602

Depth	Output	Output 8-Steps-2602	Output 4-Steps-2602

Go to the VideoX-Fun repository for more details.

Please clone the VideoX-Fun repository and create the required directories:

# Clone the code
git clone https://github.com/aigc-apps/VideoX-Fun.git

# Enter VideoX-Fun's directory
cd VideoX-Fun

# Create model directories
mkdir -p models/Diffusion_Transformer
mkdir -p models/Personalized_Model

Then download the weights into models/Diffusion_Transformer and models/Personalized_Model.

📦 models/
├── 📂 Diffusion_Transformer/
│   └── 📂 Z-Image/
├── 📂 Personalized_Model/
│   ├── 📦 Z-Image-Fun-Lora-Distill-4-Steps-2602.safetensors
│   ├── 📦 Z-Image-Fun-Lora-Distill-8-Steps-2602.safetensors
│   ├── 📦 Z-Image-Fun-Controlnet-Union-2.1.safetensors
│   └── 📦 Z-Image-Fun-Controlnet-Union-2.1-lite.safetensors

To run the model, first set the lora_path in examples/z_image/predict_t2i.py to: Personalized_Model/Z-Image-Fun-Lora-Distill-8-Steps.safetensors

Then, run the file: examples/z_image/predict_t2i.py

The following scripts are also supported:

• examples/z_image_fun/predict_t2i_control_2.1.py
• examples/z_image_fun/predict_i2i_inpaint_2.1.py

Recommended Settings:

• cfg = 1.0
• steps = 8
• lora_weight = 0.8 (suggested range: 0.7 ~ 0.9)