{"id":15315,"date":"2024-02-18T13:32:34","date_gmt":"2024-02-18T05:32:34","guid":{"rendered":"http:\/\/cxounion.cn\/?p=15315"},"modified":"2024-02-18T13:33:13","modified_gmt":"2024-02-18T05:33:13","slug":"%e3%80%90%e8%b5%84%e8%ae%af%e3%80%91sora%e5%88%b0%e5%ba%95%e6%9c%89%e4%bd%95%e7%a5%9e%e5%a5%87%e4%b9%8b%e5%a4%84%ef%bc%9f%e5%ae%83%e8%a6%81%e6%9e%84%e5%bb%ba%e7%9a%84%e6%98%af%e6%87%82","status":"publish","type":"post","link":"http:\/\/cxounion.cn\/index.php\/2024\/02\/18\/%e3%80%90%e8%b5%84%e8%ae%af%e3%80%91sora%e5%88%b0%e5%ba%95%e6%9c%89%e4%bd%95%e7%a5%9e%e5%a5%87%e4%b9%8b%e5%a4%84%ef%bc%9f%e5%ae%83%e8%a6%81%e6%9e%84%e5%bb%ba%e7%9a%84%e6%98%af%e6%87%82\/","title":{"rendered":"\u3010\u8d44\u8baf\u3011Sora\u5230\u5e95\u6709\u4f55\u795e\u5947\u4e4b\u5904\uff1f\u5b83\u8981\u6784\u5efa\u7684\u662f\u201c\u61c2\u89c4\u5219\u201d\u7684\u6570\u636e\u9a71\u52a8\u7269\u7406\u5f15\u64ce"},"content":{"rendered":"\n

2024\u5e742\u670816\u65e5\u51cc\u6668\uff08\u7f8e\u56fd\u65f6\u95f42\u670815\u65e5\uff09\uff0cOpenAI\u53d1\u5e03\u4e86\u201c\u6587\u751f\u89c6\u9891\u201d\u7684\u5de5\u5177Sora\uff0c\u518d\u6b21\u9707\u64bc\u79d1\u6280\u5708\u3002\u4e0e\u5f53\u524d\u5e73\u5747\u53ea\u67094\u79d2\u89c6\u9891\u751f\u6210\u957f\u5ea6\uff0c\u4e14\u5448\u73b0\u6296\u52a8\u548c\u5931\u771f\u7684\u89c6\u9891\u6548\u679c\u76f8\u6bd4\uff0cSora\u80fd\u591f\u6839\u636e\u7b80\u5355\u7684\u63d0\u793a\u8bcd\u751f\u621060\u79d2\u7684\u8fde\u8d2f\u89c6\u9891\uff0c\u521b\u9020\u51fa\u751f\u52a8\u7684\u89d2\u8272\u8868\u60c5\u548c\u590d\u6742\u7684\u8fd0\u955c\uff0c\u89c6\u9891\u5177\u6709\u9ad8\u5ea6\u7684\u903c\u771f\u6027\u548c\u53d9\u4e8b\u6548\u679c\uff0c\u4f7fSora\u4e00\u7ecf\u53d1\u5e03\u5c31\u5f15\u8d77\u4e86\u5305\u62ec\u9a6c\u65af\u514b\u3001\u5468\u9e3f\u794e\u7b49\u79d1\u6280\u5927\u4f6c\u5728\u5185\u7684\u9ad8\u5ea6\u5173\u6ce8\uff0c\u8fde\u82f1\u4f1f\u8fbe\u4eba\u5de5\u667a\u80fd\u7814\u7a76\u9662Jim Fan\u4e5f\u8868\u793a\uff0c\u201cSora\u662f\u4e00\u4e2a\u6570\u636e\u9a71\u52a8\u7684\u7269\u7406\u5f15\u64ce\u3002\u201d<\/p>\n\n\n\n

Sora\u6587\u751f\u89c6\u9891\u6f14\u793a\u6548\u679c<\/figcaption><\/figure>\n\n\n\n
\u63d0\u793a\uff1a\u4e00\u4f4d\u65f6\u5c1a\u7684\u5973\u4eba\u8d70\u5728\u4e1c\u4eac\u7684\u8857\u9053\u4e0a\uff0c\u8857\u9053\u4e0a\u5230\u5904\u90fd\u662f\u6e29\u6696\u7684\u53d1\u5149\u9713\u8679\u706f\u548c\u52a8\u753b\u57ce\u5e02\u6807\u5fd7\u3002\u5979\u8eab\u7a7f\u9ed1\u8272\u76ae\u5939\u514b\uff0c\u7ea2\u8272\u957f\u88d9\uff0c\u9ed1\u8272\u9774\u5b50\uff0c\u80cc\u7740\u4e00\u4e2a\u9ed1\u8272\u94b1\u5305\u3002\u5979\u6234\u7740\u58a8\u955c\uff0c\u6d82\u7740\u7ea2\u8272\u53e3\u7ea2\u3002\u5979\u81ea\u4fe1\u800c\u968f\u610f\u5730\u8d70\u8def\u3002\u8857\u9053\u6f6e\u6e7f\u800c\u53cd\u5149\uff0c\u8425\u9020\u51fa\u4e94\u989c\u516d\u8272\u7684\u706f\u5149\u7684\u955c\u9762\u6548\u679c\u3002\u8bb8\u591a\u884c\u4eba\u56db\u5904\u8d70\u52a8\u3002 CXO UNION-CXO\u8054\u76df\uff08cxounion.cn\uff09<\/mark><\/p>\n\n\n\n
\u4e00\u3001Sora\u662f\u4e00\u6b3e\u5212\u65f6\u4ee3\u7684\u6587\u751f\u89c6\u9891\u4ea7\u54c1<\/h2>\n\n\n\n
2023\u5e74\uff0c\u591a\u6a21\u6001\u5927\u6a21\u578b\u5728\u5e94\u7528\u7aef\u767e\u82b1\u9f50\u653e\uff0c\u6587\u751f\u56fe\u548c\u6587\u751f\u89c6\u9891\u5de5\u5177\u5982\u96e8\u540e\u6625\u7b0b\u822c\u7206\u53d1\uff0c\u4f5c\u4e3a\u5185\u5bb9\u521b\u4f5c\u8005\uff0c\u7b14\u8005\u4e5f\u66fe\u4ed8\u8d39\u5f00\u901a\u4e86\u591a\u6b3eAI\u89c6\u9891\u5de5\u5177\uff0c\u4f46\u64cd\u4f5c\u8d77\u6765\u6bd4\u8f83\u590d\u6742\uff0c\u751f\u6210\u6548\u679c\u96be\u8bf4\u6ee1\u610f\u3002\u56e0\u6b64\uff0c\u4e5f\u5728\u671f\u5f85\u4e00\u6b3e\u771f\u6b63\u597d\u7528\u7684AI\u6587\u751f\u89c6\u9891\u5de5\u5177\u51fa\u73b0\uff0c\u6ee1\u8db3\u6211\u8fd9\u79cd\u89c6\u9891\u521b\u4f5c\u529f\u5e95\u8f83\u5f31\u7684\u4eba\u7fa4\u9700\u6c42\uff0c\u5374\u672a\u6599\u5230\u73b0\u5b9e\u6765\u7684\u5982\u6b64\u4e4b\u5feb\u3002<\/p>\n\n\n\n
AI\u6587\u751f\u89c6\u9891\u6700\u65e9\u4e3b\u8981\u57fa\u4e8eGAN\uff08\u751f\u6210\u5f0f\u5bf9\u6297\u7f51\u7edc\uff09\u6a21\u578b\u548c VAE\uff08\u53d8\u5206\u81ea\u7f16\u7801\u5668\uff09\u8fdb\u884c\u89c6\u9891\u751f\u6210\u3002\u4e0d\u8fc7\u8fd9\u4e24\u4e2a\u6846\u67b6\u751f\u6210\u7684\u89c6\u9891\u4ec5\u9002\u7528\u9759\u6001\u3001\u5355\u4e00\u753b\u9762\uff0c\u4e14\u5206\u8fa8\u7387\u6781\u4f4e\uff0c\u5e94\u7528\u8303\u56f4\u72ed\u7a84\u3002AI\u6587\u751f\u89c6\u9891\u6280\u672f\u53d1\u5c55\u5230\u73b0\u5728\uff0c\u4e3b\u8981\u5f62\u6210\u4e86\u4e24\u6761\u6280\u672f\u8def\u7ebf\uff1a\u4e00\u6761\u662f\u57fa\u4e8eTransformer\u6a21\u578b\uff0c\u8fd9\u4e5f\u662f\u6587\u672c\u548c\u56fe\u50cf\u751f\u6210\u4e2d\u5e94\u7528\u6700\u591a\u7684\u5927\u6a21\u578b\u5e95\u5ea7\uff1b\u53e6\u4e00\u6761\u5219\u662f\u5728\u89c6\u9891\u9886\u57df\u5e94\u7528\u66f4\u5e7f\u7684\u201c\u6269\u6563\u6a21\u578b\u201d\uff0c\u8fd9\u4e5f\u662f\u5f53\u524dAI\u6587\u751f\u89c6\u9891\u4e3b\u6d41\u6280\u672f\u8def\u7ebf\uff0c\u5728\u8bed\u4e49\u7406\u89e3\u3001\u5185\u5bb9\u4e30\u5bcc\u6027\u4e0a\u66f4\u6709\u4f18\u52bf\u3002<\/p>\n\n\n\n
\u636eOpenAI\u5b98\u7f51\u516c\u5f00\u6280\u672f\u62a5\u544a\uff0cSora \u91c7\u7528\u7684\u662f Diffusion Transformer \u6a21\u578b\uff0c\u4e00\u79cd\u7ed3\u5408\u4e86\u6269\u6563\u6a21\u578b\u548c Transformer \u67b6\u6784\u7684\u6a21\u578b\uff0c\u5b83\u901a\u8fc7 Transformer \u7684\u7f16\u89e3\u7801\u5668\u5904\u7406\u5e26\u566a\u58f0\u7684\u56fe\u50cf\u8f93\u5165\uff0c\u5728\u6bcf\u4e00\u6b65\u4e2d\u9884\u6d4b\u51fa\u66f4\u6e05\u6670\u7684\u56fe\u50cf\u7248\u672c\uff0c\u4e00\u6b21\u6027\u751f\u6210\u6574\u4e2a\u89c6\u9891\u6216\u6269\u5c55\u751f\u6210\u7684\u89c6\u9891\uff0c\u4f7f\u5176\u66f4\u957f\uff0c\u540c\u65f6\u89e3\u51b3\u4e86\u4e00\u4e2a\u5177\u6709\u6311\u6218\u6027\u7684\u95ee\u9898\uff0c\u5373\u786e\u4fdd\u4e3b\u4f53\u5373\u4f7f\u6682\u65f6\u79bb\u5f00\u89c6\u91ce\u4e5f\u4fdd\u6301\u4e0d\u53d8\u3002<\/p>\n\n\n\n
\u5b9e\u9645\u4e0a\uff0c\u963f\u91cc\u5df4\u5df4\u548c\u5b57\u8282\u8df3\u52a8\u4e24\u5927\u884c\u4e1a\u5de8\u5934\u53bb\u5e74\u5c31\u5df2\u7ecf\u63a8\u51fa\u4e86AI \u89c6\u9891\u751f\u6210\u5de5\u5177\uff0c\u91c7\u7528\u7684\u662f\u6269\u6563\u6a21\u578b\u6280\u672f\u8def\u7ebf\uff0c\u4e24\u4e2a\u5de5\u5177\u7684\u5171\u540c\u70b9\u90fd\u662f\u5c06\u9759\u6001\u56fe\u53d8\u6210\u52a8\u6001\u89c6\u9891\u3002\u5176\u4e2d\u963f\u91cc\u5df4\u5df4\u667a\u80fd\u8ba1\u7b97\u7814\u7a76\u9662\u5f00\u53d1\u7684Animate Anyone\uff0c\u53ea\u9700\u8981\u7528\u6237\u63d0\u4f9b\u4e00\u4e2a\u9759\u6001\u7684\u89d2\u8272\u56fe\u50cf\uff0c\u518d\u52a0\u4e0a\u4e00\u4e9b\u52a8\u4f5c\u3001\u59ff\u52bf\uff0c\u4fbf\u53ef\u5c06\u5176\u52a8\u753b\u5316\uff1b\u5b57\u8282\u8df3\u52a8\u5219\u662f\u548c\u65b0\u52a0\u5761\u56fd\u7acb\u5927\u5b66\u8054\u5408\u63a8\u51fa\u4e86Magic Animate\uff0c\u540c\u6837\u662f\u9759\u6001\u56fe\u751f\u6210\u52a8\u6001\u89c6\u9891\uff0c\u76f8\u6bd4\u963f\u91cc\u591a\u4e86\u4e00\u80a1\u201c\u793e\u4f1a\u6447\u201d\u7684\u5473\u9053\u3002<\/p>\n\n\n\n
\u636e\u8ba1\u7b97\u673a\u4e1a\u5185\u4eba\u58eb\u5b9e\u9645\u6d4b\u8bc4\uff0cAnimate Anyone\u548cMagic Animate\u6587\u751f\u89c6\u9891\u6548\u679c\u96be\u8bf4\u7406\u60f3\uff0c\u524d\u8005\u96be\u4ee5\u751f\u6210\u7a33\u5b9a\u7684\u624b\u90e8\u8fd0\u52a8\u751f\u6210\u7ed3\u679c\uff0c\u5bfc\u81f4\u626d\u66f2\u548c\u8fd0\u52a8\u6a21\u7cca\uff0c\u4fa7\u9762\u548c\u80cc\u9762\u56fe\u7247\u7684\u751f\u6210\u6548\u679c\u4e5f\u900a\u4e8e\u4eba\u7269\u6b63\u9762\u56fe\u7247\u751f\u6210\u6548\u679c\uff1b\u540e\u8005\u751f\u6210\u6548\u679c\u6709\u5931\u771f\uff0c\u79bb\u5b9e\u9645\u843d\u5730\u5e94\u7528\u8fd8\u6709\u5f88\u957f\u4e00\u6bb5\u8ddd\u79bb\u3002\u5982\u679c\u60f3\u6253\u5f00\u5e02\u573a\uff0cAI \u6587\u751f\u89c6\u9891\u5e94\u7528\u9700\u8981\u5177\u5907\u4e00\u5b9a\u65f6\u957f\u3001\u4f18\u826f\u7684\u753b\u8d28\u3001\u521b\u610f\u903b\u8f91\u4ee5\u53ca\u8fd8\u539f\u6307\u4ee4\u8981\u6c42\u7684\u80fd\u529b\uff0c\u8ba1\u7b97\u590d\u6742\u5ea6\u663e\u8457\u63d0\u5347\uff0c\u5bf9\u7b97\u529b\u7684\u9700\u6c42\u4e5f\u66f4\u9ad8\u3002<\/p>\n\n\n\n
\u5728OpenAI\u5b98\u7f51\u516c\u5e03\u768448\u4e2a\u6f14\u793a\u89c6\u9891\u6765\u770b\uff0cSora\u4f3c\u4e4e\u5df2\u7a81\u7834AI\u6587\u751f\u89c6\u9891\u5b58\u5728\u7684\u6280\u672f\u96be\u9898\uff0c\u4ec5\u4ec5\u6839\u636e\u4e00\u53e5\u7b80\u5355\u7684\u63d0\u793a\u8bed\u5c31\u80fd\u751f\u6210\u65f6\u95f4\u957f\u3001\u7a33\u5b9a\u6027\u597d\u4ee5\u53ca\u6e05\u6670\u5ea6\u9ad8\u768460\u79d2\u89c6\u9891\uff0c\u7edd\u5bf9\u7b97\u5f97\u4e0a\u5f53\u524d\u884c\u4e1a\u7fd8\u695a\u3002<\/p>\n\n\n\n
\u4e8c\u3001Sora\u5728\u8bad\u7ec3\u4e2d\u638c\u63e1\u4e16\u754c\u201c\u7269\u7406\u89c4\u5219\u201d<\/h2>\n\n\n\n
