{"id":15683,"date":"2024-03-16T09:27:54","date_gmt":"2024-03-16T01:27:54","guid":{"rendered":"https:\/\/www.aisharenet.com\/?p=15683"},"modified":"2024-12-16T09:34:45","modified_gmt":"2024-12-16T01:34:45","slug":"foleycrafter","status":"publish","type":"post","link":"https:\/\/www.kdjingpai.com\/en\/foleycrafter\/","title":{"rendered":"FoleyCrafter\uff1a\u4e3a\u65e0\u58f0\u89c6\u9891\u6dfb\u52a0\u751f\u52a8\u540c\u6b65\u7684\u97f3\u6548"},"content":{"rendered":"<p>FoleyCrafter \u662f\u4e00\u4e2a\u7531 OpenMMLab \u5f00\u53d1\u7684\u5f00\u6e90\u9879\u76ee\uff0c\u65e8\u5728\u4e3a\u65e0\u58f0\u89c6\u9891\u751f\u6210\u751f\u52a8\u4e14\u540c\u6b65\u7684\u97f3\u6548\u3002\u8be5\u9879\u76ee\u5229\u7528\u5148\u8fdb\u7684\u4eba\u5de5\u667a\u80fd\u6280\u672f\uff0c\u901a\u8fc7\u5206\u6790\u89c6\u9891\u5185\u5bb9\uff0c\u751f\u6210\u4e0e\u4e4b\u8bed\u4e49\u76f8\u5173\u4e14\u65f6\u95f4\u540c\u6b65\u7684\u97f3\u6548\uff0c\u4ece\u800c\u589e\u5f3a\u89c6\u9891\u7684\u771f\u5b9e\u611f\u548c\u60c5\u611f\u6df1\u5ea6\u3002FoleyCrafter \u7684\u76ee\u6807\u662f\u4e3a\u7535\u5f71\u3001\u6e38\u620f\u7b49\u9886\u57df\u63d0\u4f9b\u9ad8\u8d28\u91cf\u7684\u97f3\u6548\u89e3\u51b3\u65b9\u6848\uff0c\u63d0\u5347\u89c2\u4f17\u7684\u89c6\u542c\u4f53\u9a8c\u3002<\/p>\n<p>\u81ea\u52a8\u5408\u6210\u914d\u97f3\u5de5\u4f5c\u6d41\uff1ahttps:\/\/openart.ai\/workflows\/t8star\/foleycrafter\/wZyBSeaa2lvgU3c3NlcH<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"aligncenter size-full wp-image-15685\" title=\"FoleyCrafter\uff1a\u4e3a\u65e0\u58f0\u89c6\u9891\u6dfb\u52a0\u751f\u52a8\u540c\u6b65\u7684\u97f3\u6548-1\" src=\"https:\/\/www.kdjingpai.com\/wp-content\/uploads\/2024\/12\/2626c7049492c4e.jpg\" alt=\"FoleyCrafter\uff1a\u4e3a\u65e0\u58f0\u89c6\u9891\u6dfb\u52a0\u751f\u52a8\u540c\u6b65\u7684\u97f3\u6548-1\" width=\"1104\" height=\"396\" srcset=\"https:\/\/www.kdjingpai.com\/wp-content\/uploads\/2024\/12\/2626c7049492c4e.jpg 1104w, https:\/\/www.kdjingpai.com\/wp-content\/uploads\/2024\/12\/2626c7049492c4e-300x108.jpg 300w, https:\/\/www.kdjingpai.com\/wp-content\/uploads\/2024\/12\/2626c7049492c4e-1024x367.jpg 1024w, https:\/\/www.kdjingpai.com\/wp-content\/uploads\/2024\/12\/2626c7049492c4e-768x275.jpg 768w, https:\/\/www.kdjingpai.com\/wp-content\/uploads\/2024\/12\/2626c7049492c4e-18x6.jpg 18w\" sizes=\"auto, (max-width: 1104px) 100vw, 1104px\" \/><\/p>\n<p>&nbsp;<\/p>\n<h2>\u529f\u80fd\u5217\u8868<\/h2>\n<ul>\n<li><strong>\u89c6\u9891\u5230\u97f3\u9891\u751f\u6210<\/strong>\uff1a\u6839\u636e\u89c6\u9891\u5185\u5bb9\u751f\u6210\u8bed\u4e49\u76f8\u5173\u4e14\u540c\u6b65\u7684\u97f3\u6548\u3002<\/li>\n<li><strong>\u6587\u672c\u63d0\u793a\u97f3\u6548\u751f\u6210<\/strong>\uff1a\u901a\u8fc7\u6587\u672c\u63d0\u793a\u751f\u6210\u7279\u5b9a\u573a\u666f\u7684\u97f3\u6548\u3002<\/li>\n<li><strong>\u65f6\u95f4\u5bf9\u9f50<\/strong>\uff1a\u786e\u4fdd\u751f\u6210\u7684\u97f3\u6548\u4e0e\u89c6\u9891\u5185\u5bb9\u65f6\u95f4\u540c\u6b65\u3002<\/li>\n<li><strong>Gradio \u754c\u9762<\/strong>\uff1a\u63d0\u4f9b\u7528\u6237\u53cb\u597d\u7684\u754c\u9762\uff0c\u65b9\u4fbf\u7528\u6237\u8fdb\u884c\u97f3\u6548\u751f\u6210\u64cd\u4f5c\u3002<\/li>\n<li><strong>\u5f00\u6e90\u4ee3\u7801<\/strong>\uff1a\u63d0\u4f9b\u5b8c\u6574\u7684\u4ee3\u7801\u5e93\uff0c\u65b9\u4fbf\u5f00\u53d1\u8005\u8fdb\u884c\u4e8c\u6b21\u5f00\u53d1\u548c\u5b9a\u5236\u3002<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<h2>\u4f7f\u7528\u5e2e\u52a9<\/h2>\n<h3>\u5b89\u88c5\u6d41\u7a0b<\/h3>\n<ol>\n<li><strong>\u51c6\u5907\u73af\u5883<\/strong>\uff1a\n<ul>\n<li>\u5b89\u88c5 Conda \u73af\u5883\uff1a<code>conda env create -f requirements\/environment.yaml<\/code><\/li>\n<li>\u6fc0\u6d3b\u73af\u5883\uff1a<code>conda activate foleycrafter<\/code><\/li>\n<li>\u5b89\u88c5 Git LFS\uff1a<code>conda install git-lfs<\/code>\uff0c\u7136\u540e\u8fd0\u884c <code>git lfs install<\/code><\/li>\n<\/ul>\n<\/li>\n<li><strong>\u4e0b\u8f7d\u68c0\u67e5\u70b9<\/strong>\uff1a\n<ul>\n<li>\u8fd0\u884c <code>inference.py<\/code> \u81ea\u52a8\u4e0b\u8f7d\u68c0\u67e5\u70b9\uff0c\u6216\u624b\u52a8\u4e0b\u8f7d\u5e76\u653e\u7f6e\u5728 <code>checkpoints<\/code> \u76ee\u5f55\u4e0b\u3002<\/li>\n<\/ul>\n<\/li>\n<li><strong>\u542f\u52a8 Gradio \u754c\u9762<\/strong>\uff1a\n<ul>\n<li>\u8fd0\u884c <code>python app.py --share<\/code> \u542f\u52a8 Gradio \u754c\u9762\u3002<\/li>\n<\/ul>\n<\/li>\n<\/ol>\n<h3>\u4f7f\u7528\u6d41\u7a0b<\/h3>\n<ol>\n<li><strong>\u89c6\u9891\u5230\u97f3\u9891\u751f\u6210<\/strong>\uff1a\n<ul>\n<li>\u8fd0\u884c <code>python inference.py --save_dir=output\/sora\/<\/code>\uff0c\u5c06\u751f\u6210\u7684\u97f3\u9891\u6587\u4ef6\u4fdd\u5b58\u5728\u6307\u5b9a\u76ee\u5f55\u3002<\/li>\n<\/ul>\n<\/li>\n<li><strong>\u65f6\u95f4\u5bf9\u9f50<\/strong>\uff1a\n<ul>\n<li>\u8fd0\u884c <code>python inference.py --temporal_align --input=input\/avsync --save_dir=output\/avsync\/<\/code>\uff0c\u786e\u4fdd\u751f\u6210\u7684\u97f3\u6548\u4e0e\u89c6\u9891\u5185\u5bb9\u65f6\u95f4\u540c\u6b65\u3002<\/li>\n<\/ul>\n<\/li>\n<li><strong>\u6587\u672c\u63d0\u793a\u97f3\u6548\u751f\u6210<\/strong>\uff1a\n<ul>\n<li>\u8fd0\u884c <code>python inference.py --input=input\/PromptControl\/case1\/ --seed=10201304011203481429 --prompt='noisy, people talking' --save_dir=output\/PromptControl\/case1_prompt\/<\/code>\uff0c\u6839\u636e\u6587\u672c\u63d0\u793a\u751f\u6210\u7279\u5b9a\u573a\u666f\u7684\u97f3\u6548\u3002<\/li>\n<\/ul>\n<\/li>\n<\/ol>\n<h3>\u8be6\u7ec6\u64cd\u4f5c\u6b65\u9aa4<\/h3>\n<ol>\n<li><strong>\u51c6\u5907\u73af\u5883<\/strong>\uff1a\n<ul>\n<li>\u4e0b\u8f7d\u5e76\u5b89\u88c5 Conda\uff1ahttps:\/\/docs.conda.io\/en\/latest\/miniconda.html<\/li>\n<li>\u514b\u9686\u9879\u76ee\u4ee3\u7801\uff1a<code>git clone https:\/\/github.com\/open-mmlab\/foleycrafter.git<\/code><\/li>\n<li>\u8fdb\u5165\u9879\u76ee\u76ee\u5f55\uff1a<code>cd foleycrafter<\/code><\/li>\n<li>\u6309\u7167\u4e0a\u8ff0\u6b65\u9aa4\u5b89\u88c5\u4f9d\u8d56\u5e76\u914d\u7f6e\u73af\u5883\u3002<\/li>\n<\/ul>\n<\/li>\n<li><strong>\u4e0b\u8f7d\u68c0\u67e5\u70b9<\/strong>\uff1a\n<ul>\n<li>\u4e0b\u8f7d\u5e76\u653e\u7f6e\u68c0\u67e5\u70b9\u6587\u4ef6\uff0c\u786e\u4fdd\u76ee\u5f55\u7ed3\u6784\u5982\u4e0b\uff1a<\/li>\n<\/ul>\n<pre><code> \u2514\u2500\u2500 checkpoints\r\n\u251c\u2500\u2500 