In this paper, we have developed a general-purpose architecture, Vit-Gan, capable of performing most of the image-to-image translation tasks from semantic image segmentation to single image depth perception. This paper is a follow-up paper, an extension of generator based model [1] in which the obtained results were very promising. This opened the possibility of further improvements with adversarial architecture. We used a unique vision transformers-based generator architecture and Conditional GANs(cGANs) with a Markovian Discriminator (PatchGAN) (https://github.com/YigitGunduc/vit-gan). In the present work, we use images as conditioning arguments. It is observed that the obtained results are more realistic than the commonly used architectures.

Transformers gain huge attention since they are first introduced and have a wide range of applications. Transformers start to take over all areas of deep learning and the Vision transformers paper also proved that they can be used for computer vision tasks. In this paper, we utilized a vision transformerbased custom-designed model, tensor-to-image, for the image to image translation. With the help of self-attention, our model was able to generalize and apply to different problems without a single modification.

Generative Adversarial Nets are one of the most popular generative frameworks. In our work, we introduce the SequenceGAN, a method that can generate images based on a given caption by supplying the conditional sequential text input to the generator and the discriminator. Unlike other conditional methods, SequenceGAN uses recurrent layers for better context understanding. We also demonstrated SequenceGANs performance by applying it to the MNIST and Flickr 8k datasets.