\u6839\u636eOpenAI\u5b98\u7f51\u6280\u672f\u6587\u6863\uff0c\u4ed6\u4eec\u6b63\u5728\u6559\u4eba\u5de5\u667a\u80fd\u7406\u89e3\u548c\u6a21\u62df\u8fd0\u52a8\u4e2d\u7684\u7269\u7406\u4e16\u754c\uff0c\u76ee\u6807\u662f\u8bad\u7ec3\u6a21\u578b\uff0c\u5e2e\u52a9\u4eba\u4eec\u89e3\u51b3\u9700\u8981\u73b0\u5b9e\u4e16\u754c\u4ea4\u4e92\u7684\u95ee\u9898\u3002Sora\u5c31\u662f\u8fd9\u79cd\u601d\u8def\u4e0b\u7684\u6770\u4f5c\u3002Sora\u5bf9\u8bed\u8a00\u6709\u6df1\u523b\u7406\u89e3\uff0c\u80fd\u591f\u51c6\u786e\u5730\u89e3\u91ca\u63d0\u793a\u5e76\u751f\u6210\u8868\u8fbe\u751f\u52a8\u60c5\u611f\u7684\u5f15\u4eba\u6ce8\u76ee\u7684\u89d2\u8272\uff0c\u80fd\u751f\u6210\u5177\u6709\u591a\u4e2a\u89d2\u8272\u3001\u7279\u5b9a\u7c7b\u578b\u7684\u8fd0\u52a8\u4ee5\u53ca\u4e3b\u9898\u548c\u80cc\u666f\u7684\u51c6\u786e\u7ec6\u8282\u7684\u590d\u6742\u573a\u666f\uff0c\u4e86\u89e3\u7528\u6237\u5728\u63d0\u793a\u4e2d\u8981\u6c42\u7684\u5185\u5bb9\u4ee5\u53ca\u8fd9\u4e9b\u4e1c\u897f\u5728\u7269\u7406\u4e16\u754c\u4e2d\u7684\u5b58\u5728\u65b9\u5f0f\u3002 CXO UNION-CXO\u8054\u76df\uff08cxounion.cn\uff09<\/mark><\/p>\n\n\n\n
OpenAI\u5b98\u7f51\u516c\u5e03\u768448\u4e2a\u6f14\u793a\u89c6\u9891\u4e2d\u6709\u4e00\u4e2a\u89c6\u9891\u6587\u5b57\u63d0\u793a\u662f\uff1a\u201c\u903c\u771f\u7684\u7279\u5199\u89c6\u9891\uff0c\u4e24\u8258\u6d77\u76d7\u8239\u5728\u4e00\u676f\u5496\u5561\u4e2d\u822a\u884c\u65f6\u76f8\u4e92\u4e89\u6597\u3002\u201d\u4e0d\u59a8\u5c31\u6b64\u6765\u5206\u6790\u4e00\u4e0b\uff0cSora\u5230\u5e95\u662f\u5982\u4f55\u6839\u636e\u8fd9\u6761\u63d0\u793a\u8bcd\u751f\u6210\u89c6\u9891\u3002<\/p>\n\n\n\n
$\"\"$
Sora\u6587\u751f\u89c6\u9891\u6f14\u793a\u6548\u679c<\/figcaption><\/figure>\n\n\n\n
\u63d0\u793a\uff1a\u903c\u771f\u7684\u7279\u5199\u89c6\u9891\uff0c\u4e24\u8258\u6d77\u76d7\u8239\u5728\u4e00\u676f\u5496\u5561\u4e2d\u822a\u884c\u65f6\u76f8\u4e92\u4e89\u6597\u3002<\/p>\n\n\n\n
\u9996\u5148\uff0cSora\u6a21\u62df\u5668\u5b9e\u4f8b\u5316\u4e24\u4e2a\u7cbe\u7f8e\u7684\u4e09\u7ef4\u8d44\u4ea7\uff0c\u5373\u88c5\u9970\u5404\u5f02\u7684\u6d77\u76d7\u8239\uff0c\u8fd9\u91cc\u5fc5\u987b\u5728\u6f5c\u5728\u7a7a\u95f4\u7684\u9690\u5f0f\u4e2d\u89e3\u51b3\u6587\u672c\u52303D\u7684\u95ee\u9898\u3002\u5176\u6b21\uff0c\u4fdd\u6301\u4e09\u7ef4\u7269\u4f53\u5728\u822a\u884c\u548c\u907f\u5f00\u5bf9\u65b9\u7684\u8def\u5f84\u65f6\u59cb\u7ec8\u4fdd\u6301\u52a8\u753b\u6548\u679c\u3002\u7b2c\u4e09\uff0c\u201c\u61c2\u201d\u5496\u5561\u7684\u6d41\u4f53\u529b\u5b66\uff0c\u751a\u81f3\u662f\u8239\u53ea\u5468\u56f4\u5f62\u6210\u7684\u6ce1\u6cab\uff0c\u8fd9\u91cc\u7684\u6d41\u4f53\u6a21\u62df\u662f\u8ba1\u7b97\u673a\u56fe\u5f62\u5b66\u7684\u4e00\u4e2a\u5b8c\u6574\u5b50\u9886\u57df\uff0c\u9700\u8981\u975e\u5e38\u590d\u6742\u7684\u7b97\u6cd5\u548c\u65b9\u7a0b\u3002\u7b2c\u56db\uff0c\u903c\u771f\u5ea6\uff0c\u8fd9\u91cc\u9700\u8981\u8f6f\u4ef6\u7b97\u6cd5\uff0c\u4e5f\u9700\u8981\u786c\u4ef6\u652f\u6301\uff0cNVIDIA GPU\u5149\u7ebf\u8ffd\u8e2a\u6280\u672f\u80fd\u5b9e\u73b0\u63a5\u8fd1\u771f\u5b9e\u4e16\u754c\u7684\u6e32\u67d3\u6548\u679c\u3002\u503c\u5f97\u6ce8\u610f\u7684\u662f\uff0c\u8fd9\u91cc\u6a21\u62df\u5668\u8fd8\u9700\u8981\u8003\u8651\u676f\u5b50\u7684\u4f53\u79ef\u4e0e\u6d77\u6d0b\u76f8\u6bd4\u8f83\u5c0f\uff0c\u5fc5\u987b\u91c7\u7528\u4e86\u503e\u659c\u79fb\u4f4d\u6444\u5f71\u6280\u672f\uff0c\u8425\u9020\u51fa\u4e00\u79cd\u2018\u5fae\u5c0f\u2019\u7684\u611f\u89c9\u3002<\/p>\n\n\n\n
\u770b\u4f3c\u7b80\u5355\uff0c\u5b9e\u5219\u76f8\u5f53\u590d\u6742\u3002OpenAI\u867d\u7136\u6ca1\u6709\u516c\u5e03Sora\u7684\u6280\u672f\u6587\u6863\uff0c\u4f46\u5374\u4ecb\u7ecd\u4e86\u5b83\u7684\u57fa\u672c\u539f\u7406\uff0c\u5373Sora\u901a\u8fc7\u5b66\u4e60\u89c6\u9891\u6765\u7406\u89e3\u73b0\u5b9e\u4e16\u754c\u7684\u52a8\u6001\u53d8\u5316\uff0c\u5e76\u7528\u8ba1\u7b97\u673a\u89c6\u89c9\u6280\u672f\u6a21\u62df\u8fd9\u4e9b\u53d8\u5316\uff0c\u4ece\u800c\u521b\u9020\u51fa\u65b0\u7684\u89c6\u89c9\u5185\u5bb9\u3002\u5c31\u662f\u901a\u8fc7\u4e0d\u65ad\u5730\u5b66\u4e60\u8bad\u7ec3\u6765\u4e86\u89e3\u4e16\u754c\u7684\u201c\u7269\u7406\u89c4\u5f8b\u201d\u3002\u96be\u602a\u82f1\u4f1f\u8fbe\u4eba\u5de5\u667a\u80fd\u7814\u7a76\u9662Jim Fan\u8bf4\uff1a\u201cSora\u662f\u4e00\u4e2a\u6570\u636e\u9a71\u52a8\u7684\u7269\u7406\u5f15\u64ce\u3002\u201d<\/p>\n\n\n\n
2023\u5e7411\u6708\uff0c\u7f8e\u56fdAI\u521d\u521b\u516c\u53f8Pika labs\u4e5f\u53d1\u5e03\u4e86\u7b2c\u4e00\u4e2a\u6587\u751f\u89c6\u9891\u4ea7\u54c1Pika 1.0\uff0c\u53ea\u9700\u8981\u5728\u89c6\u9891\u7f16\u8f91\u5668\u4e2d\u5199\u4e0b\u63d0\u793a\u8bcd\uff0c\u5373\u53ef\u751f\u4ea7\u9ad8\u8d28\u91cf\u7684\u89c6\u9891\uff0c\u6216\u8005\u5bf9\u89c6\u9891\u5143\u7d20\u8fdb\u884c\u7f16\u8f91\u548c\u4fee\u6539\u3002\u4f46\u4e0eSora\u76f8\u6bd4\uff0cPika 1.0\u6240\u7f3a\u5931\u7684\u5c31\u662f\u901a\u8fc7\u5b66\u4e60\u8bad\u7ec3\u79ef\u7d2f\u4e86\u89e3\u4e16\u754c\u89c4\u5219\u7684\u80fd\u529b\u3002 CXO UNION-CXO\u8054\u76df\uff08cxounion.cn\uff09<\/mark><\/p>\n\n\n\n
\u5c31\u5728Sora\u53d1\u5e03\u7684\u8fd9\u51e0\u5929\uff0c\u5404\u4e2a\u884c\u4e1a\u5a92\u4f53\u4e5f\u5728\u6df1\u6316Sora\u7684\u6280\u672f\u7ec6\u8282\uff0c\u603b\u7ed3\u4e86Sora\u6a21\u578b\u9664\u4e86\u6587\u672c\u5230\u89c6\u9891\u751f\u6210\u80fd\u529b\u3001\u8bed\u8a00\u7406\u89e3\u80fd\u529b\u3001\u9759\u6001\u56fe\u50cf\u751f\u6210\u89c6\u9891\u80fd\u529b\uff0c\u6700\u5927\u7684\u521b\u65b0\u662f\u5b9e\u73b0\u4e86\u590d\u6742\u573a\u666f\u548c\u89d2\u8272\u751f\u6210\u80fd\u529b\u3001\u591a\u955c\u5934\u751f\u6210\u80fd\u529b\u4ee5\u53ca\u7269\u7406\u4e16\u754c\u6a21\u62df\u80fd\u529b\uff0c\u540e\u9762\u8fd9\u4e09\u70b9\u4e5f\u662f\u5176\u4ed6AI\u6587\u751f\u89c6\u9891\u5de5\u5177\u6240\u4e0d\u5177\u5907\u7684\u3002<\/p>\n\n\n\n
\u53ef\u4ee5\u8bf4\uff0cSora\u7684\u51fa\u73b0\u9884\u793a\u7740\u4e00\u4e2a\u5168\u65b0\u7684\u89c6\u89c9\u53d9\u4e8b\u65f6\u4ee3\u7684\u5230\u6765\uff0c\u5b83\u80fd\u591f\u5c06\u4eba\u4eec\u7684\u60f3\u8c61\u529b\u8f6c\u5316\u4e3a\u751f\u52a8\u7684\u52a8\u6001\u753b\u9762\uff0c\u5c06\u6587\u5b57\u7684\u9b54\u529b\u8f6c\u5316\u4e3a\u89c6\u89c9\u7684\u76db\u5bb4\u3002\u5728\u8fd9\u4e2a\u7531\u6570\u636e\u548c\u7b97\u6cd5\u7f16\u7ec7\u7684\u672a\u6765\uff0cSora\u6b63\u4ee5\u5176\u72ec\u7279\u7684\u65b9\u5f0f\uff0c\u91cd\u65b0\u5b9a\u4e49\u7740\u6211\u4eec\u4e0e\u6570\u5b57\u4e16\u754c\u7684\u4e92\u52a8\u3002<\/p>\n\n\n\n
\u4e09\u3001Sora\u5c06\u6210\u4e3a\u884c\u4e1a\u53d8\u9769\u7684\u98a0\u8986\u6027\u529b\u91cf<\/h2>\n\n\n\n
\u7ee7\u6587\u672c\u3001\u56fe\u7247\u7684\u81ea\u52a8\u751f\u6210\u4e4b\u540e\uff0c\u201c\u89c6\u9891\u751f\u6210\u201d\u8fd9\u4e2a\u88ab\u79f0\u4e3a\u6700\u96be\u653b\u514b\u7684\u201c\u5c71\u5934\u201d\u4e5f\u88abAI\u62ff\u4e0b\u3002\u5e02\u573a\u89c2\u5bdf\u4eba\u58eb\u8ba4\u4e3a\uff0cSora\u7684\u51fa\u73b0\u5c06\u91cd\u5851\u89c6\u9891\u884c\u4e1a\uff0c\u50ac\u53d8\u793e\u4ea4\u5e73\u53f0\u3002\u4e0e\u573a\u666f\u53ef\u89c6\u5316\u6709\u5173\u7684\u5e94\u7528\uff0c\u5982\u4eff\u771f\u3001\u5efa\u6a21\u3001\u7279\u6548\u3001\u5e7f\u544a\u7b49\u90fd\u5c06\u9762\u4e34\u98a0\u8986\u6027\u7684\u53d8\u9769\uff0c\u60f3\u8c61\u529b\u7684\u8868\u8fbe\u83b7\u5f97\u524d\u6240\u672a\u6709\u7684\u7a7a\u95f4\uff0c\u53d9\u4e8b\u8303\u5f0f\u5c06\u8d85\u8d8a\u4f20\u7edf\u7684\u754c\u9650\u3002<\/p>\n\n\n\n
360\u96c6\u56e2\u521b\u59cb\u4eba\u5468\u9e3f\u794e\u8868\u793a\uff0cSora\u7684\u53d1\u5e03\u662fOpenAI\u5229\u7528\u5b83\u7684\u5927\u8bed\u8a00\u6a21\u578b\u4f18\u52bf\uff0c\u628aLLM\u548cDiffusion\u7ed3\u5408\u8d77\u6765\u8bad\u7ec3\uff0c\u8ba9Sora\u5b9e\u73b0\u5bf9\u73b0\u5b9e\u4e16\u754c\u7684\u7406\u89e3\u548c\u5bf9\u4e16\u754c\u7684\u6a21\u62df\u4e24\u5c42\u80fd\u529b\u3002\u4ed6\u8ba4\u4e3a\u6709\u5f3a\u52b2\u7684\u5927\u6a21\u578b\u505a\u5e95\u5b50\uff0c\u57fa\u4e8e\u5bf9\u4eba\u7c7b\u8bed\u8a00\u3001\u77e5\u8bc6\u548c\u4e16\u754c\u6a21\u578b\u7684\u4e86\u89e3\uff0c\u518d\u53e0\u52a0\u5f88\u591a\u5176\u4ed6\u7684\u6280\u672f\uff0c\u5c31\u53ef\u4ee5\u521b\u9020\u5404\u4e2a\u9886\u57df\u7684\u8d85\u7ea7\u5de5\u5177\uff0c\u6bd4\u5982\u751f\u7269\u533b\u5b66\u3001\u86cb\u767d\u8d28\u548c\u57fa\u56e0\u7814\u7a76\uff0c\u5728\u5305\u62ec\u7269\u7406\u3001\u5316\u5b66\u3001\u6570\u5b66\u7684\u5b66\u79d1\u7814\u7a76\u4e0a\u53d1\u6325\u4f5c\u7528\u3002 CXO UNION-CXO\u8054\u76df\uff08cxounion.cn\uff09<\/mark><\/p>\n\n\n\n
\u5728\u65b0\u5de5\u4e1a\u7f51\u770b\u6765\uff0c\u4efb\u4f55\u6280\u672f\u7684\u53d1\u5c55\u4e0e\u6f14\u8fdb\u90fd\u6709\u4e00\u4e2a\u5faa\u5e8f\u6e10\u8fdb\u7684\u8fc7\u7a0b\u3002\u76ee\u524d\uff0c\u4ee5Sora\u4e3a\u4ee3\u8868\u7684AI\u6587\u751f\u89c6\u9891\u6280\u672f\u8fd8\u4e0d\u8db3\u4ee5\u8fbe\u5230\u957f\u65f6\u95f4\u7684\u8fde\u7eed\u6027\u8981\u6c42\uff0c\u5728\u6a21\u62df\u590d\u6742\u7269\u7406\u73b0\u8c61\u548c\u7406\u89e3\u590d\u6742\u56e0\u679c\u5173\u7cfb\u65b9\u9762\uff0c\u8fd8\u5b58\u5728\u5931\u51c6\u7684\u7f3a\u9677\uff0c\u4f46\u968f\u7740\u591a\u6a21\u6001\u5927\u6a21\u578b\u80fd\u529b\u7684\u589e\u5f3a\u4ee5\u53caAI\u6280\u672f\u7684\u4e0d\u65ad\u8fed\u4ee3\uff0c\u4e0e\u89c6\u9891\u5316\u76f8\u5173\u7684AI\u6587\u751f\u89c6\u9891\u573a\u666f\u66ff\u4ee3\u5c06\u6210\u4e3a\u53ef\u80fd\u3002<\/p>\n\n\n\n