semantic\r\n\u2502   \u251c\u2500\u2500 semantic_adapter.bin\r\n\u251c\u2500\u2500 vocoder\r\n\u2502   \u251c\u2500\u2500 vocoder.pt\r\n\u2502   \u251c\u2500\u2500 config.json\r\n\u251c\u2500\u2500 temporal_adapter.ckpt\r\n\u2502   \u2514\u2500\u2500 timestamp_detector.pth.tar\r\n<\/code><\/pre>\n<\/li>\n<li><strong>\u542f\u52a8 Gradio \u754c\u9762<\/strong>\uff1a\n<ul>\n<li>\u8fd0\u884c <code>python app.py --share<\/code> \u542f\u52a8 Gradio \u754c\u9762\uff0c\u7528\u6237\u53ef\u4ee5\u901a\u8fc7\u6d4f\u89c8\u5668\u8bbf\u95ee\u754c\u9762\u8fdb\u884c\u64cd\u4f5c\u3002<\/li>\n<\/ul>\n<\/li>\n<li><strong>\u751f\u6210\u97f3\u6548<\/strong>\uff1a\n<ul>\n<li>\u6839\u636e\u9700\u8981\u9009\u62e9\u4e0d\u540c\u7684\u751f\u6210\u6a21\u5f0f\uff08\u89c6\u9891\u5230\u97f3\u9891\u3001\u65f6\u95f4\u5bf9\u9f50\u3001\u6587\u672c\u63d0\u793a\uff09\uff0c\u8fd0\u884c\u76f8\u5e94\u7684\u547d\u4ee4\u751f\u6210\u97f3\u6548\u6587\u4ef6\u3002<\/li>\n<\/ul>\n<\/li>\n<\/ol>\n<p>\u901a\u8fc7\u4ee5\u4e0a\u6b65\u9aa4\uff0c\u7528\u6237\u53ef\u4ee5\u8f7b\u677e\u4e0a\u624b\u4f7f\u7528 FoleyCrafter\uff0c\u4e3a\u65e0\u58f0\u89c6\u9891\u6dfb\u52a0\u751f\u52a8\u4e14\u540c\u6b65\u7684\u97f3\u6548\uff0c\u63d0\u5347\u89c6\u9891\u7684\u89c6\u542c\u4f53\u9a8c\u3002 \/n<\/p>\n","protected":false},"excerpt":{"rendered":"<p>FoleyCrafter \u662f\u4e00\u4e2a\u7531 OpenMMLab \u5f00\u53d1\u7684\u5f00\u6e90\u9879\u76ee\uff0c\u65e8\u5728\u4e3a\u65e0\u58f0\u89c6\u9891\u751f\u6210\u751f\u52a8\u4e14\u540c\u6b65\u7684\u97f3\u6548\u3002\u8be5\u9879\u76ee\u5229\u7528\u5148\u8fdb\u7684\u4eba\u5de5\u667a\u80fd\u6280\u672f\uff0c\u901a\u8fc7\u5206\u6790\u89c6\u9891\u5185\u5bb9\uff0c\u751f\u6210\u4e0e\u4e4b\u8bed\u4e49\u76f8\u5173\u4e14\u65f6\u95f4\u540c\u6b65\u7684\u97f3\u6548\uff0c\u4ece\u800c\u589e\u5f3a\u89c6\u9891\u7684\u771f\u5b9e\u611f\u548c\u60c5\u611f\u6df1\u5ea6\u3002FoleyCraf&#8230;<\/p>\n","protected":false},"author":1,"featured_media":60864,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[20],"tags":[230,206],"class_list":["post-15683","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-tool","tag-aikaiyuanxiangmu","tag-aiyinle"],"_links":{"self":[{"href":"https:\/\/www.kdjingpai.com\/en\/wp-json\/wp\/v2\/posts\/15683","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.kdjingpai.com\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.kdjingpai.com\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.kdjingpai.com\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.kdjingpai.com\/en\/wp-json\/wp\/v2\/comments?post=15683"}],"version-history":[{"count":0,"href":"https:\/\/www.kdjingpai.com\/en\/wp-json\/wp\/v2\/posts\/15683\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.kdjingpai.com\/en\/wp-json\/wp\/v2\/media\/60864"}],"wp:attachment":[{"href":"https:\/\/www.kdjingpai.com\/en\/wp-json\/wp\/v2\/media?parent=15683"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.kdjingpai.com\/en\/wp-json\/wp\/v2\/categories?post=15683"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.kdjingpai.com\/en\/wp-json\/wp\/v2\/tags?post=15683"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}