{"id":168501,"date":"2023-06-08T16:00:00","date_gmt":"2023-06-08T15:00:00","guid":{"rendered":"https:\/\/liora.io\/en\/?p=168501"},"modified":"2026-02-06T09:01:48","modified_gmt":"2026-02-06T08:01:48","slug":"edit-your-photos-at-will-with-drag-your-gan","status":"publish","type":"post","link":"https:\/\/liora.io\/en\/edit-your-photos-at-will-with-drag-your-gan","title":{"rendered":"Edit Your Photos at Will With Drag Your GAN"},"content":{"rendered":"<style>\n.elementor-heading-title{padding:0;margin:0;line-height:1}.elementor-widget-heading .elementor-heading-title[class*=elementor-size-]>a{color:inherit;font-size:inherit;line-height:inherit}.elementor-widget-heading .elementor-heading-title.elementor-size-small{font-size:15px}.elementor-widget-heading .elementor-heading-title.elementor-size-medium{font-size:19px}.elementor-widget-heading .elementor-heading-title.elementor-size-large{font-size:29px}.elementor-widget-heading .elementor-heading-title.elementor-size-xl{font-size:39px}.elementor-widget-heading .elementor-heading-title.elementor-size-xxl{font-size:59px}<\/style>\n<p><strong>With the advent of generative artificial intelligence, creative work are automated. Recently, a group of researchers created Drag Your GAN, an AI model capable of retouching images at will.<\/strong><\/p>\n<h3>What Is Drag Your GAN?<\/h3>\n<p>Drag Your GAN is a <a href=\"https:\/\/liora.io\/en\/all-about-deep-learning\" target=\"_blank\" rel=\"noopener\">deep learning AI model<\/a> called <b>Generative Adversarial Networks (GAN)<\/b>. Created by AI researchers from Google, the Max Planck Institute and MIT CSAIL, this team has devised an approach to dot-based modifications of <b>realistic images<\/b>.&nbsp;<\/p>\n<p>To achieve this, <a href=\"https:\/\/liora.io\/en\/deep-neural-network-what-is-it-and-how-is-it-working\" target=\"_blank\" rel=\"noopener\">DYG uses two deep neural networks<\/a>, a generator and a discriminator, which work in opposition to each other to generate new synthetic images compared with the original. Besides these neural networks, the researchers designed DYG based on <a href=\"https:\/\/github.com\/XingangPan\/DragGAN\" target=\"_blank\" rel=\"noopener\">latent code optimization<\/a>, which enables them to move the image to the indicated location, while preserving its proportions and structure.<\/p>\n<p>Currently in the testing phase, the group hopes to extend its model to <b>3D modifications<\/b> in the coming months.<\/p>\n<style>\n.elementor-widget-image{text-align:center}.elementor-widget-image a{display:inline-block}.elementor-widget-image a img[src$=\".svg\"]{width:48px}.elementor-widget-image img{vertical-align:middle;display:inline-block}<\/style>\n<p>\t\t\t\t\t\t\t\t\t\t\t\t<img decoding=\"async\" width=\"800\" height=\"231\" src=\"https:\/\/liora.io\/app\/uploads\/sites\/9\/2023\/06\/Capture-1024x296.png\" alt=\"\" loading=\"lazy\" srcset=\"https:\/\/liora.io\/app\/uploads\/sites\/9\/2023\/06\/Capture-1024x296.png 1024w, https:\/\/liora.io\/app\/uploads\/sites\/9\/2023\/06\/Capture-300x87.png 300w, https:\/\/liora.io\/app\/uploads\/sites\/9\/2023\/06\/Capture-768x222.png 768w, https:\/\/liora.io\/app\/uploads\/sites\/9\/2023\/06\/Capture.png 1287w\" sizes=\"(max-width: 800px) 100vw, 800px\"><\/p>\n<h3>How does Drag Your GAN work?<\/h3>\n<p><a href=\"https:\/\/vcai.mpi-inf.mpg.de\/projects\/DragGAN\/\" target=\"_blank\" rel=\"noopener\">DYG<\/a> is a futuristic <b>image editor<\/b>. Far from replacing Photoshop, it will enable users to transform their photos easily at will. All you have to do is select two points, the start and end zones, and <b>let the model do its thing<\/b>. As a pre-trained model, DYG can only modify so-called realistic images, such as photos of humans, landscapes or animals. But it can also <b>create textures<\/b> such as teeth or eyes from scratch.<\/p>\n<div style=\"width: 640px;\" class=\"wp-video\"><!--[if lt IE 9]><script>document.createElement('video');<\/script><![endif]-->\n<video class=\"wp-video-shortcode\" id=\"video-168501-1\" width=\"640\" height=\"360\" preload=\"metadata\" controls=\"controls\"><source type=\"video\/mp4\" src=\"https:\/\/vcai.mpi-inf.mpg.de\/projects\/DragGAN\/data\/DragGAN.mp4?_=1\" \/><a href=\"https:\/\/vcai.mpi-inf.mpg.de\/projects\/DragGAN\/data\/DragGAN.mp4\">https:\/\/vcai.mpi-inf.mpg.de\/projects\/DragGAN\/data\/DragGAN.mp4<\/a><\/video><\/div>\n<p>Building on their nascent success, GANs could well become <b>the next blockbuster technology<\/b> after generative AI. To carry out the research that will develop these next technologies, companies are investing heavily <b>in teams of data professionals<\/b>. So, if you&#8217;ve enjoyed this article and are considering a career in Data Science, don&#8217;t hesitate to check out <a href=\"https:\/\/liora.io\/en\/blog-en\" target=\"_blank\" rel=\"noopener\">our articles<\/a> or <a href=\"\/en\/courses\/data-ai\/\" target=\"_blank\" rel=\"noopener\">training offers<\/a> on Liora.<\/p>\n<p><i>Source : vcai.mpi-inf.mpg.de<\/i><\/p>\n","protected":false},"excerpt":{"rendered":"<p>With the advent of generative artificial intelligence, creative work are automated. Recently, a group of researchers created Drag Your GAN, an AI model capable of retouching images at will. What Is Drag Your GAN? Drag Your GAN is a deep learning AI model called Generative Adversarial Networks (GAN). Created by AI researchers from Google, the [&hellip;]<\/p>\n","protected":false},"author":74,"featured_media":168503,"comment_status":"open","ping_status":"open","sticky":false,"template":"elementor_theme","format":"standard","meta":{"_acf_changed":false,"editor_notices":[],"footnotes":""},"categories":[2433],"class_list":["post-168501","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-data-ai"],"acf":[],"_links":{"self":[{"href":"https:\/\/liora.io\/en\/wp-json\/wp\/v2\/posts\/168501","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/liora.io\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/liora.io\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/liora.io\/en\/wp-json\/wp\/v2\/users\/74"}],"replies":[{"embeddable":true,"href":"https:\/\/liora.io\/en\/wp-json\/wp\/v2\/comments?post=168501"}],"version-history":[{"count":1,"href":"https:\/\/liora.io\/en\/wp-json\/wp\/v2\/posts\/168501\/revisions"}],"predecessor-version":[{"id":206397,"href":"https:\/\/liora.io\/en\/wp-json\/wp\/v2\/posts\/168501\/revisions\/206397"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/liora.io\/en\/wp-json\/wp\/v2\/media\/168503"}],"wp:attachment":[{"href":"https:\/\/liora.io\/en\/wp-json\/wp\/v2\/media?parent=168501"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/liora.io\/en\/wp-json\/wp\/v2\/categories?post=168501"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}