{"id":20049,"date":"2022-09-25T21:53:28","date_gmt":"2022-09-26T04:53:28","guid":{"rendered":"http:\/\/jnack.com\/blog\/?p=20049"},"modified":"2022-09-25T21:53:30","modified_gmt":"2022-09-26T04:53:30","slug":"demo-generating-an-illustrated-narrative-with-dreambooth","status":"publish","type":"post","link":"http:\/\/jnack.com\/blog\/2022\/09\/25\/demo-generating-an-illustrated-narrative-with-dreambooth\/","title":{"rendered":"Demo: Generating an illustrated narrative with DreamBooth"},"content":{"rendered":"\n<p>The Corridor Crew has been banging on Stable Diffusion &amp; Google&#8217;s new DreamBooth tech (see <a href=\"http:\/\/jnack.com\/blog\/2022\/08\/30\/google-dreambooth-puts-your-dog-in-space\/\">previous<\/a>) that enables training the model to understand a specific concept\u2014e.g. one person&#8217;s face. Here they&#8217;ve trained it using a few photos of team member Sam Gorski, then inserted him into various genres:<\/p>\n\n\n\n<figure class=\"wp-block-image size-large\"><a href=\"http:\/\/jnack.com\/blog\/wp-content\/uploads\/2022\/09\/sd.jpeg\"><img decoding=\"async\" loading=\"lazy\" width=\"1024\" height=\"677\" src=\"http:\/\/jnack.com\/blog\/wp-content\/uploads\/2022\/09\/sd-1024x677.jpeg\" alt=\"\" class=\"wp-image-20050\" srcset=\"http:\/\/jnack.com\/blog\/wp-content\/uploads\/2022\/09\/sd-1024x677.jpeg 1024w, http:\/\/jnack.com\/blog\/wp-content\/uploads\/2022\/09\/sd-300x198.jpeg 300w, http:\/\/jnack.com\/blog\/wp-content\/uploads\/2022\/09\/sd-768x508.jpeg 768w, http:\/\/jnack.com\/blog\/wp-content\/uploads\/2022\/09\/sd-1536x1015.jpeg 1536w, http:\/\/jnack.com\/blog\/wp-content\/uploads\/2022\/09\/sd.jpeg 1852w\" sizes=\"(max-width: 1024px) 100vw, 1024px\" \/><\/a><\/figure>\n\n\n\n<p>From there they trained up models for various guys at the shop, then created an illustrated fantasy narrative. Just totally incredible, and their sheer exuberance makes the making-of pretty entertaining:<\/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=\"Is This The Death of VFX?\" width=\"604\" height=\"340\" src=\"https:\/\/www.youtube.com\/embed\/W4Mcuh38wyM?start=2&#038;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>The Corridor Crew has been banging on Stable Diffusion &amp; Google&#8217;s new DreamBooth tech (see previous) that enables training the model to understand a specific concept\u2014e.g. one person&#8217;s face. Here they&#8217;ve trained it using a few photos of team member Sam Gorski, then inserted him into various genres: From there they trained up models for [&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\/20049"}],"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=20049"}],"version-history":[{"count":1,"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/posts\/20049\/revisions"}],"predecessor-version":[{"id":20051,"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/posts\/20049\/revisions\/20051"}],"wp:attachment":[{"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/media?parent=20049"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/categories?post=20049"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/tags?post=20049"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}