{"id":24178,"date":"2024-12-01T10:11:01","date_gmt":"2024-12-01T02:11:01","guid":{"rendered":"https:\/\/www.1ai.net\/?p=24178"},"modified":"2024-12-01T10:11:01","modified_gmt":"2024-12-01T02:11:01","slug":"%e9%98%bf%e9%87%8c%e4%ba%91%e9%80%9a%e4%b9%89%e4%b8%87%e7%9b%b8%e6%8e%a8%e5%87%ba%e5%9b%be%e5%83%8f%e7%bc%96%e8%be%91%e6%a8%a1%e5%9e%8b-ace%ef%bc%9a%e4%b8%80%e5%8f%a5%e8%af%9d%e5%8d%b3%e5%8f%af","status":"publish","type":"post","link":"https:\/\/www.1ai.net\/en\/24178.html","title":{"rendered":"Aliyun Tongyi Wanxiang Launches Image Editing Model ACE: AI Can Modify Pictures in One Sentence"},"content":{"rendered":"<p><a href=\"https:\/\/www.1ai.net\/en\/tag\/%e9%98%bf%e9%87%8c%e4%ba%91\" title=\"_Other Organiser\" target=\"_blank\" >Alibaba Cloud<\/a><a href=\"https:\/\/www.1ai.net\/en\/tag\/%e9%80%9a%e4%b9%89%e4%b8%87%e7%9b%b8\" title=\"_Other Organiser\" target=\"_blank\" >Tongyi Wanxiang<\/a>The team this week unveiled a brand new<a href=\"https:\/\/www.1ai.net\/en\/tag\/%e5%9b%be%e5%83%8f%e7%bc%96%e8%be%91%e6%a8%a1%e5%9e%8b\" title=\"_Other Organiser\" target=\"_blank\" >Image editing model<\/a> ACE, with a single sentence, allows users to generate images and modify them. The tool can be applied to stylized portraits, split-screen production, interior design and other scenarios. The model has been open-sourced for global developers, and its localized stylization function is now available on the Tongyi App.<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-24179\" title=\"1765b7cdj00snsm0q00zvd000v900t1p\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/12\/1765b7cdj00snsm0q00zvd000v900t1p.jpg\" alt=\"1765b7cdj00snsm0q00zvd000v900t1p\" width=\"1125\" height=\"1045\" \/><\/p>\n<p>According to the official introduction, the ACE model can support both text-to-graph and image editing, and the user can enter spoken commands to complete the<strong>Controlled visual editing, element editing, area redraw editing, layering editing<\/strong>\uff08Tasks such as stylizing a specific object in a picture can be performed with PS using only dialogs, such as typing text.<strong>One click to remove watermarks, modify the background of the ID photo<\/strong>wait.<\/p>\n<p>The team proposes the Long-context Condition Unit module (LCU), which can support various multimodal condition inputs required for general-purpose editing tasks, and builds a comprehensive editing pair data construction link and instruction set generation link, which ultimately achieves accurate and high-quality image instruction editing results.<\/p>\n<p data-vmark=\"dcb2\"><span class=\"referenceTitle\">Open source address:<\/span><\/p>\n<ul class=\"custom_reference list-paddingleft-1\">\n<li class=\"list-undefined list-reference-paddingleft\">\n<p data-vmark=\"9901\">Magic Match Community:<span class=\"link-text-start-with-http\">https:\/\/www.modelscope.cn\/models\/iic\/ACE-0.6B-1024px<\/span><\/p>\n<\/li>\n<li class=\"list-undefined list-reference-paddingleft\">\n<p data-vmark=\"a0ab\">Github:<span class=\"link-text-start-with-http\">https:\/\/github.com\/ali-vilab\/ACE<\/span><\/p>\n<\/li>\n<li class=\"list-undefined list-reference-paddingleft\">\n<p data-vmark=\"728f\">Huggingface:<span class=\"link-text-start-with-http\">https:\/\/huggingface.co\/spaces\/scepter-studio\/ACE-Chat<\/span><\/p>\n<\/li>\n<\/ul>","protected":false},"excerpt":{"rendered":"<p>The AliCloud Tongyi Wanxiang team this week launched a new image editing model, ACE, which allows users to generate images and modify them with a single sentence. The tool can be applied to stylized portraits, split-screen production, interior design and other scenarios. The model has been open-sourced for developers around the world, and its localized stylization function has been launched on the Tongyi App. According to the official introduction, the ACE model can support both text-generated drawings and image editing, and the user can input spoken commands to complete tasks such as controllable visual editing, element editing, area redraw editing, and layered editing (stylizing specific objects in the drawings), so that PS functions can be realized by using only conversations, such as Inputting text to remove watermarks with one click, modifying the background of ID photos, and so on. The team proposed the Long-context Condition<\/p>","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[146],"tags":[5098,621,334],"collection":[],"class_list":["post-24178","post","type-post","status-publish","format-standard","hentry","category-news","tag-5098","tag-621","tag-334"],"acf":[],"_links":{"self":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/24178","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/comments?post=24178"}],"version-history":[{"count":0,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/24178\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/media?parent=24178"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/categories?post=24178"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/tags?post=24178"},{"taxonomy":"collection","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/collection?post=24178"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}