Image To Image

When I first learned that actress/singer Irene Cara had transitioned I immediately opened up my Discord server and private channel in Midjourney. Using version 4 (v4) I uploaded to photos of Cara and a string of words that included “sfumato” and “art deco.” Learning art history is helpful as far…

Introduction Generative Adversarial Networks (GANs) were first introduced in 2014 by Ian Goodfellow et. al. and since then this topic itself opened up a new area of research. Within a few years, the research community came up with plenty of papers on this topic some of which have very interesting names…

Multimodal Image-to-Image Translation (Implementation in PyTorch) — Introduction Deep learning techniques have made rapid progress in conditional image generation. However, most techniques have focused on generating a single result. We aim to generate a distribution of output images given an input image. Mapping from a high-dimensional input to a high-dimensional output distribution is challenging. A common approach…

Image-to-image translation is the task of translating an image of a certain domain to another domain while preserving certain semantic content. There are largely two problems in image-to-image translation, which are learning from paired data and unpaired data. …

In this tutorial we will replace Adaptive Instance Normalization(AdaIN) layers in StarGAN V2 model and train it on images with a resolution 512x512 pixels. — Why StarGAN V2? Today, there are many models for generating high-quality images. Specifically, for the attributes swapping task(in 2021), the best quality is given by models that are a further development of the StyleGAN, or obtained by distilling it, which requires significant computational time for training on new data domains. The proposed model…

Here’s a fun little side project about training a GAN to Christmasify images. The holiday season is almost here, and along with it comes the Christmas trees, the presents, and the Santa costumes. This got us at hasty.ai …