{"id":16081,"date":"2023-10-19T18:45:52","date_gmt":"2023-10-19T10:45:52","guid":{"rendered":"https:\/\/mnya.tw\/cc\/?p=16081"},"modified":"2023-10-20T22:01:45","modified_gmt":"2023-10-20T14:01:45","slug":"2117","status":"publish","type":"post","link":"https:\/\/mnya.tw\/cc\/word\/2117.html","title":{"rendered":"SD web UI x TensorRT\uff1a\u5229\u7528 NVIDIA RTX GPU \u4e2d\u7684 Tensor Cores \u63d0\u5347\u96d9\u500d AI \u751f\u6210\u6548\u80fd"},"content":{"rendered":"<p>SD web UI \u5168\u7a31 Stable Diffusion web UI\uff0c\u662f\u672c\u6b21\u8981\u642d\u914d Stable-Diffusion-WebUI-TensorRT \u64f4\u5145\u529f\u80fd\u7684 AI \u7e6a\u5716\u5de5\u5177\u3002\u9019\u6b3e\u662f NVIDIA \u5b98\u65b9\u63a8\u51fa\u7684 SD web UI \u64f4\u5145\u529f\u80fd\uff0c\u53ef\u7ffb\u500d\u5229\u7528 NVIDIA RTX GPU \u4e2d\u7684 Tensor Cores \u4e26\u5927\u91cf\u63d0\u5347 Stable Diffusion \u7684\u6548\u80fd\u3002\u6b64 TensorRT \u64f4\u5145\u5957\u4ef6\u652f\u63f4\u6587\u672c\u8f49\u5716\u50cf\u548c\u5716\u50cf\u8f49\u5716\u50cf\u3001Stable Diffusion 1.5 \u548c 2.1 \u53ca LoRA\uff0cSDXL \u7684\u652f\u63f4\u5c07\u5728\u672a\u4f86\u7684\u66f4\u65b0\u4e2d\u52a0\u5165\uff0c\u6700\u4f4e\u7cfb\u7d71\u9700\u6c42\u5982\u4e0b\uff1a<\/p>\n<blockquote><p>GPU\uff1a\u642d\u8f09 8GB VRAM \u7684 NVIDIA RTX GPU<br \/>\nRAM\uff1a16GB RAM<br \/>\n\u7db2\u8def\u9023\u7dda\uff1a\u5b89\u88dd\u671f\u9593\u9700\u8981\u7db2\u8def\u9023\u7dda<br \/>\nNVIDIA \u9a45\u52d5\u7a0b\u5f0f\uff1aNVIDIA Studio Driver 537.58\u3001Game Ready Driver 537.58\u3001NVIDIA RTX Enterprise Driver 537.58 \u53ca\u4ee5\u4e0a\u7248\u672c<\/p><\/blockquote>\n<p>\u4e00\u958b\u59cb\u8acb\u5148\u5b89\u88dd\u597d SD web UI\uff0c\u4e4b\u5f8c\u9023 TensorRT \u64f4\u5145\u529f\u80fd\u90fd\u5b89\u88dd\u597d\u5f8c\uff0c\u53ea\u8981\u70ba\u6240\u9700\u89e3\u6790\u5ea6\u751f\u6210 TensorRT \u5f15\u64ce\uff0c\u4e4b\u5f8c\u5c31\u80fd\u5728\u76f8\u5c0d\u61c9\u7684\u53c3\u6578\u4e0b\u61c9\u7528\u8a72\u5f15\u64ce\uff0c\u4ee5\u6700\u9ad8\u6548\u7387\u9032\u884c AI \u751f\u6210\u5716\u50cf\u3002\u60a8\u53ef\u4ee5\u751f\u6210\u591a\u500b\u5f15\u64ce\uff0c\u4ee5\u4f9b\u9700\u8981\u6642\u4f7f\u7528\u3002\u64f4\u5145\u5957\u4ef6\u5c07\u81ea\u52d5\u4f7f\u7528\u53ef\u7528\u7684\u6700\u4f73\u5f15\u64ce\uff0c\u56e0\u6b64\u60a8\u53ef\u4ee5\u751f\u6210\u591a\u500b\u5f15\u64ce\uff0c\u8981\u6ce8\u610f\u6bcf\u500b\u5f15\u64ce\u5927\u5c0f\u7d04\u70ba 2 GB\u3002\u5f15\u64ce\u6709\u5206\u975c\u614b\u548c\u52d5\u614b\u3002\u975c\u614b\u5f15\u64ce\u63d0\u4f9b\u66f4\u597d\u7684\u6027\u80fd\uff0c\u4f46\u53ea\u9069\u7528\u65bc\u5176\u512a\u5316\u7684\u7cbe\u78ba\u53c3\u6578\u8a2d\u5b9a\u3002\u52d5\u614b\u5f15\u64ce\u6703\u6d88\u8017\u66f4\u591a VRAM\u3002\u751f\u6210\u5f15\u64ce\u6642\uff0c\u53ef\u4ee5\u900f\u904e\u9078\u64c7\u300c\u6700\u5c0f\u6bcf\u6279\u6578\u91cf\u300d\u3001\u300c\u6700\u4f73\u6bcf\u6279\u6578\u91cf\u300d\u3001\u300c\u6700\u5927\u6bcf\u6279\u6578\u91cf\u300d\u3001\u300c\u6700\u5c0f\u9ad8\u5ea6\u300d\u3001\u300c\u6700\u4f73\u9ad8\u5ea6\u300d\u3001\u300c\u6700\u5927\u9ad8\u5ea6\u300d\u3001\u300c\u6700\u5c0f\u5bec\u5ea6\u300d\u3001\u300c\u6700\u4f73\u5bec\u5ea6\u300d\u3001\u300c\u6700\u5927\u5bec\u5ea6\u300d\u3001\u300c\u6700\u5c0f\u63d0\u8a5e\u6578\u91cf\u300d\u3001\u300c\u6700\u4f73\u63d0\u8a5e\u6578\u91cf\u300d\u3001\u300c\u6700\u5927\u63d0\u8a5e\u6578\u91cf\u300d\u7684\u8a2d\u5b9a\u9078\u9805\u4f86\u5efa\u7acb\u6700\u7b26\u5408\u9700\u6c42\u7684\u65b0\u5f15\u64ce\u3002\u8a73\u7d30\u8cc7\u8a0a\u53ca\u6548\u80fd\u6578\u64da\u53ef\u4ee5\u53c3\u8003<a