{"id":137947,"date":"2024-12-17T06:58:53","date_gmt":"2024-12-16T23:58:53","guid":{"rendered":"https:\/\/hotvideos24.online\/?p=137947"},"modified":"2024-12-17T06:58:53","modified_gmt":"2024-12-16T23:58:53","slug":"googles-new-ai-tool-whisk-uses-images-as-prompts","status":"publish","type":"post","link":"https:\/\/hotvideos24.online\/?p=137947","title":{"rendered":"Google\u2019s new AI tool Whisk uses images as prompts"},"content":{"rendered":"<p> <script async src=\"https:\/\/pagead2.googlesyndication.com\/pagead\/js\/adsbygoogle.js?client=ca-pub-3711241968723425\"\r\n     crossorigin=\"anonymous\"><\/script>\r\n<ins class=\"adsbygoogle\"\r\n     style=\"display:block\"\r\n     data-ad-format=\"fluid\"\r\n     data-ad-layout-key=\"-fb+5w+4e-db+86\"\r\n     data-ad-client=\"ca-pub-3711241968723425\"\r\n     data-ad-slot=\"7910942971\"><\/ins>\r\n<script>\r\n     (adsbygoogle = window.adsbygoogle || []).push({});\r\n<\/script><br \/>\n<\/p>\n<div>\n<p>Google has yet <a data-i13n=\"cpos:1;pos:1\" href=\"https:\/\/www.engadget.com\/googles-new-ai-experiment-composes-abstract-musical-clips-inspired-by-instruments-203732054.html\" data-ylk=\"slk:another;cpos:1;pos:1;elm:context_link;itc:0;sec:content-canvas\" class=\"link \">another<\/a> <a data-i13n=\"cpos:2;pos:1\" href=\"https:\/\/www.engadget.com\/googles-latest-ai-trick-is-summarizing-long-web-pages-160004700.html\" data-ylk=\"slk:AI tool;cpos:2;pos:1;elm:context_link;itc:0;sec:content-canvas\" class=\"link \">AI tool<\/a> to add to <a data-i13n=\"cpos:3;pos:1\" href=\"https:\/\/www.engadget.com\/google-ai-test-kitchen-lamda-2-experiments-180212404.html\" data-ylk=\"slk:the pile;cpos:3;pos:1;elm:context_link;itc:0;sec:content-canvas\" class=\"link \">the pile<\/a>. <a data-i13n=\"elm:context_link;elmt:doNotAffiliate;cpos:4;pos:1\" class=\"link \" href=\"https:\/\/blog.google\/technology\/google-labs\/httpsbloggoogletechnologygoogle-labswhisk\/\" rel=\"nofollow noopener\" target=\"_blank\" data-ylk=\"slk:Whisk;elm:context_link;elmt:doNotAffiliate;cpos:4;pos:1;itc:0;sec:content-canvas\">Whisk<\/a> is a Google Labs image generator that lets you use an existing image as your prompt. But its output only captures your starter image\u2019s \u201cessence\u201d rather than recreating it with new details. So, it\u2019s better for brainstorming and rapid-fire visualizations than edits of the source image.<\/p>\n<p>The company describes Whisk as \u201ca new type of creative tool.\u201d The input screen starts with a bare-bones interface with inputs for style and subject. This simple introductory interface only lets you choose from three predefined styles: sticker, enamel pin and plushie. I suspect Google found those three allowed for the kind of rough-outline outputs the experimental tool is most ideal for in its current form.<\/p>\n<p>As you can see in the image above, it produced a solid image of a Wilford Brimley plushie. (Google\u2019s terms forbid pictures of celebrities, but Wilford slipped through the gates, Quaker Oats in tow, without alerting the guards.)<\/p>\n<p>Whisk also includes a more advanced editor (found by clicking \u201cStart from scratch\u201d from the main screen). In this mode, you can use text or a source image in three categories: subject, scene and style. There\u2019s also an input bar to add more text for finishing touches. However, in its current form, the advanced controls didn\u2019t produce results that looked anything like my queries.<\/p>\n<p>For example, check out my attempt to generate the late Mr. Brimley in a lightbox scene in the style of a walrus plushie image I found online:<\/p>\n<figure class=\"caas-figure\">\n<div class=\"caas-figure-with-pb\" style=\"max-height: 540px\">\n<div>\n<div class=\"caas-img-container caas-img-loader\" style=\"padding-bottom:56%\"><img loading=\"lazy\" decoding=\"async\" class=\"caas-img caas-lazy has-preview has-width\" alt=\"Screenshot of an AI generation tool producing images a man who looks a bit like Wilford Brimley.\" src=\"https:\/\/s.yimg.com\/ny\/api\/res\/1.2\/sjhN5fAL631NCG3vgrIAsg--\/YXBwaWQ9aGlnaGxhbmRlcjt3PTk2MDtoPTU0MA--\/https:\/\/s.yimg.com\/os\/creatr-uploaded-images\/2024-12\/fc69d6e0-bbee-11ef-97f8-3dc8172714df\" height=\"540\" width=\"960\"\/><img loading=\"lazy\" decoding=\"async\" alt=\"Screenshot of an AI generation tool producing images a man who looks a bit like Wilford Brimley.