\u5c31\u5de5\u4e1a\u6765\u8bf4\uff0c\u80fd\u60f3\u8c61\u7684\u66ff\u4ee3\u573a\u666f\u5c31\u5305\u62ec\u4ea7\u54c1\u5efa\u6a21\u4e0e\u4eff\u771f\u3001\u5de5\u5382\u5efa\u6a21\u4e0e\u4eff\u771f\u3001\u5de5\u4e1a\u5143\u5b87\u5b99\u3001\u5de5\u4e1a\u6570\u5b57\u5b6a\u751f\u4ee5\u53ca\u4ea7\u54c1\u57f9\u8bad\u4e0e\u8fd0\u7ef4\u7b49\u573a\u666f\uff0c\u81f3\u5c11\u5e94\u5c06AI\u6587\u751f\u89c6\u9891\u6280\u672f\u4f5c\u4e3a\u4e00\u79cd\u4f7f\u80fd\u6280\u672f\uff0c\u901a\u8fc7\u79fb\u690d\u6216\u5d4c\u5165\u7b49\u624b\u6bb5\uff0c\u7814\u7a76\u5728\u7279\u5b9a\u573a\u666f\u4e2d\u5e94\u7528\u7684\u53ef\u80fd\u6027\u3002\u751a\u81f3\u6709\u4e00\u4e9b\u822a\u7a7a\u754c\u7684\u4e13\u5bb6\u63d0\u51fa\uff0c\u5728\u8bf8\u5982\u822a\u7a7a\u5668\u5e94\u7528\u73af\u5883\u4e0e\u529f\u80fd\u6027\u80fd\u6a21\u62df\u3001\u7cfb\u7edf\u654f\u611f\u6027\u4e0e\u6709\u6548\u6027\u8bc4\u5b9a\u3001\u5e7f\u4e49\u4eba\u673a\u754c\u9762\u6784\u5efa\u4e0e\u4f18\u5316\u7b49\u573a\u666f\u90fd\u53ef\u4ee5\u91c7\u7528AI\u6587\u751f\u89c6\u9891\u6280\u672f\uff0c\u5fc5\u8981\u65f6\u53ef\u7ec4\u6210\u56e2\u961f\u8fdb\u884c\u4e13\u95e8\u5316\u7814\u7a76\u3002<\/p>\n\n\n\n
OpenAI\u8868\u793a\uff0c\u901a\u8fc7\u6269\u5927\u89c6\u9891\u751f\u6210\u6a21\u578b\u7684\u89c4\u6a21\uff0c\u4ed6\u4eec\u6709\u671b\u6784\u5efa\u51fa\u80fd\u591f\u6a21\u62df\u7269\u7406\u4e16\u754c\u7684\u901a\u7528\u6a21\u62df\u5668\u3002\u540c\u65f6\u4e5f\u6307\u51fa\uff0cSora\u8fd8\u5b58\u5728\u4e0d\u80fd\u51c6\u786e\u5730\u6a21\u62df\u8bb8\u591a\u57fa\u672c\u76f8\u4e92\u4f5c\u7528\u7684\u7269\u7406\u8fc7\u7a0b\uff0c\u5982\u73bb\u7483\u7834\u788e\u7b49\u3002\u5728\u67d0\u4e9b\u4ea4\u4e92\u573a\u666f\u4e2d\u4e0d\u80fd\u603b\u662f\u4ea7\u751f\u6b63\u786e\u7684\u5bf9\u8c61\u72b6\u6001\u53d8\u5316\uff0c\u6bd4\u5982\u5403\u4e1c\u897f\uff0c\u8fd9\u90fd\u662f\u4e0b\u4e00\u6b65\u7814\u7a76\u548c\u7a81\u7834\u7684\u91cd\u70b9\u3002<\/p>\n\n\n\n
\u6211\u4eec\u8ba4\u4e3a\uff0c\u672a\u6765\u7684AI\u6587\u751f\u89c6\u9891\u53d1\u5c55\u9664\u4e86\u4e0d\u65ad\u4f18\u5316\u81ea\u7136\u8bed\u8a00\u5904\u7406\u3001\u89c6\u89c9\u5904\u7406\u4ee5\u53ca\u878d\u5408\u753b\u9762\u5408\u6210\u6280\u672f\uff0c\u8fd8\u6709\u8de8\u5b66\u79d1\u7684\u6280\u672f\u878d\u5408\u662f\u5fc5\u987b\u8de8\u8fc7\u7684\u574e\uff0c\u5f00\u542f\u901a\u7528\u4eba\u5de5\u667a\u80fd\u5728\u67d0\u4e9b\u5e94\u7528\u573a\u666f\u7684\u5c1d\u8bd5\uff0cSora\u4f5c\u4e3a\u80fd\u591f\u7406\u89e3\u548c\u6a21\u62df\u73b0\u5b9e\u4e16\u754c\u7684\u57fa\u7840\u6a21\u578b\u4e0e\u80fd\u529b\uff0c\u6709\u673a\u4f1a\u6210\u4e3a\u901a\u7528\u4eba\u5de5\u667a\u80fd\u53d1\u5c55\u9053\u8def\u4e0a\u7684\u91cd\u8981\u91cc\u7a0b\u7891\u3002<\/p>\n\n\n\n
$\"\"\/$ <\/figure>\n\n\n\n
\u7ffb\u8bd1\uff1a<\/h2>\n\n\n\n
What’s so amazing about Sora? It wants to build a data-driven physics engine that “knows the rules.<\/h3>\n\n\n\n
In the early morning of February 16, 2024 (February 15, United States time), OpenAI released the “Vincenne video” tool Sora, once again shocking the technology circle. Compared with the current average video generation length of only 4 seconds and the video effect of jitter and distortion, Sora can generate 60 seconds of coherent video based on simple prompt words, create vivid character expressions and complex mirrors, and the video has a high degree of fidelity and narrative effect. So that Sora once released caused a high degree of attention including Musk, Zhou Hongyi and other science and technology leaders, even Nvidia Artificial Intelligence Research Institute Jim Fan also said, “Sora is a data-driven physics engine.” CXO UNION-CXO\u8054\u76df\uff08cxounion.cn\uff09<\/mark><\/p>\n\n\n\n
Sora Vincennes video demonstration effect<\/p>\n\n\n\n
Hint: A stylish woman walks down a Tokyo street filled with warm glowing neon lights and animated city signs. She was wearing a black leather jacket, a long red dress, black boots and carrying a black purse. She was wearing dark glasses and red lipstick. She walked confidently and casually. The streets are damp and reflective, creating a mirror-like effect of colorful lights. Many pedestrians are walking around.<\/p>\n\n\n\n
Sora is an epoch-making Vincennes video product<\/h4>\n\n\n\n
In 2023, the multi-modal large model blooms in the application side, Vincennes diagram and Vincennes video tools mushroomed, as a content creator, the author has also paid to open a number of AI video tools, but the operation is more complex, the generation effect is difficult to be satisfied. Therefore, I am also looking forward to the emergence of a really good AI video tool to meet the needs of people with weak video creation skills, but I did not expect the reality to come so fast.<\/p>\n\n\n\n
AI Vincennes video was first mainly based on GAN (Generative Adversarial Network) model and VAE (variational autoencoder) for video generation. However, the video generated by these two frameworks is only suitable for static, single screen, and the resolution is very low, and the application range is narrow. The development of AI Vinson video technology has mainly formed two technical routes: one is based on Transformer model, which is also the most used large model base in text and image generation; The other is a wider application of the “diffusion model” in the field of video, which is also the current mainstream AI video technology route, which has more advantages in semantic understanding and content richness. CXO UNION-CXO\u8054\u76df\uff08cxounion.cn\uff09<\/mark><\/p>\n\n\n\n
According to the technical report published on the official website of OpenAI, Sora uses the Diffusion Transformer model, a model that combines the diffusion model and Transformer architecture. It processes the noisy image input through the Transformer codec. Predict a sharper version of the image at each step, generate the entire video at once or extend the generated video to make it longer, while solving the challenging problem of ensuring that the subject remains unchanged even when temporarily out of view.<\/p>\n\n\n\n
In fact, Alibaba and ByteDance two major industry giants have launched AI video generation tools last year, using the diffusion model technology route, the common point of the two tools is to turn static graphs into dynamic videos. The Animate Anyone, developed by the Alibaba Institute of Intelligent Computing, only requires the user to provide a static character image, plus some actions and postures, to animate it; Bytedance and the National University of Singapore jointly launched Magic Animate, the same static graph generated dynamic video, compared to Ali more than a “social shake” taste.<\/p>\n\n\n\n
According to the actual evaluation of the computer industry, the video effect of Animate Anyone and Magic Animate is not ideal. The former is difficult to generate stable hand motion generation results, resulting in distortion and motion blur, and the generation effect of side and back pictures is worse than that of the front pictures. The latter generation effect has distortion, and there is still a long distance from the actual landing application. If you want to open the market, AI Vinson video applications need to have a certain length of time, excellent picture quality, creative logic and the ability to restore instruction requirements, the computational complexity is significantly increased, and the demand for computing power is also higher.<\/p>\n\n\n\n
From the 48 demo videos published on OpenAI’s official website, Sora seems to have broken through the technical problems existing in AI Vincencene videos, and can generate 60-second videos with long time, good stability and high clarity just according to a simple prompt, which is definitely the current industry leader.<\/p>\n\n\n\n
Sora mastered the “physical rules” of the world in training<\/h4>\n\n\n\n
According to OpenAI’s website technical documentation, they are teaching AI to understand and simulate the physical world in motion, with the goal of training models to help people solve problems that require real-world interaction. Sora is a masterpiece in this vein. Sora has a deep understanding of language, is able to accurately interpret prompts and generate compelling characters that express vivid emotions, can generate complex scenes with multiple characters, specific types of movements, and exact details of themes and backgrounds, understands what the user is asking for in a prompt and how those things exist in the physical world. CXO UNION-CXO\u8054\u76df\uff08cxounion.cn\uff09<\/mark><\/p>\n\n\n\n
“Realistic close-up video of two pirate ships fighting each other while sailing over a cup of coffee,” reads one of the 48 demo videos posted on OpenAI’s website. Let’s take a look at how Sora generates videos based on this prompt word.<\/p>\n\n\n\n
Sora Vincennes video demonstration effect<\/p>\n\n\n\n
Tip: Realistic close-up video of two pirate ships fighting each other as they sail over a cup of coffee.<\/p>\n\n\n\n