href=\"https:\/\/nvidia.custhelp.com\/app\/answers\/detail\/a_id\/5487\/~\/tensorrt-extension-for-stable-diffusion-web-ui\" target=\"_blank\" rel=\"noopener\">\u5b98\u65b9\u91cb\u51fa\u7684\u6587\u4ef6<\/a>\u3002<\/p>\n<p>\ud83d\udd17 Stable-Diffusion-WebUI-TensorRT\uff1a<a href=\"https:\/\/github.com\/NVIDIA\/Stable-Diffusion-WebUI-TensorRT\" target=\"_blank\" rel=\"noopener\">https:\/\/github.com\/NVIDIA\/Stable-Diffusion-WebUI-TensorRT<\/a><\/p>\n<p><img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/mnya.tw\/cc\/wp-content\/uploads\/2023\/2117-1.jpg\" width=\"1024\" height=\"768\" \/><br \/>\n\u25b2 \u6253\u958b Stable Diffusion web UI \u5207\u5230\u300c\u64f4\u5145\u529f\u80fd\u300d\u9801\u9762\uff0c\u9078\u300c\u5f9e\u7db2\u5740\u5b89\u88dd\u300d\uff0c\u5c07\u64f4\u5145\u529f\u80fd\u5b8c\u6574\u7684 git \u7db2\u5740\uff08\u5373 https:\/\/github.com\/NVIDIA\/Stable-Diffusion-WebUI-TensorRT.git \uff09\u8f38\u5165\u9032\u53bb\u518d\u9ede\u300c\u5b89\u88dd\u300d\u6309\u9215\uff0c\u5b89\u88dd\u5b8c\u7562\u53ef\u4ee5\u5728 stable-diffusion-webui\\extensions\\ \u8def\u5f91\u4e0b\u770b\u5230\u540d\u70ba Stable-Diffusion-WebUI-TensorRT \u7684\u8cc7\u6599\u593e\u3002<br \/>\n<img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/mnya.tw\/cc\/wp-content\/uploads\/2023\/2117-2.jpg\" width=\"1024\" height=\"768\" \/><br \/>\n\u25b2 \u5207\u5230\u300c\u5df2\u5b89\u88dd\u300d\uff0c\u53ef\u4ee5\u770b\u5230\u300cStable-Diffusion-WebUI-TensorRT\u300d\u5df2\u7d93\u5b89\u88dd\uff0c\u672a\u4f86\u53ef\u4ee5\u5728\u6b64\u6aa2\u67e5\u66f4\u65b0\u3002\u9ede\u300c\u66f4\u65b0\u4e26\u91cd\u65b0\u555f\u52d5\u4f7f\u7528\u8005\u4ecb\u9762\u300d\uff0c\u9019\u6a23\u5c31\u6210\u529f\u555f\u7528\u8a72\u64f4\u5145\u529f\u80fd\u56c9\uff01\uff08\u82e5\u6709\u9047\u4e0a\u4efb\u4f55\u5176\u4ed6\u554f\u984c\uff0c\u8acb\u76f4\u63a5\u91cd\u65b0\u555f\u52d5 SD web UI \u8edf\u9ad4\u7d42\u7aef\u8996\u7a97\uff09<br \/>\n<img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/mnya.tw\/cc\/wp-content\/uploads\/2023\/2117-3.jpg\" width=\"1024\" height=\"768\" \/><br \/>\n\u25b2 \u5b89\u88dd\u6210\u529f\u5f8c\u6703\u51fa\u73fe\u300cTensorRT\u300d\u7684\u9078\u9805\u5361\uff0c\u5207\u904e\u4f86\u5f8c\u53ef\u4ee5\u76f4\u63a5\u5728\u300cTensorRT Exporter\u300d\u8655\u7528\u300cDefault\u300d\uff08\u9810\u8a2d\uff09\u914d\u7f6e\u751f\u6210\u65b0\u5f15\u64ce\uff0c\u9810\u8a2d\u7684\u5f15\u64ce\u70ba\u52d5\u614b\u5f15\u64ce\uff0c\u5176\u7bc4\u570d\u5305\u62ec\u9ad8\u5ea6\u548c\u5bec\u5ea6\u5f9e 512 \u5230 768\uff0c\u6bcf\u6279\u6578\u91cf\u5f9e 1 \u5230 4\u3002\u751f\u6210\u4e00\u500b\u5f15\u64ce\u5927\u6982\u8981\u4e94\u5206\u9418\u6216\u66f4\u4e45\uff0c\u9019\u53d6\u6c7a\u65bc\u60a8\u7684\u786c\u9ad4\u8a2d\u5099\u3002\u6ce8\u610f\uff01\u751f\u6210\u5f15\u64ce\u524d\u8981\u5148\u9078\u597d\u5e73\u5e38\u5728\u4f7f\u7528\u7684 Stable Diffusion \u6a21\u578b\u6b0a\u91cd\u5b58\u6a94\u9ede\uff08Checkpoint\uff09\u5594\uff01\u64f4\u5145\u6703\u91dd\u5c0d\u8a72\u6a21\u578b\u9032\u884c\u5f15\u64ce\u751f\u6210\u3002<br \/>\n<img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/mnya.tw\/cc\/wp-content\/uploads\/2023\/2117-4.jpg\" width=\"1024\" height=\"768\" \/><br \/>\n\u25b2 \u5f15\u64ce\u6210\u529f\u751f\u6210\u5f8c\u4e0b\u65b9\u300cAvailable TensorRT Engine Profiles\u300d\u53ef\u4ee5\u67e5\u770b\u5404\u5f15\u64ce\u7684\u7d30\u7bc0\uff0c\u9019\u500b\u5c31\u662f\u9810\u8a2d\u5f15\u64ce\u7684\u7d30\u7bc0\u8cc7\u8a0a\u3002<br \/>\n<img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/mnya.tw\/cc\/wp-content\/uploads\/2023\/2117-5.jpg\" width=\"1024\" height=\"768\" \/><br \/>\n\u25b2 \u63a5\u8457\u5230\u300c\u8a2d\u5b9a\u300d\u2192\u300c\u4f7f\u7528\u8005\u4ecb\u9762\u300d\u2192\u300c\u5feb\u6377\u8a2d\u5b9a\u5217\u8868\u300d\uff0c\u5c07\u300csd_unet\u300d\u52a0\u5165\uff0c\u5230\u6700\u4e0a\u65b9\u9ede\u300c\u5957\u7528\u8a2d\u5b9a\u300d\u5f8c\u9ede\u300c\u91cd\u65b0\u8f09\u5165 UI\u300d\u3002<br \/>\n<img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/mnya.tw\/cc\/wp-content\/uploads\/2023\/2117-6.jpg\" width=\"1024\" height=\"768\" \/><br \/>\n\u25b2 \u4e4b\u5f8c\u5c31\u80fd\u5728\u6700\u4e0a\u65b9\u300cSD Unet\u300d\u9078\u64c7\u5c0d\u61c9\u6a21\u578b\u6b0a\u91cd\u5b58\u6a94\u9ede\uff08Checkpoint\uff09\u7684 TRT \u5f15\u64ce\uff0c\u63a5\u8457\u64f4\u5145\u5c31\u6703\u518d\u627e\u6700\u9069\u5408\u76ee\u524d\u53c3\u6578\u7684\u5f15\u64ce\u4f86\u9032\u884c\u751f\u6210\u3002\u82e5\u627e\u4e0d\u5230\u5408\u9069\u7684\uff0c\u5247\u6703\u986f\u793a\u4ee5\u4e0b\u932f\u8aa4\u8a0a\u606f\uff1a<\/p>\n<blockquote><p>ValueError: No valid profile found. Please go to the TensorRT tab and generate an engine with the necessary profile. If using hires.fix, you need an engine for both the base and upscaled resolutions. Otherwise, use the default (torch) U-Net.<\/p><div class=\"3a456c955cc9861673f62d33beb7714e\" data-index=\"2\" style=\"float: none; margin:0px;\">\n<script async src=\"https:\/\/pagead2.googlesyndication.com\/pagead\/js\/adsbygoogle.js?client=ca-pub-2683739050533486\"\r\n     crossorigin=\"anonymous\"><\/script>\r\n<ins class=\"adsbygoogle\"\r\n     style=\"display:block; text-align:center;\"\r\n     data-ad-layout=\"in-article\"\r\n     data-ad-format=\"fluid\"\r\n     data-ad-client=\"ca-pub-2683739050533486\"\r\n     data-ad-slot=\"3270345536\"><\/ins>\r\n<script>\r\n     (adsbygoogle = window.adsbygoogle || []).push({});\r\n<\/script>\n<\/div>\n<\/blockquote>\n<p>\u610f\u601d\u5c31\u662f\u627e\u4e0d\u5230\u6709\u6548\u7684\u5f15\u64ce\u3002\u9700\u8981\u524d\u5f80 TensorRT \u9078\u9805\u5361\u4e26\u751f\u6210\u9700\u8981\u7684\u5f15\u64ce\u3002\u5982\u679c\u4f7f\u7528 hires.fix \u529f\u80fd\uff0c\u60a8\u9700\u8981\u4e00\u500b\u7528\u65bc\u57fa\u672c\u89e3\u6790\u5ea6\u548c\u5347\u7d1a\u89e3\u6790\u5ea6\u7684\u5f15\u64ce\u3002\u5426\u5247\uff0c\u8acb\u4f7f\u7528\u9810\u8a2d (torch) U-Net\uff01<\/p>\n<p>\u5982\u679c\u9700\u8981\u522a\u9664\u5f15\u64ce\uff0c\u7121\u6cd5\u5f9e UI \u4e0a\u9032\u884c\uff0c\u9700\u8981\u624b\u52d5\u81f3 stable-diffusion-webui\\models\\Unet-trt \u8655\u522a\u9664\u6307\u5b9a\u7684 .trt \u6a94\u6848\uff0c\u53e6\u5916\u4e5f\u9700\u8981\u4fee\u6539 model.json \u5167\u76f8\u5c0d\u61c9\u7684\u8cc7\u6599\u3002<\/p>\n<p>\u4ee5\u4e0b\u63d0\u4f9b\u4e00\u500b\u4f7f\u7528 RTX 3070 Laptops GPU \u7684\u751f\u6210\u8f38\u51fa\u5c0d\u7167\uff0c\u8b93\u5927\u5bb6\u770b\u770b\u6548\u80fd\u7684\u4e0d\u540c\uff01\u9019\u908a\u7d71\u4e00\u4f7f\u7528 Anything V5 \u6a21\u578b\uff08\u76f4\u63a5\u6587\u751f\u5716\uff0c\u7121\u4f7f\u7528 LoRA \u6a21\u578b\uff09\uff0c\u53d6\u6a23\u65b9\u5f0f\u70ba DPM++ 2M\uff0c\u5927\u5c0f 512 x 768 px\uff0c\u6709\u7528\u5230 ADetailer\uff0c\u61c9\u7528\u9810\u8a2d\u52d5\u614b\u5f15\u64ce\u4f86\u512a\u5316\u6548\u80fd\u3002<\/p>\n<p><span style=\"color: #003366;\"><strong>\u9810\u8a2d (torch) U-Net \u5f15\u64ce<\/strong><\/span><\/p>\n<p>100%|\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588| 80\/80 [00:15&lt;00:00, 5.29it\/s]<br \/>\nTotal progress: 100%|\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588| 80\/80 [00:14&lt;00:00, 5.31it\/s]<br \/>\n0: 640x448 1 face, 13.2ms<br \/>\nSpeed: 4.9ms preprocess, 13.2ms inference, 4.0ms postprocess per image at shape (1, 3, 640, 448)<br \/>\n100%|\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588| 33\/33 [00:06&lt;00:00, 5.32it\/s]<br \/>\nTotal progress: 100%|\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588| 80\/80 [00:24&lt;00:00, 3.27it\/s]<br \/>\nTotal progress: 100%|\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588| 80\/80 [00:24&lt;00:00, 5.31it\/s]<\/p>\n<p><span style=\"color: #003366;\"><strong>TensorRT \u9810\u8a2d\u52d5\u614b\u5f15\u64ce<\/strong><\/span><\/p>\n<p>Activating unet: [TRT] AnythingV5Ink_v5RE<br \/>\nLoading TensorRT engine: C:\\stable-diffusion-webui\\models\\Unet-trt\\AnythingV5Ink_v5RE_2986849f_cc86_sample=1x4x64x64+2x4x64x64+8x4x96x96-timesteps=1+2+8-encoder_hidden_states=1x77x768+2x77x768+8x154x768.trt<br \/>\n[I] Loading bytes from C:\\stable-diffusion-webui\\models\\Unet-trt\\AnythingV5Ink_v5RE_2986849f_cc86_sample=1x4x64x64+2x4x64x64+8x4x96x96-timesteps=1+2+8-encoder_hidden_states=1x77x768+2x77x768+8x154x768.trt<br \/>\nProfile 0:<br \/>\nsample = [(1, 4, 64, 64), (2, 4, 64, 64), (8, 4, 96, 96)]<br \/>\ntimesteps = [(1,), (2,), (8,)]<br \/>\nencoder_hidden_states = [(1, 77, 768), (2, 77, 768), (8, 154, 768)]<br \/>\nlatent = [(-1945979547), (-1945980577), (-1945989120)]<\/p>\n<p>100%|\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588| 80\/80 [00:09&lt;00:00, 8.80it\/s]<br \/>\nTotal progress: 100%|\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588| 80\/80 [00:08&lt;00:00, 9.01it\/s]<br \/>\n0: 640x448 1 face, 11.5ms<br \/>\nSpeed: 1.5ms preprocess, 11.5ms inference, 2.0ms postprocess per image at shape (1, 3, 640, 448)<br \/>\n100%|\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588| 33\/33 [00:03&lt;00:00, 8.95it\/s]<br \/>\nTotal progress: 100%|\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588| 80\/80 [00:15&lt;00:00, 5.14it\/s]<br \/>\nTotal progress: 100%|\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588| 80\/80 [00:15&lt;00:00, 9.01it\/s]<\/p>\n\n<div style=\"font-size: 0px; height: 0px; line-height: 0px; margin: 0; padding: 0; clear: both;\"><\/div>","protected":false},"excerpt":{"rendered":"<p>SD web UI \u5168\u7a31 Stable Diffusion web UI\uff0c\u662f\u672c\u6b21\u8981\u642d\u914d Stable-Diffusion-WebUI-TensorRT \u64f4\u5145\u529f\u80fd\u7684 AI \u7e6a\u5716\u5de5\u5177\u3002\u9019\u6b3e\u662f N [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":16084,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[16,525,557],"tags":[553],"class_list":["post-16081","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-software-application","category-ai","category-ai-drawing","tag-stable-diffusion-web-ui"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v27.3 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>SD web UI x TensorRT\uff1a\u5229\u7528 NVIDIA RTX GPU \u4e2d\u7684 Tensor Cores \u63d0\u5347\u96d9\u500d AI \u751f\u6210\u6548\u80fd - \u840c\u82bd\u7d9c\u5408\u5929\u5730 - \u840c\u82bd\u7db2\u9801<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/mnya.tw\/cc\/word\/2117.html\" \/>\n<meta