Deep Convolutional Generative Adversarial Network (DCGAN)  which is an extension of the existing Generative Adversarial Networks (GANs) was applied to generate faces of animated characters. In the GAN framework, a “generator” network is tasked with fooling a “discriminator” network into believing that its own samples are real data. In DCGAN, max pooling is replaced with convolutional stride and transposed convolution is used for upsampling. DCGAN uses Deep Convolutional networks in place of fully connected networks of GAN.