First, the Sora emulator instantiates two beautiful 3D assets, namely a decorated pirate ship, where the text-to-3D problem must be solved implicitly in the potential space. Second, keep 3D objects animated as they navigate and avoid each other’s paths. Third, to “understand” the fluid dynamics of coffee, or even the foam that forms around a boat, fluid simulation here is a whole subfield of computer graphics that requires very complex algorithms and equations. Fourth, fidelity, which requires software algorithms, but also need hardware support, NVIDIA GPU ray tracing technology can achieve close to the real world rendering effect. It is worth noting that the simulator also needs to consider the small volume of the cup compared to the ocean, and must use tilt shift photography technology to create a “tiny” feeling.<\/p>\n\n\n\n
It seems simple, but it’s actually quite complicated. While OpenAI did not publish Sora’s technical documentation, it did introduce its basic principle that Sora learns video to understand the dynamics of the real world and uses computer vision technology to simulate those changes to create new visual content. It is through continuous learning and training to understand the “physical laws” of the world. No wonder Jim Fan of Nvidia’s AI Institute says, “Sora is a data-driven physics engine.”<\/p>\n\n\n\n
In November 2023, American AI startup Pika labs also released the first Vincenne video product, Pika 1.0, which only needs to write prompt words in the video editor to produce high-quality videos, or edit and modify video elements. But what is missing in Pika 1.0 compared to Sora is the ability to learn the rules of the world through learning and training.<\/p>\n\n\n\n
Just a few days after the release of Sora, various industry media are also digging deep into the technical details of Sora, summarizing the Sora model in addition to text-to-video generation capabilities, language understanding capabilities, and static image video generation capabilities, the biggest innovation is the realization of complex scene and character generation capabilities, multi-shot generation capabilities, and physical world simulation capabilities. The latter three points are also not available in other AI Vincennes video tools.<\/p>\n\n\n\n
It can be said that the emergence of Sora heralds the arrival of a new era of visual narration, which can transform people’s imagination into vivid dynamic pictures, and transform the magic of words into visual feast. In a future woven by data and algorithms, Sora is, in its own way, redefining how we interact with the digital world. CXO UNION-CXO\u8054\u76df\uff08cxounion.cn\uff09<\/mark><\/p>\n\n\n\n
Sora will become a disruptive force for industry change<\/h4>\n\n\n\n
After the automatic generation of text and pictures, “video generation”, which is known as the most difficult “mountain”, has also been taken down by AI. Market watchers believe that Sora’s emergence will reshape the video industry and accelerate the transformation of social platforms. Applications related to scene visualization, such as simulation, modeling, special effects, advertising, etc., will face subversive changes, the expression of imagination will gain unprecedented space, and narrative paradigms will transcend traditional boundaries.<\/p>\n\n\n\n
Zhou Hongyi, founder of 360 Group, said that the release of Sora is OpenAI using its advantages of large language model, combining LLM and Diffusion training, so that Sora can realize the understanding of the real world and the simulation of the world. He believes that with a strong foundation of large models, based on the understanding of human language, knowledge and models of the world, combined with many other technologies, you can create super tools in various fields, such as biomedical, protein and gene research, and play a role in the study of disciplines including physics, chemistry and mathematics.<\/p>\n\n\n\n
In the view of the new industry network, the development and evolution of any technology has a gradual process. At present, AI Vincencene video technology represented by Sora is not enough to meet the long-term continuity requirements, and there are still defects of misalignment in simulating complex physical phenomena and understanding complex causality. However, with the enhancement of multi-modal large model capabilities and the continuous iteration of AI technology, it will be possible to replace AI Vincene video scenes related to video.<\/p>\n\n\n\n
As far as industry is concerned, the alternative scenarios that can be imagined include product modeling and simulation, factory modeling and simulation, industrial metauniverse, industrial digital twins, and product training and operation and maintenance scenarios, at least AI video technology should be used as an enabling technology, through transplantation or embedding means, to study the possibility of application in specific scenarios. Some experts in the aviation industry have even proposed that AI Vinson video technology can be used in scenarios such as aircraft application environment and functional performance simulation, system sensitivity and effectiveness assessment, and generalized human-machine interface construction and optimization, and a team can be formed to conduct specialized research if necessary. CXO UNION-CXO\u8054\u76df\uff08cxounion.cn\uff09<\/mark><\/p>\n\n\n\n
By scaling up the video generation model, OpenAI says it hopes to build general-purpose simulators capable of simulating the physical world. It is also pointed out that Sora also exists many physical processes that cannot accurately simulate fundamental interactions, such as glass breakage. In some interaction scenarios, the correct object state changes cannot always be produced, such as eating, which is the focus of further research and breakthroughs.<\/p>\n\n\n\n
We believe that in the future development of AI Vinson video, in addition to continuously optimizing natural language processing, visual processing and integrated picture synthesis technology, interdisciplinary technology integration is a barrier that must be crossed, opening the attempt of general artificial intelligence in some application scenarios. Sora, as a basic model and ability to understand and simulate the real world, Has the opportunity to become an important milestone in the development of general artificial intelligence.<\/p>\n\n\n\n
\u7531CXO UNION-CXO\u8054\u76df\uff08cxounion.cn\uff09<\/a>\u8f6c\u8f7d\u800c\u6210\uff0c\u6765\u6e90\u4e8e\u65b0\u5de5\u4e1a\u7f51\uff1b\u7f16\u8f91\/\u7ffb\u8bd1\uff1aCXO UNIONCXO\u8054\u76df\u5c0fU\u3002<\/p>\n\n\n\n
\u5982\u9700\u52a0\u5165 CXO UNION\uff08CXO\u8054\u76df\uff09<\/a>\u9ad8\u7ba1\u793e\u7fa4\uff0c\u8bf7\u8054\u7cfb\u793e\u7fa4\u5c0f\u4f19\u4f34\u54e6~<\/p>\n\n\n\n
$\"\"\/$ <\/figure>\n\n\n\n
\u514d\u8d23\u58f0\u660e: \u672c\u7f51\u7ad9(http:\/\/www.cxounion.cn\/<\/a>)\u5185\u5bb9\u4e3b\u8981\u6765\u81ea\u539f\u521b\u3001\u5408\u4f5c\u5a92\u4f53\u4f9b\u7a3f\u548c\u7b2c\u4e09\u65b9\u6295\u7a3f\uff0c\u51e1\u5728\u672c\u7f51\u7ad9\u51fa\u73b0\u7684\u4fe1\u606f\uff0c\u5747\u4ec5\u4f9b\u53c2\u8003\u3002\u672c\u7f51\u7ad9\u5c06\u5c3d\u529b\u786e\u4fdd\u6240\u63d0\u4f9b\u4fe1\u606f\u7684\u51c6\u786e\u6027\u53ca\u53ef\u9760\u6027\uff0c\u4f46\u4e0d\u4fdd\u8bc1\u6709\u5173\u8d44\u6599\u7684\u51c6\u786e\u6027\u53ca\u53ef\u9760\u6027\uff0c\u8bfb\u8005\u5728\u4f7f\u7528\u524d\u8bf7\u8fdb\u4e00\u6b65\u6838\u5b9e\uff0c\u5e76\u5bf9\u4efb\u4f55\u81ea\u4e3b\u51b3\u5b9a\u7684\u884c\u4e3a\u8d1f\u8d23\u3002\u672c\u7f51\u7ad9\u5bf9\u6709\u5173\u8d44\u6599\u6240\u5f15\u81f4\u7684\u9519\u8bef\u3001\u4e0d\u786e\u6216\u9057\u6f0f\uff0c\u6982\u4e0d\u8d1f\u4efb\u4f55\u6cd5\u5f8b\u8d23\u4efb\u3002<\/p>\n\n\n\n
\u672c\u7f51\u7ad9\u520a\u8f7d\u7684\u6240\u6709\u5185\u5bb9(\u5305\u62ec\u4f46\u4e0d\u4ec5\u9650\u6587\u5b57\u3001\u56fe\u7247\u3001LOGO\u3001\u97f3\u9891\u3001\u89c6\u9891\u3001\u8f6f\u4ef6\u3001\u7a0b\u5e8f\u7b49) \u7248\u6743\u5f52\u539f\u4f5c\u8005\u6240\u6709\u3002\u4efb\u4f55\u5355\u4f4d\u6216\u4e2a\u4eba\u8ba4\u4e3a\u672c\u7f51\u7ad9\u4e2d\u7684\u5185\u5bb9\u53ef\u80fd\u6d89\u5acc\u4fb5\u72af\u5176\u77e5\u8bc6\u4ea7\u6743\u6216\u5b58\u5728\u4e0d\u5b9e\u5185\u5bb9\u65f6\uff0c\u8bf7\u53ca\u65f6\u901a\u77e5\u672c\u7ad9\uff0c\u4e88\u4ee5\u5220\u9664\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"