property=\"og:locale\" content=\"zh_TW\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"SD web UI x TensorRT\uff1a\u5229\u7528 NVIDIA RTX GPU \u4e2d\u7684 Tensor Cores \u63d0\u5347\u96d9\u500d AI \u751f\u6210\u6548\u80fd - \u840c\u82bd\u7d9c\u5408\u5929\u5730 - \u840c\u82bd\u7db2\u9801\" \/>\n<meta property=\"og:description\" content=\"SD web UI \u5168\u7a31 Stable Diffusion web UI\uff0c\u662f\u672c\u6b21\u8981\u642d\u914d Stable-Diffusion-WebUI-TensorRT \u64f4\u5145\u529f\u80fd\u7684 AI \u7e6a\u5716\u5de5\u5177\u3002\u9019 [&hellip;]\" \/>\n<meta property=\"og:url\" content=\"https:\/\/mnya.tw\/cc\/word\/2117.html\" \/>\n<meta property=\"og:site_name\" content=\"\u840c\u82bd\u7d9c\u5408\u5929\u5730\" \/>\n<meta property=\"article:published_time\" content=\"2023-10-19T10:45:52+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2023-10-20T14:01:45+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/mnya.tw\/cc\/wp-content\/uploads\/2023\/2117-3.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"1024\" \/>\n\t<meta property=\"og:image:height\" content=\"768\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" \/>\n<meta name=\"author\" content=\"\u840c\u82bd\u7ad9\u9577\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:creator\" content=\"@https:\/\/x.com\/qwe987299\" \/>\n<meta name=\"twitter:label1\" content=\"\u4f5c\u8005:\" \/>\n\t<meta name=\"twitter:data1\" content=\"\u840c\u82bd\u7ad9\u9577\" \/>\n\t<meta name=\"twitter:label2\" content=\"\u9810\u4f30\u95b1\u8b80\u6642\u9593\" \/>\n\t<meta name=\"twitter:data2\" content=\"3 \u5206\u9418\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\\\/\\\/mnya.tw\\\/cc\\\/word\\\/2117.html#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/mnya.tw\\\/cc\\\/word\\\/2117.html\"},\"author\":{\"name\":\"\u840c\u82bd\u7ad9\u9577\",\"@id\":\"https:\\\/\\\/mnya.tw\\\/cc\\\/#\\\/schema\\\/person\\\/28e9ae25bc418b8ec216b7aa2c848faa\"},\"headline\":\"SD web UI x TensorRT\uff1a\u5229\u7528 NVIDIA RTX GPU \u4e2d\u7684 Tensor Cores \u63d0\u5347\u96d9\u500d AI \u751f\u6210\u6548\u80fd\",\"datePublished\":\"2023-10-19T10:45:52+00:00\",\"dateModified\":\"2023-10-20T14:01:45+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/mnya.tw\\\/cc\\\/word\\\/2117.html\"},\"wordCount\":328,\"commentCount\":0,\"image\":{\"@id\":\"https:\\\/\\\/mnya.tw\\\/cc\\\/word\\\/2117.html#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/mnya.tw\\\/cc\\\/wp-content\\\/uploads\\\/2023\\\/2117-3.jpg\",\"keywords\":[\"Stable Diffusion web UI\"],\"articleSection\":[\"\u8edf\u9ad4\u61c9\u7528\",\"\u4eba\u5de5\u667a\u6167\",\"AI\u7e6a\u5716\"],\"inLanguage\":\"zh-TW\",\"potentialAction\":[{\"@type\":\"CommentAction\",\"name\":\"Comment\",\"target\":[\"https:\\\/\\\/mnya.tw\\\/cc\\\/word\\\/2117.html#respond\"]}]},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/mnya.tw\\\/cc\\\/word\\\/2117.html\",\"url\":\"https:\\\/\\\/mnya.tw\\\/cc\\\/word\\\/2117.html\",\"name\":\"SD web UI x TensorRT\uff1a\u5229\u7528 NVIDIA RTX GPU \u4e2d\u7684 Tensor Cores \u63d0\u5347\u96d9\u500d AI \u751f\u6210\u6548\u80fd - \u840c\u82bd\u7d9c\u5408\u5929\u5730 - \u840c\u82bd\u7db2\u9801\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/mnya.tw\\\/cc\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/mnya.tw\\\/cc\\\/word\\\/2117.html#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/mnya.tw\\\/cc\\\/word\\\/2117.html#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/mnya.tw\\\/cc\\\/wp-content\\\/uploads\\\/2023\\\/2117-3.jpg\",\"datePublished\":\"2023-10-19T10:45:52+00:00\",\"dateModified\":\"2023-10-20T14:01:45+00:00\",\"author\":{\"@id\":\"https:\\\/\\\/mnya.tw\\\/cc\\\/#\\\/schema\\\/person\\\/28e9ae25bc418b8ec216b7aa2c848faa\"},\"breadcrumb\":{\"@id\":\"https:\\\/\\\/mnya.tw\\\/cc\\\/word\\\/2117.html#breadcrumb\"},\"inLanguage\":\"zh-TW\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/mnya.tw\\\/cc\\\/word\\\/2117.html\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"zh-TW\",\"@id\":\"https:\\\/\\\/mnya.tw\\\/cc\\\/word\\\/2117.html#primaryimage\",\"url\":\"https:\\\/\\\/mnya.tw\\\/cc\\\/wp-content\\\/uploads\\\/2023\\\/2117-3.jpg\",\"contentUrl\":\"https:\\\/\\\/mnya.tw\\\/cc\\\/wp-content\\\/uploads\\\/2023\\\/2117-3.jpg\",\"width\":1024,\"height\":768},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/mnya.tw\\\/cc\\\/word\\\/2117.html#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"\u9996\u9801\",\"item\":\"https:\\\/\\\/mnya.tw\\\/cc\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"SD web UI x TensorRT\uff1a\u5229\u7528 NVIDIA RTX GPU \u4e2d\u7684 Tensor Cores \u63d0\u5347\u96d9\u500d AI \u751f\u6210\u6548\u80fd\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/mnya.tw\\\/cc\\\/#website\",\"url\":\"https:\\\/\\\/mnya.tw\\\/cc\\\/\",\"name\":\"\u840c\u82bd\u7d9c\u5408\u5929\u5730\",\"description\":\"\u751f\u6d3b\u4f11\u9592\u2502\u96fb\u5b50\u8cc7\u8a0a\u2502\u5b78\u8853\u77e5\u8b58\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/mnya.tw\\\/cc\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"zh-TW\"},{\"@type\":\"Person\",\"@id\":\"https:\\\/\\\/mnya.tw\\\/cc\\\/#\\\/schema\\\/person\\\/28e9ae25bc418b8ec216b7aa2c848faa\",\"name\":\"\u840c\u82bd\u7ad9\u9577\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"zh-TW\",\"@id\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/c63875472a671bb4fd1e3a1012e8ef8bb9672b41d7810b61f508a42ad15ef16a?s=96&d=mm&r=g\",\"url\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/c63875472a671bb4fd1e3a1012e8ef8bb9672b41d7810b61f508a42ad15ef16a?s=96&d=mm&r=g\",\"contentUrl\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/c63875472a671bb4fd1e3a1012e8ef8bb9672b41d7810b61f508a42ad15ef16a?s=96&d=mm&r=g\",\"caption\":\"\u840c\u82bd\u7ad9\u9577\"},\"description\":\"\u60a8\u597d\uff0c\u6211\u662f\u840c\u82bd\u7cfb\u5217\u7db2\u7ad9\uff08Mnya Series Website\uff09\u7684\u7ad9\u9577&amp;\u5275\u59cb\u4eba\uff0c\u53ef\u4ee5\u7a31\u547c\u6211\u300c\u840c\u82bd\u7ad9\u9577\u300d\u3002\u6211\u7684\u8208\u8da3\u8207\u5c08\u9577\u6709\u767b\u5c71\u3001\u89c0\u5bdf\u5730\u5f62\u3001\u651d\u5f71\u3001\u65c5\u904a\u3001\u7db2\u9801\u8a2d\u8a08\uff06\u67b6\u8a2d\uff06\u7d93\u71df\u3001\u52d5\u756b\u88fd\u4f5c\u3001\u5716\u7247\u8655\u7406\u3001\u8cc7\u6599\u5f59\u6574\u7b49\u3002\u6709\u4efb\u4f55\u554f\u984c\u6216\u5efa\u8b70\u8acb\u81f3\u840c\u82bd\u8ad6\u58c7\u767c\u8868\u3002\u7db2\u7ad9\u696d\u52d9\u3001\u5546\u696d\u5408\u4f5c\u7684\u806f\u7d61\u65b9\u5f0f\u5728\u300c\u95dc\u65bc\u672c\u7ad9 \u2192 \u5718\u968a\u4ecb\u7d39 \u2192 \u7ad9\u9577\u4ecb\u7d39\u300d\uff0c\u5f88\u9ad8\u8208\u8a8d\u8b58\u60a8\uff01\u8acb\u591a\u6307\u6559\uff01\",\"sameAs\":[\"https:\\\/\\\/mnya.tw\\\/\",\"https:\\\/\\\/x.com\\\/https:\\\/\\\/x.com\\\/qwe987299\"],\"url\":\"https:\\\/\\\/mnya.tw\\\/cc\\\/word\\\/author\\\/qwe987299\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"SD