Z-Image-Fun-Lora-Distill

Model Card

Name	Description
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.

Model Features

• 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. In most cases, the Distill LoRA performs well; currently, the biggest issue is that it may make the generated results brighter.
• The purpose of this model is to provide fast generation compatibility for Z-Image derivative models, not to replace Z-Image-Turbo.

TODO

• Optimize the output brightness;
• Train a 4-step LoRA.

Results

Work itself

Output 25 steps	Output 8 steps

Output 25 steps	Output 8 steps

Output 25 steps	Output 8 steps

Output 25 steps	Output 8 steps

Work with Controlnet

Pose + Inpaint	Output 25 steps	Output 8 steps

Pose + Inpaint	Output 25 steps	Output 8 steps

Pose	Output 25 steps	Output 8 steps

Pose	Output 25 steps	Output 8 steps

Canny	Output	Output 8 steps

Depth	Output	Output 8 steps

Inference

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-8-Steps.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 ~ 0.8)