vumichien's picture
- huggan
- gan
- unconditional-image-generation
- huggan/few-shot-fauvism-still-life
# See a list of available tags here:
# task: unconditional-image-generation or conditional-image-generation or image-to-image
license: mit
# Generate fauvism still life image using FastGAN
## Model description
[FastGAN model]( is a Generative Adversarial Networks (GAN) training on a small amount of high-fidelity images with minimum computing cost. Using a skip-layer channel-wise excitation module and a self-supervised discriminator trained as a feature-encoder, the model was able to converge after some hours of training for either 100 high-quality images or 1000 images datasets.
This model was trained on a dataset of 124 high-quality Fauvism painting images.
#### How to use
# Clone this model
git clone
def load_generator(model_name_or_path):
generator = Generator(in_channels=256, out_channels=3)
generator = generator.from_pretrained(model_name_or_path, in_channels=256, out_channels=3)
_ = generator.eval()
return generator
def _denormalize(input: torch.Tensor) -> torch.Tensor:
return (input * 127.5) + 127.5
# Load generator
generator = load_generator("huggan/fastgan-few-shot-fauvism-still-life")
# Generate a random noise image
noise = torch.zeros(1, 256, 1, 1, device=device).normal_(0.0, 1.0)
with torch.no_grad():
gan_images, _ = generator(noise)
gan_images = _denormalize(gan_images.detach())
save_image(gan_images, "sample.png", nrow=1, normalize=True)
#### Limitations and bias
* Converge faster and better with small datasets (less than 1000 samples)
## Training data
## Generated Images
![Example image](example.png)
### BibTeX entry and citation info
title={Towards Faster and Stabilized GAN Training for High-fidelity Few-shot Image Synthesis},
author={Bingchen Liu, Yizhe Zhu, Kunpeng Song, Ahmed Elgammal},