{"id":13772,"date":"2024-06-22T09:39:02","date_gmt":"2024-06-22T01:39:02","guid":{"rendered":"https:\/\/www.1ai.net\/?p=13772"},"modified":"2024-06-22T09:39:02","modified_gmt":"2024-06-22T01:39:02","slug":"%e8%85%be%e8%ae%af%e6%b7%b7%e5%85%83%e6%96%87%e7%94%9f%e5%9b%be%e5%a4%a7%e6%a8%a1%e5%9e%8b%e5%bc%80%e6%ba%90%e8%ae%ad%e7%bb%83%e4%bb%a3%e7%a0%81-%e5%8f%91%e5%b8%83lora%e4%b8%8econtrolnet%e6%8f%92","status":"publish","type":"post","link":"https:\/\/www.1ai.net\/en\/13772.html","title":{"rendered":"Tencent Hunyuan Wenshengtu Large Model Open Source Training Code Release LoRA and ControlNet Plugins"},"content":{"rendered":"<p><a href=\"https:\/\/www.1ai.net\/en\/tag\/%e8%85%be%e8%ae%af\" title=\"[View articles tagged with [Tencent]]\" target=\"_blank\" >Tencent<\/a><a href=\"https:\/\/www.1ai.net\/en\/tag\/%e6%b7%b7%e5%85%83\" title=\"_Other Organiser\" target=\"_blank\" >origin of the universe<\/a><a href=\"https:\/\/www.1ai.net\/en\/tag\/%e6%96%87%e7%94%9f%e5%9b%be%e5%a4%a7%e6%a8%a1%e5%9e%8b\" title=\"[Sees articles with tags]\" target=\"_blank\" >Vincent Figure Large Model<\/a>(hybrid DiT model) announced a comprehensive<a href=\"https:\/\/www.1ai.net\/en\/tag\/%e5%bc%80%e6%ba%90\" title=\"[View articles tagged with [open source]]\" target=\"_blank\" >Open Source<\/a>Training code, including LoRA plug-in and ControlNet plug-in.<\/p>\n<p>LoRA is a technique for fine-tuning large language models to train models with specific features using a small amount of data without modifying the original model or increasing its size.<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-13773\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/06\/6385456742624450562765055.jpg\" alt=\"\" width=\"682\" height=\"504\" \/><\/p>\n<p>ControlNet is a controlled chemical generation algorithm that allows users to better control image generation by adding additional conditions. Tencent Hybrid provides three premiere ControlNet models that can extract and apply image conditions such as edges, depth, and human pose.<\/p>\n<p>In addition, DiT has released a proprietary acceleration library to improve reasoning efficiency and simplify usage. DiT has been widely used in various fields such as material creation, product synthesis, game graphics, etc., including Tencent's AdMyth platform and a number of media outlets using DiT models for content generation.<\/p>\n<p><strong>Official website.<\/strong><\/p>\n<p>https:\/\/dit.hunyuan.tencent.com\/<\/p>\n<p><strong>Code:<\/strong><\/p>\n<p>https:\/\/github.com\/Tencent\/HunyuanDiT<\/p>\n<p><strong>Model:<\/strong><\/p>\n<p>https:\/\/huggingface.co\/Tencent-Hunyuan\/HunyuanDiT<\/p>\n<p><strong>Dissertation.<\/strong><\/p>\n<p>https:\/\/tencent.github.io\/HunyuanDiT\/asset\/Hunyuan_DiT_Tech_Report_05140553.pdf<\/p>\n<p><strong>Data production process.<\/strong><\/p>\n<p>https:\/\/github.com\/Tencent\/HunyuanDiT\/blob\/main\/IndexKits\/docs\/MakeDataset.md<\/p>","protected":false},"excerpt":{"rendered":"<p>Tencent's Mixed-Dimensional Digraph Large Model (Mixed-Dimensional DiT Model) announced full open source training code, including the LoRA plugin and ControlNet plugin. LoRA is a technique for fine-tuning large language models to train models with specific features using small amounts of data without modifying the original model or increasing the model size. ControlNet is a controlled generation algorithm that allows users to better control image generation by adding additional conditions. Tencent Hybrid offers three premiere ControlNet models that can extract and apply image conditions such as edges, depth, and human pose. In addition, DiT has released a proprietary acceleration library to improve inference efficiency and simplify usage. Mixed Element DiT has<\/p>","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[146],"tags":[219,2860,2656,323],"collection":[],"class_list":["post-13772","post","type-post","status-publish","format-standard","hentry","category-news","tag-219","tag-2860","tag-2656","tag-323"],"acf":[],"_links":{"self":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/13772","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=13772"}],"version-history":[{"count":0,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/13772\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/media?parent=13772"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/categories?post=13772"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/tags?post=13772"},{"taxonomy":"collection","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/collection?post=13772"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}