{"id":14960,"date":"2021-06-07T13:46:19","date_gmt":"2021-06-07T20:46:19","guid":{"rendered":"http:\/\/jnack.com\/blog\/?p=14960"},"modified":"2021-06-07T13:46:21","modified_gmt":"2021-06-07T20:46:21","slug":"automatic-caricature-creation-gets-better-better","status":"publish","type":"post","link":"http:\/\/jnack.com\/blog\/2021\/06\/07\/automatic-caricature-creation-gets-better-better\/","title":{"rendered":"Automatic caricature creation gets better &#038; better"},"content":{"rendered":"\n<p>A few weeks ago I <a href=\"http:\/\/jnack.com\/blog\/2021\/04\/22\/using-ai-to-create-disney-pixar-style-caricatures\/\">mentioned<\/a> <a href=\"http:\/\/toonify.photos\">Toonify<\/a>, an online app that can render your picture in a variety of cartoon styles. Researchers are busily cranking away to improve upon it, and the new <a href=\"https:\/\/guoxiansong.github.io\/homepage\/agilegan.html\">AgileGAN<\/a> promises better results &amp; the ability to train models via just a few inputs:<\/p>\n\n\n\n<blockquote class=\"wp-block-quote\"><p>Our approach provides greater agility in creating high quality and high resolution (1024\u00d71024) portrait stylization models, requiring only a limited number of style exemplars (\u223c100) and short training time (\u223c1 hour).<\/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=\"AgileGAN: Stylizing Portraits by Inversion-Consistent Transfer Learning\" width=\"604\" height=\"340\" src=\"https:\/\/www.youtube.com\/embed\/o0HHIvOT_n0?feature=oembed\" frameborder=\"0\" allow=\"accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture\" allowfullscreen><\/iframe>\n<\/div><\/figure>\n\n\n\n<figure class=\"wp-block-image\"><img decoding=\"async\" src=\"https:\/\/guoxiansong.github.io\/homepage\/agilegan\/teaser.PNG\" alt=\"alt text\"\/><\/figure>\n","protected":false},"excerpt":{"rendered":"<p>A few weeks ago I mentioned Toonify, an online app that can render your picture in a variety of cartoon styles. Researchers are busily cranking away to improve upon it, and the new AgileGAN promises better results &amp; the ability to train models via just a few inputs: Our approach provides greater agility in creating [&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\/14960"}],"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=14960"}],"version-history":[{"count":2,"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/posts\/14960\/revisions"}],"predecessor-version":[{"id":14965,"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/posts\/14960\/revisions\/14965"}],"wp:attachment":[{"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/media?parent=14960"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/categories?post=14960"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/tags?post=14960"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}