web UI x TensorRT\uff1a\u5229\u7528 NVIDIA RTX GPU \u4e2d\u7684 Tensor Cores \u63d0\u5347\u96d9\u500d AI \u751f\u6210\u6548\u80fd - \u840c\u82bd\u7d9c\u5408\u5929\u5730 - \u840c\u82bd\u7db2\u9801","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/mnya.tw\/cc\/word\/2117.html","og_locale":"zh_TW","og_type":"article","og_title":"SD web UI x TensorRT\uff1a\u5229\u7528 NVIDIA RTX GPU \u4e2d\u7684 Tensor Cores \u63d0\u5347\u96d9\u500d AI \u751f\u6210\u6548\u80fd - \u840c\u82bd\u7d9c\u5408\u5929\u5730 - \u840c\u82bd\u7db2\u9801","og_description":"SD web UI \u5168\u7a31 Stable Diffusion web UI\uff0c\u662f\u672c\u6b21\u8981\u642d\u914d Stable-Diffusion-WebUI-TensorRT \u64f4\u5145\u529f\u80fd\u7684 AI \u7e6a\u5716\u5de5\u5177\u3002\u9019 [&hellip;]","og_url":"https:\/\/mnya.tw\/cc\/word\/2117.html","og_site_name":"\u840c\u82bd\u7d9c\u5408\u5929\u5730","article_published_time":"2023-10-19T10:45:52+00:00","article_modified_time":"2023-10-20T14:01:45+00:00","og_image":[{"width":1024,"height":768,"url":"https:\/\/mnya.tw\/cc\/wp-content\/uploads\/2023\/2117-3.jpg","type":"image\/jpeg"}],"author":"\u840c\u82bd\u7ad9\u9577","twitter_card":"summary_large_image","twitter_creator":"@https:\/\/x.com\/qwe987299","twitter_misc":{"\u4f5c\u8005:":"\u840c\u82bd\u7ad9\u9577","\u9810\u4f30\u95b1\u8b80\u6642\u9593":"3 \u5206\u9418"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/mnya.tw\/cc\/word\/2117.html#article","isPartOf":{"@id":"https:\/\/mnya.tw\/cc\/word\/2117.html"},"author":{"name":"\u840c\u82bd\u7ad9\u9577","@id":"https:\/\/mnya.tw\/cc\/#\/schema\/person\/28e9ae25bc418b8ec216b7aa2c848faa"},"headline":"SD web UI x TensorRT\uff1a\u5229\u7528 NVIDIA RTX GPU \u4e2d\u7684 Tensor Cores \u63d0\u5347\u96d9\u500d AI \u751f\u6210\u6548\u80fd","datePublished":"2023-10-19T10:45:52+00:00","dateModified":"2023-10-20T14:01:45+00:00","mainEntityOfPage":{"@id":"https:\/\/mnya.tw\/cc\/word\/2117.html"},"wordCount":328,"commentCount":0,"image":{"@id":"https:\/\/mnya.tw\/cc\/word\/2117.html#primaryimage"},"thumbnailUrl":"https:\/\/mnya.tw\/cc\/wp-content\/uploads\/2023\/2117-3.jpg","keywords":["Stable Diffusion web UI"],"articleSection":["\u8edf\u9ad4\u61c9\u7528","\u4eba\u5de5\u667a\u6167","AI\u7e6a\u5716"],"inLanguage":"zh-TW","potentialAction":[{"@type":"CommentAction","name":"Comment","target":["https:\/\/mnya.tw\/cc\/word\/2117.html#respond"]}]},{"@type":"WebPage","@id":"https:\/\/mnya.tw\/cc\/word\/2117.html","url":"https:\/\/mnya.tw\/cc\/word\/2117.html","name":"SD web UI x TensorRT\uff1a\u5229\u7528 NVIDIA RTX GPU \u4e2d\u7684 Tensor Cores \u63d0\u5347\u96d9\u500d AI \u751f\u6210\u6548\u80fd - \u840c\u82bd\u7d9c\u5408\u5929\u5730 - \u840c\u82bd\u7db2\u9801","isPartOf":{"@id":"https:\/\/mnya.tw\/cc\/#website"},"primaryImageOfPage":{"@id":"https:\/\/mnya.tw\/cc\/word\/2117.html#primaryimage"},"image":{"@id":"https:\/\/mnya.tw\/cc\/word\/2117.html#primaryimage"},"thumbnailUrl":"https:\/\/mnya.tw\/cc\/wp-content\/uploads\/2023\/2117-3.jpg","datePublished":"2023-10-19T10:45:52+00:00","dateModified":"2023-10-20T14:01:45+00:00","author":{"@id":"https:\/\/mnya.tw\/cc\/#\/schema\/person\/28e9ae25bc418b8ec216b7aa2c848faa"},"breadcrumb":{"@id":"https:\/\/mnya.tw\/cc\/word\/2117.html#breadcrumb"},"inLanguage":"zh-TW","potentialAction":[{"@type":"ReadAction","target":["https:\/\/mnya.tw\/cc\/word\/2117.html"]}]},{"@type":"ImageObject","inLanguage":"zh-TW","@id":"https:\/\/mnya.tw\/cc\/word\/2117.html#primaryimage","url":"https:\/\/mnya.tw\/cc\/wp-content\/uploads\/2023\/2117-3.jpg","contentUrl":"https:\/\/mnya.tw\/cc\/wp-content\/uploads\/2023\/2117-3.jpg","width":1024,"height":768},{"@type":"BreadcrumbList","@id":"https:\/\/mnya.tw\/cc\/word\/2117.html#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"\u9996\u9801","item":"https:\/\/mnya.tw\/cc"},{"@type":"ListItem","position":2,"name":"SD