{"id":22584,"date":"2025-02-09T13:18:34","date_gmt":"2025-02-09T21:18:34","guid":{"rendered":"http:\/\/jnack.com\/blog\/?p=22584"},"modified":"2025-02-09T13:18:34","modified_gmt":"2025-02-09T21:18:34","slug":"deepseek-meets-flux-in-krea-chat","status":"publish","type":"post","link":"http:\/\/jnack.com\/blog\/2025\/02\/09\/deepseek-meets-flux-in-krea-chat\/","title":{"rendered":"DeepSeek meets Flux in Krea Chat"},"content":{"rendered":"\n<p>Conversational creation &amp; iteration is such a promising pattern, as shown through people making ChatGPT take images to greater &amp; greater extremes:<\/p>\n\n\n<blockquote class=\"twitter-tweet\">\n<p dir=\"ltr\" lang=\"zxx\"><a href=\"https:\/\/t.co\/7SQwBMyrlv\">pic.twitter.com\/7SQwBMyrlv<\/a><\/p>\n<p>\u2014 No Context Shitposting (@NoContextCrap) <a href=\"https:\/\/twitter.com\/NoContextCrap\/status\/1888200103317401823?ref_src=twsrc%5Etfw\">February 8, 2025<\/a><\/p>\n<\/blockquote>\n<p><script async=\"\" src=\"https:\/\/platform.twitter.com\/widgets.js\" charset=\"utf-8\"><\/script><br \/>But how do we go from ironic laughs to actual usefulness? Krea is taking a swing by integrating (I think) the Flux imaging model with the DeepSeek LLM:<\/p>\n<blockquote class=\"twitter-tweet\">\n<p dir=\"ltr\" lang=\"en\">Krea Chat is here.<\/p>\n<p>a brand new way of creating images and videos with AI.<\/p>\n<p>open beta out now. <a href=\"https:\/\/t.co\/dbHX31l92A\">pic.twitter.com\/dbHX31l92A<\/a><\/p>\n<p>\u2014 KREA AI (@krea_ai) <a href=\"https:\/\/twitter.com\/krea_ai\/status\/1887886539398459533?ref_src=twsrc%5Etfw\">February 7, 2025<\/a><\/p>\n<\/blockquote>\n<p><script async=\"\" src=\"https:\/\/platform.twitter.com\/widgets.js\" charset=\"utf-8\"><\/script><\/p>\n\n\n<p>It doesn&#8217;t yet offer the kind of localized refinements people want (e.g. &#8220;show me a dog on the beach,&#8221; then &#8220;put a hat on the dog&#8221; and don&#8217;t change anything outside the hat area). Even so, it&#8217;s great to be able to create an image, add a photo reference to refine it, and then create a video. Here&#8217;s my cute, if not exactly accurate, first attempt. \ud83d\ude42<\/p>\n\n\n\n<figure class=\"wp-block-video\"><video controls src=\"http:\/\/jnack.com\/blog\/wp-content\/uploads\/2025\/02\/Moonadoodle.mov\"><\/video><\/figure>\n","protected":false},"excerpt":{"rendered":"<p>Conversational creation &amp; iteration is such a promising pattern, as shown through people making ChatGPT take images to greater &amp; greater extremes: pic.twitter.com\/7SQwBMyrlv \u2014 No Context Shitposting (@NoContextCrap) February 8, 2025 But how do we go from ironic laughs to actual usefulness? Krea is taking a swing by integrating (I think) the Flux imaging model [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"","sticky":false,"template":"","format":"standard","meta":[],"categories":[66],"tags":[],"_links":{"self":[{"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/posts\/22584"}],"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=22584"}],"version-history":[{"count":1,"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/posts\/22584\/revisions"}],"predecessor-version":[{"id":22586,"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/posts\/22584\/revisions\/22586"}],"wp:attachment":[{"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/media?parent=22584"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/categories?post=22584"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/tags?post=22584"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}