{"id":14526,"date":"2021-04-05T08:02:00","date_gmt":"2021-04-05T15:02:00","guid":{"rendered":"http:\/\/jnack.com\/blog\/?p=14526"},"modified":"2022-04-18T21:14:18","modified_gmt":"2022-04-19T04:14:18","slug":"witchcraft-alert-my-new-adobe-team-enables-image-transformation-via-text","status":"publish","type":"post","link":"http:\/\/jnack.com\/blog\/2021\/04\/05\/witchcraft-alert-my-new-adobe-team-enables-image-transformation-via-text\/","title":{"rendered":"Witchcraft alert: My new Adobe team enables image transformation via text"},"content":{"rendered":"\n<p>Welcome to the rabbit hole, my friends. &#x1f643;<\/p>\n\n\n\n<p>What if instead of pushing pixels, you could simply <em>tell<\/em> your tools what changes you&#8217;d like to see? (Cue <a href=\"https:\/\/www.youtube.com\/watch?v=7W0EO6C2sFg\">Kramer voice<\/a>: &#8220;Why don&#8217;t you just <em>tell<\/em> me the movie&#8230;??&#8221;) This new <a href=\"https:\/\/arxiv.org\/abs\/2103.17249\">StyleCLIP technology<\/a> (<a href=\"https:\/\/github.com\/orpatashnik\/StyleCLIP\">code<\/a>) builds on NVIDIA&#8217;s <a href=\"https:\/\/en.wikipedia.org\/wiki\/StyleGAN\">StyleGAN<\/a> foundation to enable image editing simply by applying various terms. Check out some examples (&#8220;before&#8221; images in the top row; &#8220;after&#8221; below along with editing terms).<\/p>\n\n\n\n<figure class=\"wp-block-image size-large\"><a href=\"http:\/\/jnack.com\/blog\/wp-content\/uploads\/2021\/04\/StyleCLIP.jpg\"><img decoding=\"async\" loading=\"lazy\" width=\"1024\" height=\"413\" src=\"http:\/\/jnack.com\/blog\/wp-content\/uploads\/2021\/04\/StyleCLIP-1024x413.jpg\" alt=\"\" class=\"wp-image-14528\" srcset=\"http:\/\/jnack.com\/blog\/wp-content\/uploads\/2021\/04\/StyleCLIP-1024x413.jpg 1024w, http:\/\/jnack.com\/blog\/wp-content\/uploads\/2021\/04\/StyleCLIP-300x121.jpg 300w, http:\/\/jnack.com\/blog\/wp-content\/uploads\/2021\/04\/StyleCLIP-768x310.jpg 768w, http:\/\/jnack.com\/blog\/wp-content\/uploads\/2021\/04\/StyleCLIP.jpg 1200w\" sizes=\"(max-width: 1024px) 100vw, 1024px\" \/><\/a><\/figure>\n\n\n\n<p>Here&#8217;s a demo of editing human &amp; animal faces, and even of transforming cars:<\/p>\n\n\n\n<figure class=\"wp-block-embed is-type-video is-provider-youtube wp-block-embed-youtube wp-embed-aspect-16-9 wp-has-aspect-ratio\"><div class=\"wp-block-embed__wrapper\">\n<iframe loading=\"lazy\" title=\"StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery\" width=\"604\" height=\"340\" src=\"https:\/\/www.youtube.com\/embed\/5icI0NgALnQ?feature=oembed\" frameborder=\"0\" allow=\"accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture\" allowfullscreen><\/iframe>\n<\/div><\/figure>\n\n\n\n<p><em>By no means<\/em> have I been around here long enough (five whole days!) to grok everything that&#8217;s going on here, but as I come up to speed, I&#8217;ll do my best to share what I&#8217;m learning. Meanwhile I&#8217;d love to hear your thoughts on how we might thoughtfully bring techniques like this to life.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Welcome to the rabbit hole, my friends. &#x1f643; What if instead of pushing pixels, you could simply tell your tools what changes you&#8217;d like to see? (Cue Kramer voice: &#8220;Why don&#8217;t you just tell me the movie&#8230;??&#8221;) This new StyleCLIP technology (code) builds on NVIDIA&#8217;s StyleGAN foundation to enable image editing simply by applying various [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":[],"categories":[66],"tags":[],"_links":{"self":[{"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/posts\/14526"}],"collection":[{"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/comments?post=14526"}],"version-history":[{"count":5,"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/posts\/14526\/revisions"}],"predecessor-version":[{"id":14534,"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/posts\/14526\/revisions\/14534"}],"wp:attachment":[{"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/media?parent=14526"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/categories?post=14526"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/tags?post=14526"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}