README.md

metadata

library_name: pytorch
tags:
  - dcgan

cryptopunks-gan

A DCGAN trained to generate novel Cryptopunks.

Check out the code by Teddy Koker here.

Generated Punks

Here are some punks generated by this model:

Usage

You can try it out yourself, or you can play with the demo.

To use it yourself - make sure you have torch, torchvision, and huggingface_hub installed. Then, run the following to generate a grid of 64 random punks:

import torch
from huggingface_hub import hf_hub_download
from torch import nn
from torchvision.utils import save_image


class Generator(nn.Module):
    def __init__(self, nc=4, nz=100, ngf=64):
        super(Generator, self).__init__()
        self.network = nn.Sequential(
            nn.ConvTranspose2d(nz, ngf * 4, 3, 1, 0, bias=False),
            nn.BatchNorm2d(ngf * 4),
            nn.ReLU(True),
            nn.ConvTranspose2d(ngf * 4, ngf * 2, 3, 2, 1, bias=False),
            nn.BatchNorm2d(ngf * 2),
            nn.ReLU(True),
            nn.ConvTranspose2d(ngf * 2, ngf, 4, 2, 0, bias=False),
            nn.BatchNorm2d(ngf),
            nn.ReLU(True),
            nn.ConvTranspose2d(ngf, nc, 4, 2, 1, bias=False),
            nn.Tanh(),
        )

    def forward(self, input):
        output = self.network(input)
        return output


model = Generator()
weights_path = hf_hub_download('nateraw/cryptopunks-gan', 'generator.pth')
model.load_state_dict(torch.load(weights_path, map_location=torch.device('cpu')))

out = model(torch.randn(64, 100, 1, 1))
save_image(out, "punks.png", normalize=True)