alibaba-pai/Z-Image-Turbo-Fun-Controlnet-Union

Z-Image-Turbo-Fun-Controlnet-Union


News

The new control model with more control blocks and inpaint mode is released.

Model Features

• —This ControlNet is added on 6 blocks.
• —The model was trained from scratch for 10,000 steps on a dataset of 1 million high-quality images covering both general and human-centric content. Training was performed at 1328 resolution using BFloat16 precision, with a batch size of 64, a learning rate of 2e-5, and a text dropout ratio of 0.10.
• —It supports multiple control conditions—including Canny, HED, Depth, Pose and MLSD can be used like a standard ControlNet.
• —You can adjust controlcontextscale for stronger control and better detail preservation. For better stability, we highly recommend using a detailed prompt. The optimal range for controlcontextscale is from 0.65 to 0.80.

TODO

• —[ ] Train on more data and for more steps.
• —[ ] Support inpaint mode.

Results

<table border="0" style="width: 100%; text-align: left; margin-top: 20px;"> <tr> <td>Pose</td> <td>Output</td> </tr> <tr> <td><img src="asset/pose2.jpg" width="100%" /></td> <td><img src="results/pose2.png" width="100%" /></td> </tr> </table>

<table border="0" style="width: 100%; text-align: left; margin-top: 20px;"> <tr> <td>Pose</td> <td>Output</td> </tr> <tr> <td><img src="asset/pose.jpg" width="100%" /></td> <td><img src="results/pose.png" width="100%" /></td> </tr> </table>

<table border="0" style="width: 100%; text-align: left; margin-top: 20px;"> <tr> <td>Canny</td> <td>Output</td> </tr> <tr> <td><img src="asset/canny.jpg" width="100%" /></td> <td><img src="results/canny.png" width="100%" /></td> </tr> </table>

<table border="0" style="width: 100%; text-align: left; margin-top: 20px;"> <tr> <td>HED</td> <td>Output</td> </tr> <tr> <td><img src="asset/hed.jpg" width="100%" /></td> <td><img src="results/hed.png" width="100%" /></td> </tr> </table>

<table border="0" style="width: 100%; text-align: left; margin-top: 20px;"> <tr> <td>Depth</td> <td>Output</td> </tr> <tr> <td><img src="asset/depth.jpg" width="100%" /></td> <td><img src="results/depth.png" width="100%" /></td> </tr> </table>

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/DiffusionTransformer and models/PersonalizedModel.

📦 models/
├── 📂 Diffusion_Transformer/
│   └── 📂 Z-Image-Turbo/
├── 📂 Personalized_Model/
│   └── 📦 Z-Image-Turbo-Fun-Controlnet-Union.safetensors

Then run the file examples/z_image_fun/predict_t2i_control.py.