{"id":601,"date":"2024-11-03T20:59:54","date_gmt":"2024-11-03T20:59:54","guid":{"rendered":"https:\/\/www.alanknipmeyer.phd\/?p=601"},"modified":"2024-11-03T20:59:54","modified_gmt":"2024-11-03T20:59:54","slug":"omnigen-unified-image-generation","status":"publish","type":"post","link":"https:\/\/www.alanknipmeyer.phd\/index.php\/2024\/11\/03\/omnigen-unified-image-generation\/","title":{"rendered":"OmniGen: Unified Image Generation"},"content":{"rendered":"\n<p>So I&#8217;ve been doing lots of other stuff between now and the last posting (lab reorg, server rebuilds, new tech), but I&#8217;ll cover those in another post when I can put them all together nicely! I thought I&#8217;d make a short but nethertheless interesting post on a new AI platform for image generation.<\/p>\n\n\n\n<p>I have used <a href=\"https:\/\/www.alanknipmeyer.phd\/index.php\/2024\/09\/30\/cog-video\/\">Cog Video<\/a> on my home lab, which is incredible in its ability to do text to image creation, so it was great interest to read about <a href=\"https:\/\/arxiv.org\/pdf\/2409.11340\">OmniGen<\/a> which takes that to the next level. I loaded this up on my P100 home lab server and whilst it took a little time (c.15 min for one image, c. 30 min for two image manipulation) it was amazing to see what it could produce.<\/p>\n\n\n\n<p>I started with some random ideas,  such as breakdancing beavers in time square in new york. <\/p>\n\n\n\n<figure class=\"wp-block-image size-large\"><img fetchpriority=\"high\" decoding=\"async\" width=\"1024\" height=\"1024\" src=\"https:\/\/www.alanknipmeyer.phd\/wp-content\/uploads\/2024\/11\/beavers-1024x1024.jpg\" alt=\"\" class=\"wp-image-602\" srcset=\"https:\/\/www.alanknipmeyer.phd\/wp-content\/uploads\/2024\/11\/beavers-1024x1024.jpg 1024w, https:\/\/www.alanknipmeyer.phd\/wp-content\/uploads\/2024\/11\/beavers-300x300.jpg 300w, https:\/\/www.alanknipmeyer.phd\/wp-content\/uploads\/2024\/11\/beavers-150x150.jpg 150w, https:\/\/www.alanknipmeyer.phd\/wp-content\/uploads\/2024\/11\/beavers-768x768.jpg 768w, https:\/\/www.alanknipmeyer.phd\/wp-content\/uploads\/2024\/11\/beavers-1536x1536.jpg 1536w, https:\/\/www.alanknipmeyer.phd\/wp-content\/uploads\/2024\/11\/beavers.jpg 2048w\" sizes=\"(max-width: 1024px) 100vw, 1024px\" \/><\/figure>\n\n\n\n<p>I was astounded by the results, not only in image quality, but how accurate the model had turned the text into what I had asked. This was all possible with Cog VIdeo, so what is it that got me really excited about OmniGen, well it can take pictures and do a plethora of actions. One online friend suggested this was how so many of these &#8216;deep fakes&#8217; where created, which raised the ethical use of AI as a benefit or a burden to society, indeed a platform like this it would be very easy to make high quality images that where so life-like it would be difficult to tell they where generated by AI.<\/p>\n\n\n\n<p>I was netherthe less very happy to try out another AI image platform and start reading the paper so I could learn more about it myself and be able to run it on my home lab.<\/p>\n\n\n\n<p> If you want to &#8216;play&#8217; yourself, there is a platform available <a href=\"https:\/\/fal.ai\/models\/fal-ai\/omnigen-v1\/playground\">here<\/a>, which provides access to create your own images. I&#8217;m very excited about this, but much like any &#8216;tool&#8217; its unto the user to make best use of it responsibly !<\/p>\n","protected":false},"excerpt":{"rendered":"<p>So I&#8217;ve been doing lots of other stuff between now and the last posting (lab reorg, server rebuilds, new tech), but I&#8217;ll cover those in another post when I can put them all together nicely! I thought I&#8217;d make a short but nethertheless interesting post on a new AI platform for image generation. I have [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[],"class_list":["post-601","post","type-post","status-publish","format-standard","hentry","category-uncategorised"],"_links":{"self":[{"href":"https:\/\/www.alanknipmeyer.phd\/index.php\/wp-json\/wp\/v2\/posts\/601","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.alanknipmeyer.phd\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.alanknipmeyer.phd\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.alanknipmeyer.phd\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.alanknipmeyer.phd\/index.php\/wp-json\/wp\/v2\/comments?post=601"}],"version-history":[{"count":1,"href":"https:\/\/www.alanknipmeyer.phd\/index.php\/wp-json\/wp\/v2\/posts\/601\/revisions"}],"predecessor-version":[{"id":603,"href":"https:\/\/www.alanknipmeyer.phd\/index.php\/wp-json\/wp\/v2\/posts\/601\/revisions\/603"}],"wp:attachment":[{"href":"https:\/\/www.alanknipmeyer.phd\/index.php\/wp-json\/wp\/v2\/media?parent=601"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.alanknipmeyer.phd\/index.php\/wp-json\/wp\/v2\/categories?post=601"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.alanknipmeyer.phd\/index.php\/wp-json\/wp\/v2\/tags?post=601"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}