README
Z-Image-Fun-Controlnet-Union-2.1
Model Card
| Name | Description |
|---|---|
| Z-Image-Fun-Controlnet-Union-2.1.safetensors | ControlNet weights for Z-Image. The model supports multiple control conditions such as Canny, Depth, Pose, MLSD, Scribble, Hed and Gray. This ControlNet is added on 15 layer blocks and 2 refiner layer blocks. |
| Z-Image-Fun-Controlnet-Union-2.1-lite.safetensors | Compared to the large version of the model, fewer layers have control added, resulting in weaker control conditions. This makes it suitable for larger control_context_scale values, and the generation results appear more natural. It is also suitable for lower-spec machines. |
| Z-Image-Fun-Controlnet-Tile-2.1.safetensors | A Tile model trained on high-definition datasets (up to 2048×2048) for super-resolution. |
| Z-Image-Fun-Controlnet-Tile-2.1-lite.safetensors | Applied control latents to fewer layers, resulting in weaker control. This allows for larger control_context_scale values with more natural results, and is also better suited for lower-spec machines. |
Model Features
- This ControlNet is added on 15 layer blocks and 2 refiner layer blocks (Lite models are added on 3 layer blocks and 2 refiner blocks). It supports multiple control conditions—including Canny, Depth, Pose, MLSD, Scribble, Hed and Gray can be used like a standard ControlNet.
- Inpainting mode is also supported. When using inpaint mode, please use a larger control_context_scale, as this will result in better image continuity.
- You can adjust control_context_scale for stronger control and better detail preservation. For better stability, we highly recommend using a detailed prompt. The optimal range for control_context_scale is from 0.65 to 1.00.
Results
| Inpaint | Output |
  |  |
| Pose + Inpaint | Output |
 |  |
| Pose | Output |
 |  |
| Pose | Output |
|  |
| Pose | Output |
 |  |
| Canny | Output |
 |  |
| HED | Output |
 |  |
| Depth | Output |
 |  |
| Gray | Output |
 |  |
| Low Resolution | High Resolution |
 |  |
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-Controlnet-Union-2.1.safetensors
│ └── 📦 Z-Image-Fun-Controlnet-Union-2.1-lite.safetensors
Then run the file examples/z_image_fun/predict_t2i_control_2.1.py and examples/z_image_fun/predict_i2i_inpaint_2.1.py.
Contributors
BU
bubbliiiing
8 commits
Similar repos
README
Z-Image-Fun-Controlnet-Union-2.1
Model Card
| Name | Description |
|---|---|
| Z-Image-Fun-Controlnet-Union-2.1.safetensors | ControlNet weights for Z-Image. The model supports multiple control conditions such as Canny, Depth, Pose, MLSD, Scribble, Hed and Gray. This ControlNet is added on 15 layer blocks and 2 refiner layer blocks. |
| Z-Image-Fun-Controlnet-Union-2.1-lite.safetensors | Compared to the large version of the model, fewer layers have control added, resulting in weaker control conditions. This makes it suitable for larger control_context_scale values, and the generation results appear more natural. It is also suitable for lower-spec machines. |
| Z-Image-Fun-Controlnet-Tile-2.1.safetensors | A Tile model trained on high-definition datasets (up to 2048×2048) for super-resolution. |
| Z-Image-Fun-Controlnet-Tile-2.1-lite.safetensors | Applied control latents to fewer layers, resulting in weaker control. This allows for larger control_context_scale values with more natural results, and is also better suited for lower-spec machines. |
Model Features
- This ControlNet is added on 15 layer blocks and 2 refiner layer blocks (Lite models are added on 3 layer blocks and 2 refiner blocks). It supports multiple control conditions—including Canny, Depth, Pose, MLSD, Scribble, Hed and Gray can be used like a standard ControlNet.
- Inpainting mode is also supported. When using inpaint mode, please use a larger control_context_scale, as this will result in better image continuity.
- You can adjust control_context_scale for stronger control and better detail preservation. For better stability, we highly recommend using a detailed prompt. The optimal range for control_context_scale is from 0.65 to 1.00.
Results
| Inpaint | Output |
| |
| Pose + Inpaint | Output |
| |
| Pose | Output |
| |
| Pose | Output |
| |
| Pose | Output |
| |
| Canny | Output |
| |
| HED | Output |
| |
| Depth | Output |
| |
| Gray | Output |
| |
| Low Resolution | High Resolution |
| |
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-Controlnet-Union-2.1.safetensors
│ └── 📦 Z-Image-Fun-Controlnet-Union-2.1-lite.safetensors
Then run the file examples/z_image_fun/predict_t2i_control_2.1.py and examples/z_image_fun/predict_i2i_inpaint_2.1.py.
Similar repos
Linked in READMEs
Contributors
BU
bubbliiiing
8 commits