{"id":14549,"date":"2021-04-08T08:22:00","date_gmt":"2021-04-08T15:22:00","guid":{"rendered":"http:\/\/jnack.com\/blog\/?p=14549"},"modified":"2021-04-07T08:24:17","modified_gmt":"2021-04-07T15:24:17","slug":"a-man-a-plan-a-stylegan","status":"publish","type":"post","link":"http:\/\/jnack.com\/blog\/2021\/04\/08\/a-man-a-plan-a-stylegan\/","title":{"rendered":"A Man, A Plan, A StyleGAN&#8230;"},"content":{"rendered":"\n<p>On Monday I mentioned my new team&#8217;s mind-blowing work to enable <a href=\"http:\/\/jnack.com\/blog\/2021\/04\/05\/witchcraft-alert-my-new-adobe-team-enables-image-transformation-via-text\/\">image synthesis through typing<\/a>, and I noted that it builds on NVIDIA&#8217;s StyleGAN research. If you&#8217;re interested in the latter, check out this two-minute demo of how it enables amazing interactive generation of stylized imagery:<\/p>\n\n\n\n<blockquote class=\"wp-block-quote\"><p>This new project called StyleGAN2, developed by NVIDIA Research, and presented at CVPR 2020, uses transfer learning to produce seemingly infinite numbers of portraits in an infinite variety of painting styles. The work builds on the team\u2019s previously published StyleGAN project. <a href=\"https:\/\/nvda.ws\/2UJ3udu\">Learn more here<\/a>.<\/p><\/blockquote>\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=\"Synthesizing High-Resolution Images with StyleGAN2\" width=\"604\" height=\"340\" src=\"https:\/\/www.youtube.com\/embed\/9QuDh3W3lOY?feature=oembed\" frameborder=\"0\" allow=\"accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture\" allowfullscreen><\/iframe>\n<\/div><\/figure>\n","protected":false},"excerpt":{"rendered":"<p>On Monday I mentioned my new team&#8217;s mind-blowing work to enable image synthesis through typing, and I noted that it builds on NVIDIA&#8217;s StyleGAN research. If you&#8217;re interested in the latter, check out this two-minute demo of how it enables amazing interactive generation of stylized imagery: This new project called StyleGAN2, developed by NVIDIA Research, [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":[],"categories":[66,2],"tags":[],"_links":{"self":[{"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/posts\/14549"}],"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=14549"}],"version-history":[{"count":4,"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/posts\/14549\/revisions"}],"predecessor-version":[{"id":14559,"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/posts\/14549\/revisions\/14559"}],"wp:attachment":[{"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/media?parent=14549"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/categories?post=14549"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/tags?post=14549"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}