2024\u5e742\u670816\u65e5\u51cc\u6668\uff08\u7f8e\u56fd\u65f6\u95f42\u670815\u65e5\uff09\uff0cOpenAI\u53d1\u5e03\u4e86\u201c\u6587\u751f\u89c6\u9891\u201d\u7684\u5de5\u5177Sora\uff0c\u518d\u6b21\u9707\u64bc\u79d1\u6280\u5708\u3002<\/p>\n","protected":false},"author":1,"featured_media":15318,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[13,1],"tags":[61],"class_list":["post-15315","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-viewpoint","category-other-news","tag-61"],"_links":{"self":[{"href":"http:\/\/cxounion.cn\/index.php\/wp-json\/wp\/v2\/posts\/15315","targetHints":{"allow":["GET"]}}],"collection":[{"href":"http:\/\/cxounion.cn\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"http:\/\/cxounion.cn\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"http:\/\/cxounion.cn\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"http:\/\/cxounion.cn\/index.php\/wp-json\/wp\/v2\/comments?post=15315"}],"version-history":[{"count":2,"href":"http:\/\/cxounion.cn\/index.php\/wp-json\/wp\/v2\/posts\/15315\/revisions"}],"predecessor-version":[{"id":15323,"href":"http:\/\/cxounion.cn\/index.php\/wp-json\/wp\/v2\/posts\/15315\/revisions\/15323"}],"wp:featuredmedia":[{"embeddable":true,"href":"http:\/\/cxounion.cn\/index.php\/wp-json\/wp\/v2\/media\/15318"}],"wp:attachment":[{"href":"http:\/\/cxounion.cn\/index.php\/wp-json\/wp\/v2\/media?parent=15315"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/cxounion.cn\/index.php\/wp-json\/wp\/v2\/categories?post=15315"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/cxounion.cn\/index.php\/wp-json\/wp\/v2\/tags?post=15315"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}

Sora\u6587\u751f\u89c6\u9891\u6f14\u793a\u6548\u679c<\/figcaption><\/figure>\n\n\n\n
\u63d0\u793a\uff1a\u4e00\u4f4d\u65f6\u5c1a\u7684\u5973\u4eba\u8d70\u5728\u4e1c\u4eac\u7684\u8857\u9053\u4e0a\uff0c\u8857\u9053\u4e0a\u5230\u5904\u90fd\u662f\u6e29\u6696\u7684\u53d1\u5149\u9713\u8679\u706f\u548c\u52a8\u753b\u57ce\u5e02\u6807\u5fd7\u3002\u5979\u8eab\u7a7f\u9ed1\u8272\u76ae\u5939\u514b\uff0c\u7ea2\u8272\u957f\u88d9\uff0c\u9ed1\u8272\u9774\u5b50\uff0c\u80cc\u7740\u4e00\u4e2a\u9ed1\u8272\u94b1\u5305\u3002\u5979\u6234\u7740\u58a8\u955c\uff0c\u6d82\u7740\u7ea2\u8272\u53e3\u7ea2\u3002\u5979\u81ea\u4fe1\u800c\u968f\u610f\u5730\u8d70\u8def\u3002\u8857\u9053\u6f6e\u6e7f\u800c\u53cd\u5149\uff0c\u8425\u9020\u51fa\u4e94\u989c\u516d\u8272\u7684\u706f\u5149\u7684\u955c\u9762\u6548\u679c\u3002\u8bb8\u591a\u884c\u4eba\u56db\u5904\u8d70\u52a8\u3002 CXO UNION-CXO\u8054\u76df\uff08cxounion.cn\uff09<\/mark><\/p>\n\n\n\n
\u4e00\u3001Sora\u662f\u4e00\u6b3e\u5212\u65f6\u4ee3\u7684\u6587\u751f\u89c6\u9891\u4ea7\u54c1<\/h2>\n\n\n\n
2023\u5e74\uff0c\u591a\u6a21\u6001\u5927\u6a21\u578b\u5728\u5e94\u7528\u7aef\u767e\u82b1\u9f50\u653e\uff0c\u6587\u751f\u56fe\u548c\u6587\u751f\u89c6\u9891\u5de5\u5177\u5982\u96e8\u540e\u6625\u7b0b\u822c\u7206\u53d1\uff0c\u4f5c\u4e3a\u5185\u5bb9\u521b\u4f5c\u8005\uff0c\u7b14\u8005\u4e5f\u66fe\u4ed8\u8d39\u5f00\u901a\u4e86\u591a\u6b3eAI\u89c6\u9891\u5de5\u5177\uff0c\u4f46\u64cd\u4f5c\u8d77\u6765\u6bd4\u8f83\u590d\u6742\uff0c\u751f\u6210\u6548\u679c\u96be\u8bf4\u6ee1\u610f\u3002\u56e0\u6b64\uff0c\u4e5f\u5728\u671f\u5f85\u4e00\u6b3e\u771f\u6b63\u597d\u7528\u7684AI\u6587\u751f\u89c6\u9891\u5de5\u5177\u51fa\u73b0\uff0c\u6ee1\u8db3\u6211\u8fd9\u79cd\u89c6\u9891\u521b\u4f5c\u529f\u5e95\u8f83\u5f31\u7684\u4eba\u7fa4\u9700\u6c42\uff0c\u5374\u672a\u6599\u5230\u73b0\u5b9e\u6765\u7684\u5982\u6b64\u4e4b\u5feb\u3002<\/p>\n\n\n\n
AI\u6587\u751f\u89c6\u9891\u6700\u65e9\u4e3b\u8981\u57fa\u4e8eGAN\uff08\u751f\u6210\u5f0f\u5bf9\u6297\u7f51\u7edc\uff09\u6a21\u578b\u548c VAE\uff08\u53d8\u5206\u81ea\u7f16\u7801\u5668\uff09\u8fdb\u884c\u89c6\u9891\u751f\u6210\u3002\u4e0d\u8fc7\u8fd9\u4e24\u4e2a\u6846\u67b6\u751f\u6210\u7684\u89c6\u9891\u4ec5\u9002\u7528\u9759\u6001\u3001\u5355\u4e00\u753b\u9762\uff0c\u4e14\u5206\u8fa8\u7387\u6781\u4f4e\uff0c\u5e94\u7528\u8303\u56f4\u72ed\u7a84\u3002AI\u6587\u751f\u89c6\u9891\u6280\u672f\u53d1\u5c55\u5230\u73b0\u5728\uff0c\u4e3b\u8981\u5f62\u6210\u4e86\u4e24\u6761\u6280\u672f\u8def\u7ebf\uff1a\u4e00\u6761\u662f\u57fa\u4e8eTransformer\u6a21\u578b\uff0c\u8fd9\u4e5f\u662f\u6587\u672c\u548c\u56fe\u50cf\u751f\u6210\u4e2d\u5e94\u7528\u6700\u591a\u7684\u5927\u6a21\u578b\u5e95\u5ea7\uff1b\u53e6\u4e00\u6761\u5219\u662f\u5728\u89c6\u9891\u9886\u57df\u5e94\u7528\u66f4\u5e7f\u7684\u201c\u6269\u6563\u6a21\u578b\u201d\uff0c\u8fd9\u4e5f\u662f\u5f53\u524dAI\u6587\u751f\u89c6\u9891\u4e3b\u6d41\u6280\u672f\u8def\u7ebf\uff0c\u5728\u8bed\u4e49\u7406\u89e3\u3001\u5185\u5bb9\u4e30\u5bcc\u6027\u4e0a\u66f4\u6709\u4f18\u52bf\u3002<\/p>\n\n\n\n
\u636eOpenAI\u5b98\u7f51\u516c\u5f00\u6280\u672f\u62a5\u544a\uff0cSora \u91c7\u7528\u7684\u662f Diffusion Transformer \u6a21\u578b\uff0c\u4e00\u79cd\u7ed3\u5408\u4e86\u6269\u6563\u6a21\u578b\u548c Transformer \u67b6\u6784\u7684\u6a21\u578b\uff0c\u5b83\u901a\u8fc7 Transformer \u7684\u7f16\u89e3\u7801\u5668\u5904\u7406\u5e26\u566a\u58f0\u7684\u56fe\u50cf\u8f93\u5165\uff0c\u5728\u6bcf\u4e00\u6b65\u4e2d\u9884\u6d4b\u51fa\u66f4\u6e05\u6670\u7684\u56fe\u50cf\u7248\u672c\uff0c\u4e00\u6b21\u6027\u751f\u6210\u6574\u4e2a\u89c6\u9891\u6216\u6269\u5c55\u751f\u6210\u7684\u89c6\u9891\uff0c\u4f7f\u5176\u66f4\u957f\uff0c\u540c\u65f6\u89e3\u51b3\u4e86\u4e00\u4e2a\u5177\u6709\u6311\u6218\u6027\u7684\u95ee\u9898\uff0c\u5373\u786e\u4fdd\u4e3b\u4f53\u5373\u4f7f\u6682\u65f6\u79bb\u5f00\u89c6\u91ce\u4e5f\u4fdd\u6301\u4e0d\u53d8\u3002<\/p>\n\n\n\n
\u5b9e\u9645\u4e0a\uff0c\u963f\u91cc\u5df4\u5df4\u548c\u5b57\u8282\u8df3\u52a8\u4e24\u5927\u884c\u4e1a\u5de8\u5934\u53bb\u5e74\u5c31\u5df2\u7ecf\u63a8\u51fa\u4e86AI \u89c6\u9891\u751f\u6210\u5de5\u5177\uff0c\u91c7\u7528\u7684\u662f\u6269\u6563\u6a21\u578b\u6280\u672f\u8def\u7ebf\uff0c\u4e24\u4e2a\u5de5\u5177\u7684\u5171\u540c\u70b9\u90fd\u662f\u5c06\u9759\u6001\u56fe\u53d8\u6210\u52a8\u6001\u89c6\u9891\u3002\u5176\u4e2d\u963f\u91cc\u5df4\u5df4\u667a\u80fd\u8ba1\u7b97\u7814\u7a76\u9662\u5f00\u53d1\u7684Animate Anyone\uff0c\u53ea\u9700\u8981\u7528\u6237\u63d0\u4f9b\u4e00\u4e2a\u9759\u6001\u7684\u89d2\u8272\u56fe\u50cf\uff0c\u518d\u52a0\u4e0a\u4e00\u4e9b\u52a8\u4f5c\u3001\u59ff\u52bf\uff0c\u4fbf\u53ef\u5c06\u5176\u52a8\u753b\u5316\uff1b\u5b57\u8282\u8df3\u52a8\u5219\u662f\u548c\u65b0\u52a0\u5761\u56fd\u7acb\u5927\u5b66\u8054\u5408\u63a8\u51fa\u4e86Magic Animate\uff0c\u540c\u6837\u662f\u9759\u6001\u56fe\u751f\u6210\u52a8\u6001\u89c6\u9891\uff0c\u76f8\u6bd4\u963f\u91cc\u591a\u4e86\u4e00\u80a1\u201c\u793e\u4f1a\u6447\u201d\u7684\u5473\u9053\u3002<\/p>\n\n\n\n
\u636e\u8ba1\u7b97\u673a\u4e1a\u5185\u4eba\u58eb\u5b9e\u9645\u6d4b\u8bc4\uff0cAnimate Anyone\u548cMagic Animate\u6587\u751f\u89c6\u9891\u6548\u679c\u96be\u8bf4\u7406\u60f3\uff0c\u524d\u8005\u96be\u4ee5\u751f\u6210\u7a33\u5b9a\u7684\u624b\u90e8\u8fd0\u52a8\u751f\u6210\u7ed3\u679c\uff0c\u5bfc\u81f4\u626d\u66f2\u548c\u8fd0\u52a8\u6a21\u7cca\uff0c\u4fa7\u9762\u548c\u80cc\u9762\u56fe\u7247\u7684\u751f\u6210\u6548\u679c\u4e5f\u900a\u4e8e\u4eba\u7269\u6b63\u9762\u56fe\u7247\u751f\u6210\u6548\u679c\uff1b\u540e\u8005\u751f\u6210\u6548\u679c\u6709\u5931\u771f\uff0c\u79bb\u5b9e\u9645\u843d\u5730\u5e94\u7528\u8fd8\u6709\u5f88\u957f\u4e00\u6bb5\u8ddd\u79bb\u3002\u5982\u679c\u60f3\u6253\u5f00\u5e02\u573a\uff0cAI \u6587\u751f\u89c6\u9891\u5e94\u7528\u9700\u8981\u5177\u5907\u4e00\u5b9a\u65f6\u957f\u3001\u4f18\u826f\u7684\u753b\u8d28\u3001\u521b\u610f\u903b\u8f91\u4ee5\u53ca\u8fd8\u539f\u6307\u4ee4\u8981\u6c42\u7684\u80fd\u529b\uff0c\u8ba1\u7b97\u590d\u6742\u5ea6\u663e\u8457\u63d0\u5347\uff0c\u5bf9\u7b97\u529b\u7684\u9700\u6c42\u4e5f\u66f4\u9ad8\u3002<\/p>\n\n\n\n
\u5728OpenAI\u5b98\u7f51\u516c\u5e03\u768448\u4e2a\u6f14\u793a\u89c6\u9891\u6765\u770b\uff0cSora\u4f3c\u4e4e\u5df2\u7a81\u7834AI\u6587\u751f\u89c6\u9891\u5b58\u5728\u7684\u6280\u672f\u96be\u9898\uff0c\u4ec5\u4ec5\u6839\u636e\u4e00\u53e5\u7b80\u5355\u7684\u63d0\u793a\u8bed\u5c31\u80fd\u751f\u6210\u65f6\u95f4\u957f\u3001\u7a33\u5b9a\u6027\u597d\u4ee5\u53ca\u6e05\u6670\u5ea6\u9ad8\u768460\u79d2\u89c6\u9891\uff0c\u7edd\u5bf9\u7b97\u5f97\u4e0a\u5f53\u524d\u884c\u4e1a\u7fd8\u695a\u3002<\/p>\n\n\n\n
\u4e8c\u3001Sora\u5728\u8bad\u7ec3\u4e2d\u638c\u63e1\u4e16\u754c\u201c\u7269\u7406\u89c4\u5219\u201d<\/h2>\n\n\n\n
\u6839\u636eOpenAI\u5b98\u7f51\u6280\u672f\u6587\u6863\uff0c\u4ed6\u4eec\u6b63\u5728\u6559\u4eba\u5de5\u667a\u80fd\u7406\u89e3\u548c\u6a21\u62df\u8fd0\u52a8\u4e2d\u7684\u7269\u7406\u4e16\u754c\uff0c\u76ee\u6807\u662f\u8bad\u7ec3\u6a21\u578b\uff0c\u5e2e\u52a9\u4eba\u4eec\u89e3\u51b3\u9700\u8981\u73b0\u5b9e\u4e16\u754c\u4ea4\u4e92\u7684\u95ee\u9898\u3002Sora\u5c31\u662f\u8fd9\u79cd\u601d\u8def\u4e0b\u7684\u6770\u4f5c\u3002Sora\u5bf9\u8bed\u8a00\u6709\u6df1\u523b\u7406\u89e3\uff0c\u80fd\u591f\u51c6\u786e\u5730\u89e3\u91ca\u63d0\u793a\u5e76\u751f\u6210\u8868\u8fbe\u751f\u52a8\u60c5\u611f\u7684\u5f15\u4eba\u6ce8\u76ee\u7684\u89d2\u8272\uff0c\u80fd\u751f\u6210\u5177\u6709\u591a\u4e2a\u89d2\u8272\u3001\u7279\u5b9a\u7c7b\u578b\u7684\u8fd0\u52a8\u4ee5\u53ca\u4e3b\u9898\u548c\u80cc\u666f\u7684\u51c6\u786e\u7ec6\u8282\u7684\u590d\u6742\u573a\u666f\uff0c\u4e86\u89e3\u7528\u6237\u5728\u63d0\u793a\u4e2d\u8981\u6c42\u7684\u5185\u5bb9\u4ee5\u53ca\u8fd9\u4e9b\u4e1c\u897f\u5728\u7269\u7406\u4e16\u754c\u4e2d\u7684\u5b58\u5728\u65b9\u5f0f\u3002 CXO UNION-CXO\u8054\u76df\uff08cxounion.cn\uff09<\/mark><\/p>\n\n\n\n
