|
|
--- |
|
|
license: mit |
|
|
tags: |
|
|
- gan |
|
|
- stylegan2 |
|
|
- discriminator |
|
|
- image-generation |
|
|
- nvidia |
|
|
- ffhq |
|
|
--- |
|
|
|
|
|
# StyleGAN2 Discriminator (FFHQ, NVIDIA) |
|
|
|
|
|
This model is the **discriminator** component of **StyleGAN2**, based on the original architecture introduced by NVIDIA and trained on the [FFHQ dataset](https://github.com/NVlabs/ffhq-dataset). The model is designed to distinguish between real and fake images, and is typically used in generative adversarial networks (GANs) for high-resolution face synthesis. |
|
|
|
|
|
## 🧩 Model Details |
|
|
|
|
|
- **Architecture**: StyleGAN2 Discriminator (NVIDIA) |
|
|
- **Framework**: PyTorch |
|
|
- **Trained on**: FFHQ (Flickr-Faces-HQ) |
|
|
- **Use case**: Discriminator in GAN training or standalone real/fake image classification |
|
|
|
|
|
## 🛠️ How to Use |
|
|
|
|
|
```python |
|
|
from huggingface_hub import hf_hub_download |
|
|
import torch |
|
|
|
|
|
# Download the model |
|
|
model_path = hf_hub_download(repo_id="mukhbiir/StyleGAN2_Discriminator", filename="model.pt") |
|
|
model = torch.load(model_path) |
|
|
model.eval() |
|
|
|