\" src=\"https:\/\/s.yimg.com\/ny\/api\/res\/1.2\/sjhN5fAL631NCG3vgrIAsg--\/YXBwaWQ9aGlnaGxhbmRlcjt3PTk2MDtoPTU0MA--\/https:\/\/s.yimg.com\/os\/creatr-uploaded-images\/2024-12\/fc69d6e0-bbee-11ef-97f8-3dc8172714df\" height=\"540\" width=\"960\" class=\"caas-img has-width\"\/><\/div>\n<\/div>\n<\/div>\n<p><figcaption class=\"caption-collapse\"><span class=\"caption-credit\"> Google \/ Screenshot by Will Shanklin for Engadget<\/span><\/figcaption><\/p>\n<\/figure>\n<p>Whisk spit out what looks like a vaguely Wilford Brimley-esque actor eating oatmeal inside a lightbox frame. As far as I can tell, that dude is not a plushie. So, it\u2019s clear why Google recommends using the tool more for \u201crapid visual exploration\u201d and less for production-ready content.<\/p>\n<p>Google acknowledges that Whisk will only draw from \u201ca few key characteristics\u201d of your source image. \u201cFor example, the generated subject might have a different height, weight, hairstyle or skin tone,\u201d the company warns.<\/p>\n<p>To understand why, look no further than Google\u2019s description of how Whisk works under the hood. It uses the <a data-i13n=\"cpos:5;pos:1\" href=\"https:\/\/www.engadget.com\/ai\/gemini-20-is-googles-most-capable-ai-model-yet-and-available-to-preview-today-170329180.html\" data-ylk=\"slk:Gemini language model;cpos:5;pos:1;elm:context_link;itc:0;sec:content-canvas\" class=\"link \">Gemini language model<\/a> to write a detailed caption of the source image you upload. It then feeds that description into the <a data-i13n=\"cpos:6;pos:1\" href=\"https:\/\/www.engadget.com\/google-unveils-veo-and-imagen-3-its-latest-ai-media-creation-models-173617373.html\" data-ylk=\"slk:Imagen 3 image generator;cpos:6;pos:1;elm:context_link;itc:0;sec:content-canvas\" class=\"link \">Imagen 3 image generator<\/a>. So, the result is an image based on <em>Gemini\u2019s words about your image<\/em> \u2014 not the source image itself.<\/p>\n<p>Whisk is only available in the US, at least for now. You can try it at the project\u2019s <a data-i13n=\"cpos:7;pos:1\" href=\"https:\/\/labs.google\/fx\/tools\/whisk\" rel=\"nofollow noopener\" target=\"_blank\" data-ylk=\"slk:Google Labs site;cpos:7;pos:1;elm:context_link;itc:0;sec:content-canvas\" class=\"link \">Google Labs site<\/a>.<\/p>\n<\/div>\n<p><script async src=\"https:\/\/pagead2.googlesyndication.com\/pagead\/js\/adsbygoogle.js?client=ca-pub-3711241968723425\"\r\n     crossorigin=\"anonymous\"><\/script>\r\n<ins class=\"adsbygoogle\"\r\n     style=\"display:block\"\r\n     data-ad-format=\"fluid\"\r\n     data-ad-layout-key=\"-fb+5w+4e-db+86\"\r\n     data-ad-client=\"ca-pub-3711241968723425\"\r\n     data-ad-slot=\"7910942971\"><\/ins>\r\n<script>\r\n     (adsbygoogle = window.adsbygoogle || []).push({});\r\n<\/script><br \/>\n<br \/><div data-type=\"_mgwidget\" data-widget-id=\"1660802\">\r\n<\/div>\r\n<script>(function(w,q){w[q]=w[q]||[];w[q].push([\"_mgc.load\"])})(window,\"_mgq\");\r\n<\/script>\r\n<br \/>\n<br \/><a href=\"https:\/\/www.engadget.com\/ai\/googles-new-ai-tool-whisk-uses-images-as-prompts-210105371.html\">Source link <\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Google has yet another AI tool to add to the pile. Whisk is a Google Labs image generator that lets you use an existing image as your prompt. But its &hellip; <a href=\"https:\/\/hotvideos24.online\/?p=137947\" class=\"more-link\">Read More<\/a><\/p>\n","protected":false},"author":2,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[8630],"tags":[],"class_list":["post-137947","post","type-post","status-publish","format-standard","hentry","category-technology","entry"],"_links":{"self":[{"href":"https:\/\/hotvideos24.online\/index.php?rest_route=\/wp\/v2\/posts\/137947","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/hotvideos24.online\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/hotvideos24.online\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/hotvideos24.online\/index.php?rest_route=\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/hotvideos24.online\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=137947"}],"version-history":[{"count":0,"href":"https:\/\/hotvideos24.online\/index.php?rest_route=\/wp\/v2\/posts\/137947\/revisions"}],"wp:attachment":[{"href":"https:\/\/hotvideos24.online\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=137947"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/hotvideos24.online\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=137947"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/hotvideos24.online\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=137947"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}