OpenAI\u5b98\u7f51\u516c\u5e03\u768448\u4e2a\u6f14\u793a\u89c6\u9891\u4e2d\u6709\u4e00\u4e2a\u89c6\u9891\u6587\u5b57\u63d0\u793a\u662f\uff1a\u201c\u903c\u771f\u7684\u7279\u5199\u89c6\u9891\uff0c\u4e24\u8258\u6d77\u76d7\u8239\u5728\u4e00\u676f\u5496\u5561\u4e2d\u822a\u884c\u65f6\u76f8\u4e92\u4e89\u6597\u3002\u201d\u4e0d\u59a8\u5c31\u6b64\u6765\u5206\u6790\u4e00\u4e0b\uff0cSora\u5230\u5e95\u662f\u5982\u4f55\u6839\u636e\u8fd9\u6761\u63d0\u793a\u8bcd\u751f\u6210\u89c6\u9891\u3002<\/p>\n\n\n\n
$\"\"$
Sora\u6587\u751f\u89c6\u9891\u6f14\u793a\u6548\u679c<\/figcaption><\/figure>\n\n\n\n
\u63d0\u793a\uff1a\u903c\u771f\u7684\u7279\u5199\u89c6\u9891\uff0c\u4e24\u8258\u6d77\u76d7\u8239\u5728\u4e00\u676f\u5496\u5561\u4e2d\u822a\u884c\u65f6\u76f8\u4e92\u4e89\u6597\u3002<\/p>\n\n\n\n
\u9996\u5148\uff0cSora\u6a21\u62df\u5668\u5b9e\u4f8b\u5316\u4e24\u4e2a\u7cbe\u7f8e\u7684\u4e09\u7ef4\u8d44\u4ea7\uff0c\u5373\u88c5\u9970\u5404\u5f02\u7684\u6d77\u76d7\u8239\uff0c\u8fd9\u91cc\u5fc5\u987b\u5728\u6f5c\u5728\u7a7a\u95f4\u7684\u9690\u5f0f\u4e2d\u89e3\u51b3\u6587\u672c\u52303D\u7684\u95ee\u9898\u3002\u5176\u6b21\uff0c\u4fdd\u6301\u4e09\u7ef4\u7269\u4f53\u5728\u822a\u884c\u548c\u907f\u5f00\u5bf9\u65b9\u7684\u8def\u5f84\u65f6\u59cb\u7ec8\u4fdd\u6301\u52a8\u753b\u6548\u679c\u3002\u7b2c\u4e09\uff0c\u201c\u61c2\u201d\u5496\u5561\u7684\u6d41\u4f53\u529b\u5b66\uff0c\u751a\u81f3\u662f\u8239\u53ea\u5468\u56f4\u5f62\u6210\u7684\u6ce1\u6cab\uff0c\u8fd9\u91cc\u7684\u6d41\u4f53\u6a21\u62df\u662f\u8ba1\u7b97\u673a\u56fe\u5f62\u5b66\u7684\u4e00\u4e2a\u5b8c\u6574\u5b50\u9886\u57df\uff0c\u9700\u8981\u975e\u5e38\u590d\u6742\u7684\u7b97\u6cd5\u548c\u65b9\u7a0b\u3002\u7b2c\u56db\uff0c\u903c\u771f\u5ea6\uff0c\u8fd9\u91cc\u9700\u8981\u8f6f\u4ef6\u7b97\u6cd5\uff0c\u4e5f\u9700\u8981\u786c\u4ef6\u652f\u6301\uff0cNVIDIA GPU\u5149\u7ebf\u8ffd\u8e2a\u6280\u672f\u80fd\u5b9e\u73b0\u63a5\u8fd1\u771f\u5b9e\u4e16\u754c\u7684\u6e32\u67d3\u6548\u679c\u3002\u503c\u5f97\u6ce8\u610f\u7684\u662f\uff0c\u8fd9\u91cc\u6a21\u62df\u5668\u8fd8\u9700\u8981\u8003\u8651\u676f\u5b50\u7684\u4f53\u79ef\u4e0e\u6d77\u6d0b\u76f8\u6bd4\u8f83\u5c0f\uff0c\u5fc5\u987b\u91c7\u7528\u4e86\u503e\u659c\u79fb\u4f4d\u6444\u5f71\u6280\u672f\uff0c\u8425\u9020\u51fa\u4e00\u79cd\u2018\u5fae\u5c0f\u2019\u7684\u611f\u89c9\u3002<\/p>\n\n\n\n
\u770b\u4f3c\u7b80\u5355\uff0c\u5b9e\u5219\u76f8\u5f53\u590d\u6742\u3002OpenAI\u867d\u7136\u6ca1\u6709\u516c\u5e03Sora\u7684\u6280\u672f\u6587\u6863\uff0c\u4f46\u5374\u4ecb\u7ecd\u4e86\u5b83\u7684\u57fa\u672c\u539f\u7406\uff0c\u5373Sora\u901a\u8fc7\u5b66\u4e60\u89c6\u9891\u6765\u7406\u89e3\u73b0\u5b9e\u4e16\u754c\u7684\u52a8\u6001\u53d8\u5316\uff0c\u5e76\u7528\u8ba1\u7b97\u673a\u89c6\u89c9\u6280\u672f\u6a21\u62df\u8fd9\u4e9b\u53d8\u5316\uff0c\u4ece\u800c\u521b\u9020\u51fa\u65b0\u7684\u89c6\u89c9\u5185\u5bb9\u3002\u5c31\u662f\u901a\u8fc7\u4e0d\u65ad\u5730\u5b66\u4e60\u8bad\u7ec3\u6765\u4e86\u89e3\u4e16\u754c\u7684\u201c\u7269\u7406\u89c4\u5f8b\u201d\u3002\u96be\u602a\u82f1\u4f1f\u8fbe\u4eba\u5de5\u667a\u80fd\u7814\u7a76\u9662Jim Fan\u8bf4\uff1a\u201cSora\u662f\u4e00\u4e2a\u6570\u636e\u9a71\u52a8\u7684\u7269\u7406\u5f15\u64ce\u3002\u201d<\/p>\n\n\n\n
2023\u5e7411\u6708\uff0c\u7f8e\u56fdAI\u521d\u521b\u516c\u53f8Pika labs\u4e5f\u53d1\u5e03\u4e86\u7b2c\u4e00\u4e2a\u6587\u751f\u89c6\u9891\u4ea7\u54c1Pika 1.0\uff0c\u53ea\u9700\u8981\u5728\u89c6\u9891\u7f16\u8f91\u5668\u4e2d\u5199\u4e0b\u63d0\u793a\u8bcd\uff0c\u5373\u53ef\u751f\u4ea7\u9ad8\u8d28\u91cf\u7684\u89c6\u9891\uff0c\u6216\u8005\u5bf9\u89c6\u9891\u5143\u7d20\u8fdb\u884c\u7f16\u8f91\u548c\u4fee\u6539\u3002\u4f46\u4e0eSora\u76f8\u6bd4\uff0cPika 1.0\u6240\u7f3a\u5931\u7684\u5c31\u662f\u901a\u8fc7\u5b66\u4e60\u8bad\u7ec3\u79ef\u7d2f\u4e86\u89e3\u4e16\u754c\u89c4\u5219\u7684\u80fd\u529b\u3002 CXO UNION-CXO\u8054\u76df\uff08cxounion.cn\uff09<\/mark><\/p>\n\n\n\n
\u5c31\u5728Sora\u53d1\u5e03\u7684\u8fd9\u51e0\u5929\uff0c\u5404\u4e2a\u884c\u4e1a\u5a92\u4f53\u4e5f\u5728\u6df1\u6316Sora\u7684\u6280\u672f\u7ec6\u8282\uff0c\u603b\u7ed3\u4e86Sora\u6a21\u578b\u9664\u4e86\u6587\u672c\u5230\u89c6\u9891\u751f\u6210\u80fd\u529b\u3001\u8bed\u8a00\u7406\u89e3\u80fd\u529b\u3001\u9759\u6001\u56fe\u50cf\u751f\u6210\u89c6\u9891\u80fd\u529b\uff0c\u6700\u5927\u7684\u521b\u65b0\u662f\u5b9e\u73b0\u4e86\u590d\u6742\u573a\u666f\u548c\u89d2\u8272\u751f\u6210\u80fd\u529b\u3001\u591a\u955c\u5934\u751f\u6210\u80fd\u529b\u4ee5\u53ca\u7269\u7406\u4e16\u754c\u6a21\u62df\u80fd\u529b\uff0c\u540e\u9762\u8fd9\u4e09\u70b9\u4e5f\u662f\u5176\u4ed6AI\u6587\u751f\u89c6\u9891\u5de5\u5177\u6240\u4e0d\u5177\u5907\u7684\u3002<\/p>\n\n\n\n
\u53ef\u4ee5\u8bf4\uff0cSora\u7684\u51fa\u73b0\u9884\u793a\u7740\u4e00\u4e2a\u5168\u65b0\u7684\u89c6\u89c9\u53d9\u4e8b\u65f6\u4ee3\u7684\u5230\u6765\uff0c\u5b83\u80fd\u591f\u5c06\u4eba\u4eec\u7684\u60f3\u8c61\u529b\u8f6c\u5316\u4e3a\u751f\u52a8\u7684\u52a8\u6001\u753b\u9762\uff0c\u5c06\u6587\u5b57\u7684\u9b54\u529b\u8f6c\u5316\u4e3a\u89c6\u89c9\u7684\u76db\u5bb4\u3002\u5728\u8fd9\u4e2a\u7531\u6570\u636e\u548c\u7b97\u6cd5\u7f16\u7ec7\u7684\u672a\u6765\uff0cSora\u6b63\u4ee5\u5176\u72ec\u7279\u7684\u65b9\u5f0f\uff0c\u91cd\u65b0\u5b9a\u4e49\u7740\u6211\u4eec\u4e0e\u6570\u5b57\u4e16\u754c\u7684\u4e92\u52a8\u3002<\/p>\n\n\n\n
\u4e09\u3001Sora\u5c06\u6210\u4e3a\u884c\u4e1a\u53d8\u9769\u7684\u98a0\u8986\u6027\u529b\u91cf<\/h2>\n\n\n\n
\u7ee7\u6587\u672c\u3001\u56fe\u7247\u7684\u81ea\u52a8\u751f\u6210\u4e4b\u540e\uff0c\u201c\u89c6\u9891\u751f\u6210\u201d\u8fd9\u4e2a\u88ab\u79f0\u4e3a\u6700\u96be\u653b\u514b\u7684\u201c\u5c71\u5934\u201d\u4e5f\u88abAI\u62ff\u4e0b\u3002\u5e02\u573a\u89c2\u5bdf\u4eba\u58eb\u8ba4\u4e3a\uff0cSora\u7684\u51fa\u73b0\u5c06\u91cd\u5851\u89c6\u9891\u884c\u4e1a\uff0c\u50ac\u53d8\u793e\u4ea4\u5e73\u53f0\u3002\u4e0e\u573a\u666f\u53ef\u89c6\u5316\u6709\u5173\u7684\u5e94\u7528\uff0c\u5982\u4eff\u771f\u3001\u5efa\u6a21\u3001\u7279\u6548\u3001\u5e7f\u544a\u7b49\u90fd\u5c06\u9762\u4e34\u98a0\u8986\u6027\u7684\u53d8\u9769\uff0c\u60f3\u8c61\u529b\u7684\u8868\u8fbe\u83b7\u5f97\u524d\u6240\u672a\u6709\u7684\u7a7a\u95f4\uff0c\u53d9\u4e8b\u8303\u5f0f\u5c06\u8d85\u8d8a\u4f20\u7edf\u7684\u754c\u9650\u3002<\/p>\n\n\n\n
360\u96c6\u56e2\u521b\u59cb\u4eba\u5468\u9e3f\u794e\u8868\u793a\uff0cSora\u7684\u53d1\u5e03\u662fOpenAI\u5229\u7528\u5b83\u7684\u5927\u8bed\u8a00\u6a21\u578b\u4f18\u52bf\uff0c\u628aLLM\u548cDiffusion\u7ed3\u5408\u8d77\u6765\u8bad\u7ec3\uff0c\u8ba9Sora\u5b9e\u73b0\u5bf9\u73b0\u5b9e\u4e16\u754c\u7684\u7406\u89e3\u548c\u5bf9\u4e16\u754c\u7684\u6a21\u62df\u4e24\u5c42\u80fd\u529b\u3002\u4ed6\u8ba4\u4e3a\u6709\u5f3a\u52b2\u7684\u5927\u6a21\u578b\u505a\u5e95\u5b50\uff0c\u57fa\u4e8e\u5bf9\u4eba\u7c7b\u8bed\u8a00\u3001\u77e5\u8bc6\u548c\u4e16\u754c\u6a21\u578b\u7684\u4e86\u89e3\uff0c\u518d\u53e0\u52a0\u5f88\u591a\u5176\u4ed6\u7684\u6280\u672f\uff0c\u5c31\u53ef\u4ee5\u521b\u9020\u5404\u4e2a\u9886\u57df\u7684\u8d85\u7ea7\u5de5\u5177\uff0c\u6bd4\u5982\u751f\u7269\u533b\u5b66\u3001\u86cb\u767d\u8d28\u548c\u57fa\u56e0\u7814\u7a76\uff0c\u5728\u5305\u62ec\u7269\u7406\u3001\u5316\u5b66\u3001\u6570\u5b66\u7684\u5b66\u79d1\u7814\u7a76\u4e0a\u53d1\u6325\u4f5c\u7528\u3002 CXO UNION-CXO\u8054\u76df\uff08cxounion.cn\uff09<\/mark><\/p>\n\n\n\n
\u5728\u65b0\u5de5\u4e1a\u7f51\u770b\u6765\uff0c\u4efb\u4f55\u6280\u672f\u7684\u53d1\u5c55\u4e0e\u6f14\u8fdb\u90fd\u6709\u4e00\u4e2a\u5faa\u5e8f\u6e10\u8fdb\u7684\u8fc7\u7a0b\u3002\u76ee\u524d\uff0c\u4ee5Sora\u4e3a\u4ee3\u8868\u7684AI\u6587\u751f\u89c6\u9891\u6280\u672f\u8fd8\u4e0d\u8db3\u4ee5\u8fbe\u5230\u957f\u65f6\u95f4\u7684\u8fde\u7eed\u6027\u8981\u6c42\uff0c\u5728\u6a21\u62df\u590d\u6742\u7269\u7406\u73b0\u8c61\u548c\u7406\u89e3\u590d\u6742\u56e0\u679c\u5173\u7cfb\u65b9\u9762\uff0c\u8fd8\u5b58\u5728\u5931\u51c6\u7684\u7f3a\u9677\uff0c\u4f46\u968f\u7740\u591a\u6a21\u6001\u5927\u6a21\u578b\u80fd\u529b\u7684\u589e\u5f3a\u4ee5\u53caAI\u6280\u672f\u7684\u4e0d\u65ad\u8fed\u4ee3\uff0c\u4e0e\u89c6\u9891\u5316\u76f8\u5173\u7684AI\u6587\u751f\u89c6\u9891\u573a\u666f\u66ff\u4ee3\u5c06\u6210\u4e3a\u53ef\u80fd\u3002<\/p>\n\n\n\n
\u5c31\u5de5\u4e1a\u6765\u8bf4\uff0c\u80fd\u60f3\u8c61\u7684\u66ff\u4ee3\u573a\u666f\u5c31\u5305\u62ec\u4ea7\u54c1\u5efa\u6a21\u4e0e\u4eff\u771f\u3001\u5de5\u5382\u5efa\u6a21\u4e0e\u4eff\u771f\u3001\u5de5\u4e1a\u5143\u5b87\u5b99\u3001\u5de5\u4e1a\u6570\u5b57\u5b6a\u751f\u4ee5\u53ca\u4ea7\u54c1\u57f9\u8bad\u4e0e\u8fd0\u7ef4\u7b49\u573a\u666f\uff0c\u81f3\u5c11\u5e94\u5c06AI\u6587\u751f\u89c6\u9891\u6280\u672f\u4f5c\u4e3a\u4e00\u79cd\u4f7f\u80fd\u6280\u672f\uff0c\u901a\u8fc7\u79fb\u690d\u6216\u5d4c\u5165\u7b49\u624b\u6bb5\uff0c\u7814\u7a76\u5728\u7279\u5b9a\u573a\u666f\u4e2d\u5e94\u7528\u7684\u53ef\u80fd\u6027\u3002\u751a\u81f3\u6709\u4e00\u4e9b\u822a\u7a7a\u754c\u7684\u4e13\u5bb6\u63d0\u51fa\uff0c\u5728\u8bf8\u5982\u822a\u7a7a\u5668\u5e94\u7528\u73af\u5883\u4e0e\u529f\u80fd\u6027\u80fd\u6a21\u62df\u3001\u7cfb\u7edf\u654f\u611f\u6027\u4e0e\u6709\u6548\u6027\u8bc4\u5b9a\u3001\u5e7f\u4e49\u4eba\u673a\u754c\u9762\u6784\u5efa\u4e0e\u4f18\u5316\u7b49\u573a\u666f\u90fd\u53ef\u4ee5\u91c7\u7528AI\u6587\u751f\u89c6\u9891\u6280\u672f\uff0c\u5fc5\u8981\u65f6\u53ef\u7ec4\u6210\u56e2\u961f\u8fdb\u884c\u4e13\u95e8\u5316\u7814\u7a76\u3002<\/p>\n\n\n\n