web UI x TensorRT\uff1a\u5229\u7528 NVIDIA RTX GPU \u4e2d\u7684 Tensor Cores \u63d0\u5347\u96d9\u500d AI \u751f\u6210\u6548\u80fd"}]},{"@type":"WebSite","@id":"https:\/\/mnya.tw\/cc\/#website","url":"https:\/\/mnya.tw\/cc\/","name":"\u840c\u82bd\u7d9c\u5408\u5929\u5730","description":"\u751f\u6d3b\u4f11\u9592\u2502\u96fb\u5b50\u8cc7\u8a0a\u2502\u5b78\u8853\u77e5\u8b58","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/mnya.tw\/cc\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"zh-TW"},{"@type":"Person","@id":"https:\/\/mnya.tw\/cc\/#\/schema\/person\/28e9ae25bc418b8ec216b7aa2c848faa","name":"\u840c\u82bd\u7ad9\u9577","image":{"@type":"ImageObject","inLanguage":"zh-TW","@id":"https:\/\/secure.gravatar.com\/avatar\/c63875472a671bb4fd1e3a1012e8ef8bb9672b41d7810b61f508a42ad15ef16a?s=96&d=mm&r=g","url":"https:\/\/secure.gravatar.com\/avatar\/c63875472a671bb4fd1e3a1012e8ef8bb9672b41d7810b61f508a42ad15ef16a?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/c63875472a671bb4fd1e3a1012e8ef8bb9672b41d7810b61f508a42ad15ef16a?s=96&d=mm&r=g","caption":"\u840c\u82bd\u7ad9\u9577"},"description":"\u60a8\u597d\uff0c\u6211\u662f\u840c\u82bd\u7cfb\u5217\u7db2\u7ad9\uff08Mnya Series Website\uff09\u7684\u7ad9\u9577&amp;\u5275\u59cb\u4eba\uff0c\u53ef\u4ee5\u7a31\u547c\u6211\u300c\u840c\u82bd\u7ad9\u9577\u300d\u3002\u6211\u7684\u8208\u8da3\u8207\u5c08\u9577\u6709\u767b\u5c71\u3001\u89c0\u5bdf\u5730\u5f62\u3001\u651d\u5f71\u3001\u65c5\u904a\u3001\u7db2\u9801\u8a2d\u8a08\uff06\u67b6\u8a2d\uff06\u7d93\u71df\u3001\u52d5\u756b\u88fd\u4f5c\u3001\u5716\u7247\u8655\u7406\u3001\u8cc7\u6599\u5f59\u6574\u7b49\u3002\u6709\u4efb\u4f55\u554f\u984c\u6216\u5efa\u8b70\u8acb\u81f3\u840c\u82bd\u8ad6\u58c7\u767c\u8868\u3002\u7db2\u7ad9\u696d\u52d9\u3001\u5546\u696d\u5408\u4f5c\u7684\u806f\u7d61\u65b9\u5f0f\u5728\u300c\u95dc\u65bc\u672c\u7ad9 \u2192 \u5718\u968a\u4ecb\u7d39 \u2192 \u7ad9\u9577\u4ecb\u7d39\u300d\uff0c\u5f88\u9ad8\u8208\u8a8d\u8b58\u60a8\uff01\u8acb\u591a\u6307\u6559\uff01","sameAs":["https:\/\/mnya.tw\/","https:\/\/x.com\/https:\/\/x.com\/qwe987299"],"url":"https:\/\/mnya.tw\/cc\/word\/author\/qwe987299"}]}},"_links":{"self":[{"href":"https:\/\/mnya.tw\/cc\/wp-json\/wp\/v2\/posts\/16081","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/mnya.tw\/cc\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/mnya.tw\/cc\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/mnya.tw\/cc\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/mnya.tw\/cc\/wp-json\/wp\/v2\/comments?post=16081"}],"version-history":[{"count":0,"href":"https:\/\/mnya.tw\/cc\/wp-json\/wp\/v2\/posts\/16081\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/mnya.tw\/cc\/wp-json\/wp\/v2\/media\/16084"}],"wp:attachment":[{"href":"https:\/\/mnya.tw\/cc\/wp-json\/wp\/v2\/media?parent=16081"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/mnya.tw\/cc\/wp-json\/wp\/v2\/categories?post=16081"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/mnya.tw\/cc\/wp-json\/wp\/v2\/tags?post=16081"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}