OpenAI\u8868\u793a\uff0c\u901a\u8fc7\u6269\u5927\u89c6\u9891\u751f\u6210\u6a21\u578b\u7684\u89c4\u6a21\uff0c\u4ed6\u4eec\u6709\u671b\u6784\u5efa\u51fa\u80fd\u591f\u6a21\u62df\u7269\u7406\u4e16\u754c\u7684\u901a\u7528\u6a21\u62df\u5668\u3002\u540c\u65f6\u4e5f\u6307\u51fa\uff0cSora\u8fd8\u5b58\u5728\u4e0d\u80fd\u51c6\u786e\u5730\u6a21\u62df\u8bb8\u591a\u57fa\u672c\u76f8\u4e92\u4f5c\u7528\u7684\u7269\u7406\u8fc7\u7a0b\uff0c\u5982\u73bb\u7483\u7834\u788e\u7b49\u3002\u5728\u67d0\u4e9b\u4ea4\u4e92\u573a\u666f\u4e2d\u4e0d\u80fd\u603b\u662f\u4ea7\u751f\u6b63\u786e\u7684\u5bf9\u8c61\u72b6\u6001\u53d8\u5316\uff0c\u6bd4\u5982\u5403\u4e1c\u897f\uff0c\u8fd9\u90fd\u662f\u4e0b\u4e00\u6b65\u7814\u7a76\u548c\u7a81\u7834\u7684\u91cd\u70b9\u3002<\/p>\n\n\n\n
\u6211\u4eec\u8ba4\u4e3a\uff0c\u672a\u6765\u7684AI\u6587\u751f\u89c6\u9891\u53d1\u5c55\u9664\u4e86\u4e0d\u65ad\u4f18\u5316\u81ea\u7136\u8bed\u8a00\u5904\u7406\u3001\u89c6\u89c9\u5904\u7406\u4ee5\u53ca\u878d\u5408\u753b\u9762\u5408\u6210\u6280\u672f\uff0c\u8fd8\u6709\u8de8\u5b66\u79d1\u7684\u6280\u672f\u878d\u5408\u662f\u5fc5\u987b\u8de8\u8fc7\u7684\u574e\uff0c\u5f00\u542f\u901a\u7528\u4eba\u5de5\u667a\u80fd\u5728\u67d0\u4e9b\u5e94\u7528\u573a\u666f\u7684\u5c1d\u8bd5\uff0cSora\u4f5c\u4e3a\u80fd\u591f\u7406\u89e3\u548c\u6a21\u62df\u73b0\u5b9e\u4e16\u754c\u7684\u57fa\u7840\u6a21\u578b\u4e0e\u80fd\u529b\uff0c\u6709\u673a\u4f1a\u6210\u4e3a\u901a\u7528\u4eba\u5de5\u667a\u80fd\u53d1\u5c55\u9053\u8def\u4e0a\u7684\u91cd\u8981\u91cc\u7a0b\u7891\u3002<\/p>\n\n\n\n
$\"\"\/$ <\/figure>\n\n\n\n
\u7ffb\u8bd1\uff1a<\/h2>\n\n\n\n
What’s so amazing about Sora? It wants to build a data-driven physics engine that “knows the rules.<\/h3>\n\n\n\n
In the early morning of February 16, 2024 (February 15, United States time), OpenAI released the “Vincenne video” tool Sora, once again shocking the technology circle. Compared with the current average video generation length of only 4 seconds and the video effect of jitter and distortion, Sora can generate 60 seconds of coherent video based on simple prompt words, create vivid character expressions and complex mirrors, and the video has a high degree of fidelity and narrative effect. So that Sora once released caused a high degree of attention including Musk, Zhou Hongyi and other science and technology leaders, even Nvidia Artificial Intelligence Research Institute Jim Fan also said, “Sora is a data-driven physics engine.” CXO UNION-CXO\u8054\u76df\uff08cxounion.cn\uff09<\/mark><\/p>\n\n\n\n
Sora Vincennes video demonstration effect<\/p>\n\n\n\n
Hint: A stylish woman walks down a Tokyo street filled with warm glowing neon lights and animated city signs. She was wearing a black leather jacket, a long red dress, black boots and carrying a black purse. She was wearing dark glasses and red lipstick. She walked confidently and casually. The streets are damp and reflective, creating a mirror-like effect of colorful lights. Many pedestrians are walking around.<\/p>\n\n\n\n
Sora is an epoch-making Vincennes video product<\/h4>\n\n\n\n
In 2023, the multi-modal large model blooms in the application side, Vincennes diagram and Vincennes video tools mushroomed, as a content creator, the author has also paid to open a number of AI video tools, but the operation is more complex, the generation effect is difficult to be satisfied. Therefore, I am also looking forward to the emergence of a really good AI video tool to meet the needs of people with weak video creation skills, but I did not expect the reality to come so fast.<\/p>\n\n\n\n
AI Vincennes video was first mainly based on GAN (Generative Adversarial Network) model and VAE (variational autoencoder) for video generation. However, the video generated by these two frameworks is only suitable for static, single screen, and the resolution is very low, and the application range is narrow. The development of AI Vinson video technology has mainly formed two technical routes: one is based on Transformer model, which is also the most used large model base in text and image generation; The other is a wider application of the “diffusion model” in the field of video, which is also the current mainstream AI video technology route, which has more advantages in semantic understanding and content richness. CXO UNION-CXO\u8054\u76df\uff08cxounion.cn\uff09<\/mark><\/p>\n\n\n\n
According to the technical report published on the official website of OpenAI, Sora uses the Diffusion Transformer model, a model that combines the diffusion model and Transformer architecture. It processes the noisy image input through the Transformer codec. Predict a sharper version of the image at each step, generate the entire video at once or extend the generated video to make it longer, while solving the challenging problem of ensuring that the subject remains unchanged even when temporarily out of view.<\/p>\n\n\n\n
In fact, Alibaba and ByteDance two major industry giants have launched AI video generation tools last year, using the diffusion model technology route, the common point of the two tools is to turn static graphs into dynamic videos. The Animate Anyone, developed by the Alibaba Institute of Intelligent Computing, only requires the user to provide a static character image, plus some actions and postures, to animate it; Bytedance and the National University of Singapore jointly launched Magic Animate, the same static graph generated dynamic video, compared to Ali more than a “social shake” taste.<\/p>\n\n\n\n
According to the actual evaluation of the computer industry, the video effect of Animate Anyone and Magic Animate is not ideal. The former is difficult to generate stable hand motion generation results, resulting in distortion and motion blur, and the generation effect of side and back pictures is worse than that of the front pictures. The latter generation effect has distortion, and there is still a long distance from the actual landing application. If you want to open the market, AI Vinson video applications need to have a certain length of time, excellent picture quality, creative logic and the ability to restore instruction requirements, the computational complexity is significantly increased, and the demand for computing power is also higher.<\/p>\n\n\n\n
From the 48 demo videos published on OpenAI’s official website, Sora seems to have broken through the technical problems existing in AI Vincencene videos, and can generate 60-second videos with long time, good stability and high clarity just according to a simple prompt, which is definitely the current industry leader.<\/p>\n\n\n\n
Sora mastered the “physical rules” of the world in training<\/h4>\n\n\n\n
According to OpenAI’s website technical documentation, they are teaching AI to understand and simulate the physical world in motion, with the goal of training models to help people solve problems that require real-world interaction. Sora is a masterpiece in this vein. Sora has a deep understanding of language, is able to accurately interpret prompts and generate compelling characters that express vivid emotions, can generate complex scenes with multiple characters, specific types of movements, and exact details of themes and backgrounds, understands what the user is asking for in a prompt and how those things exist in the physical world. CXO UNION-CXO\u8054\u76df\uff08cxounion.cn\uff09<\/mark><\/p>\n\n\n\n
“Realistic close-up video of two pirate ships fighting each other while sailing over a cup of coffee,” reads one of the 48 demo videos posted on OpenAI’s website. Let’s take a look at how Sora generates videos based on this prompt word.<\/p>\n\n\n\n
Sora Vincennes video demonstration effect<\/p>\n\n\n\n
Tip: Realistic close-up video of two pirate ships fighting each other as they sail over a cup of coffee.<\/p>\n\n\n\n
First, the Sora emulator instantiates two beautiful 3D assets, namely a decorated pirate ship, where the text-to-3D problem must be solved implicitly in the potential space. Second, keep 3D objects animated as they navigate and avoid each other’s paths. Third, to “understand” the fluid dynamics of coffee, or even the foam that forms around a boat, fluid simulation here is a whole subfield of computer graphics that requires very complex algorithms and equations. Fourth, fidelity, which requires software algorithms, but also need hardware support, NVIDIA GPU ray tracing technology can achieve close to the real world rendering effect. It is worth noting that the simulator also needs to consider the small volume of the cup compared to the ocean, and must use tilt shift photography technology to create a “tiny” feeling.<\/p>\n\n\n\n
It seems simple, but it’s actually quite complicated. While OpenAI did not publish Sora’s technical documentation, it did introduce its basic principle that Sora learns video to understand the dynamics of the real world and uses computer vision technology to simulate those changes to create new visual content. It is through continuous learning and training to understand the “physical laws” of the world. No wonder Jim Fan of Nvidia’s AI Institute says, “Sora is a data-driven physics engine.”<\/p>\n\n\n\n
In November 2023, American AI startup Pika labs also released the first Vincenne video product, Pika 1.0, which only needs to write prompt words in the video editor to produce high-quality videos, or edit and modify video elements. But what is missing in Pika 1.0 compared to Sora is the ability to learn the rules of the world through learning and training.<\/p>\n\n\n\n
Just a few days after the release of Sora, various industry media are also digging deep into the technical details of Sora, summarizing the Sora model in addition to text-to-video generation capabilities, language understanding capabilities, and static image video generation capabilities, the biggest innovation is the realization of complex scene and character generation capabilities, multi-shot generation capabilities, and physical world simulation capabilities. The latter three points are also not available in other AI Vincennes video tools.<\/p>\n\n\n\n
It can be said that the emergence of Sora heralds the arrival of a new era of visual narration, which can transform people’s imagination into vivid dynamic pictures, and transform the magic of words into visual feast. In a future woven by data and algorithms, Sora is, in its own way, redefining how we interact with the digital world. CXO UNION-CXO\u8054\u76df\uff08cxounion.cn\uff09<\/mark><\/p>\n\n\n\n
Sora will become a disruptive force for industry change<\/h4>\n\n\n\n
After the automatic generation of text and pictures, “video generation”, which is known as the most difficult “mountain”, has also been taken down by AI. Market watchers believe that Sora’s emergence will reshape the video industry and accelerate the transformation of social platforms. Applications related to scene visualization, such as simulation, modeling, special effects, advertising, etc., will face subversive changes, the expression of imagination will gain unprecedented space, and narrative paradigms will transcend traditional boundaries.<\/p>\n\n\n\n
Zhou Hongyi, founder of 360 Group, said that the release of Sora is OpenAI using its advantages of large language model, combining LLM and Diffusion training, so that Sora can realize the understanding of the real world and the simulation of the world. He believes that with a strong foundation of large models, based on the understanding of human language, knowledge and models of the world, combined with many other technologies, you can create super tools in various fields, such as biomedical, protein and gene research, and play a role in the study of disciplines including physics, chemistry and mathematics.<\/p>\n\n\n\n
In the view of the new industry network, the development and evolution of any technology has a gradual process. At present, AI Vincencene video technology represented by Sora is not enough to meet the long-term continuity requirements, and there are still defects of misalignment in simulating complex physical phenomena and understanding complex causality. However, with the enhancement of multi-modal large model capabilities and the continuous iteration of AI technology, it will be possible to replace AI Vincene video scenes related to video.<\/p>\n\n\n\n
As far as industry is concerned, the alternative scenarios that can be imagined include product modeling and simulation, factory modeling and simulation, industrial metauniverse, industrial digital twins, and product training and operation and maintenance scenarios, at least AI video technology should be used as an enabling technology, through transplantation or embedding means, to study the possibility of application in specific scenarios. Some experts in the aviation industry have even proposed that AI Vinson video technology can be used in scenarios such as aircraft application environment and functional performance simulation, system sensitivity and effectiveness assessment, and generalized human-machine interface construction and optimization, and a team can be formed to conduct specialized research if necessary. CXO UNION-CXO\u8054\u76df\uff08cxounion.cn\uff09<\/mark><\/p>\n\n\n\n
By scaling up the video generation model, OpenAI says it hopes to build general-purpose simulators capable of simulating the physical world. It is also pointed out that Sora also exists many physical processes that cannot accurately simulate fundamental interactions, such as glass breakage. In some interaction scenarios, the correct object state changes cannot always be produced, such as eating, which is the focus of further research and breakthroughs.<\/p>\n\n\n\n
We believe that in the future development of AI Vinson video, in addition to continuously optimizing natural language processing, visual processing and integrated picture synthesis technology, interdisciplinary technology integration is a barrier that must be crossed, opening the attempt of general artificial intelligence in some application scenarios. Sora, as a basic model and ability to understand and simulate the real world, Has the opportunity to become an important milestone in the development of general artificial intelligence.<\/p>\n\n\n\n
\u7531CXO UNION-CXO\u8054\u76df\uff08cxounion.cn\uff09<\/a>\u8f6c\u8f7d\u800c\u6210\uff0c\u6765\u6e90\u4e8e\u65b0\u5de5\u4e1a\u7f51\uff1b\u7f16\u8f91\/\u7ffb\u8bd1\uff1aCXO UNIONCXO\u8054\u76df\u5c0fU\u3002<\/p>\n\n\n\n
\u5982\u9700\u52a0\u5165 CXO UNION\uff08CXO\u8054\u76df\uff09<\/a>\u9ad8\u7ba1\u793e\u7fa4\uff0c\u8bf7\u8054\u7cfb\u793e\u7fa4\u5c0f\u4f19\u4f34\u54e6~<\/p>\n\n\n\n
$\"\"\/$ <\/figure>\n\n\n\n
\u514d\u8d23\u58f0\u660e: \u672c\u7f51\u7ad9(http:\/\/www.cxounion.cn\/<\/a>)\u5185\u5bb9\u4e3b\u8981\u6765\u81ea\u539f\u521b\u3001\u5408\u4f5c\u5a92\u4f53\u4f9b\u7a3f\u548c\u7b2c\u4e09\u65b9\u6295\u7a3f\uff0c\u51e1\u5728\u672c\u7f51\u7ad9\u51fa\u73b0\u7684\u4fe1\u606f\uff0c\u5747\u4ec5\u4f9b\u53c2\u8003\u3002\u672c\u7f51\u7ad9\u5c06\u5c3d\u529b\u786e\u4fdd\u6240\u63d0\u4f9b\u4fe1\u606f\u7684\u51c6\u786e\u6027\u53ca\u53ef\u9760\u6027\uff0c\u4f46\u4e0d\u4fdd\u8bc1\u6709\u5173\u8d44\u6599\u7684\u51c6\u786e\u6027\u53ca\u53ef\u9760\u6027\uff0c\u8bfb\u8005\u5728\u4f7f\u7528\u524d\u8bf7\u8fdb\u4e00\u6b65\u6838\u5b9e\uff0c\u5e76\u5bf9\u4efb\u4f55\u81ea\u4e3b\u51b3\u5b9a\u7684\u884c\u4e3a\u8d1f\u8d23\u3002\u672c\u7f51\u7ad9\u5bf9\u6709\u5173\u8d44\u6599\u6240\u5f15\u81f4\u7684\u9519\u8bef\u3001\u4e0d\u786e\u6216\u9057\u6f0f\uff0c\u6982\u4e0d\u8d1f\u4efb\u4f55\u6cd5\u5f8b\u8d23\u4efb\u3002<\/p>\n\n\n\n
\u672c\u7f51\u7ad9\u520a\u8f7d\u7684\u6240\u6709\u5185\u5bb9(\u5305\u62ec\u4f46\u4e0d\u4ec5\u9650\u6587\u5b57\u3001\u56fe\u7247\u3001LOGO\u3001\u97f3\u9891\u3001\u89c6\u9891\u3001\u8f6f\u4ef6\u3001\u7a0b\u5e8f\u7b49) \u7248\u6743\u5f52\u539f\u4f5c\u8005\u6240\u6709\u3002\u4efb\u4f55\u5355\u4f4d\u6216\u4e2a\u4eba\u8ba4\u4e3a\u672c\u7f51\u7ad9\u4e2d\u7684\u5185\u5bb9\u53ef\u80fd\u6d89\u5acc\u4fb5\u72af\u5176\u77e5\u8bc6\u4ea7\u6743\u6216\u5b58\u5728\u4e0d\u5b9e\u5185\u5bb9\u65f6\uff0c\u8bf7\u53ca\u65f6\u901a\u77e5\u672c\u7ad9\uff0c\u4e88\u4ee5\u5220\u9664\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"
2024\u5e742\u670816\u65e5\u51cc\u6668\uff08\u7f8e\u56fd\u65f6\u95f42\u670815\u65e5\uff09\uff0cOpenAI\u53d1\u5e03\u4e86\u201c\u6587\u751f\u89c6\u9891\u201d\u7684\u5de5\u5177Sora\uff0c\u518d\u6b21\u9707\u64bc\u79d1\u6280\u5708\u3002<\/p>\n","protected":false},"author":1,"featured_media":15318,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[13,1],"tags":[61],"class_list":["post-15315","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-viewpoint","category-other-news","tag-61"],"_links":{"self":[{"href":"http:\/\/cxounion.cn\/index.php\/wp-json\/wp\/v2\/posts\/15315","targetHints":{"allow":["GET"]}}],"collection":[{"href":"http:\/\/cxounion.cn\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"http:\/\/cxounion.cn\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"http:\/\/cxounion.cn\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"http:\/\/cxounion.cn\/index.php\/wp-json\/wp\/v2\/comments?post=15315"}],"version-history":[{"count":2,"href":"http:\/\/cxounion.cn\/index.php\/wp-json\/wp\/v2\/posts\/15315\/revisions"}],"predecessor-version":[{"id":15323,"href":"http:\/\/cxounion.cn\/index.php\/wp-json\/wp\/v2\/posts\/15315\/revisions\/15323"}],"wp:featuredmedia":[{"embeddable":true,"href":"http:\/\/cxounion.cn\/index.php\/wp-json\/wp\/v2\/media\/15318"}],"wp:attachment":[{"href":"http:\/\/cxounion.cn\/index.php\/wp-json\/wp\/v2\/media?parent=15315"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/cxounion.cn\/index.php\/wp-json\/wp\/v2\/categories?post=15315"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/cxounion.cn\/index.php\/wp-json\/wp\/v2\/tags?post=15315"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}

\u7ffb\u8bd1\uff1a<\/h2>\n\n\n\n