\u4e09\u79d2\u949f\u770b\u61c2\uff1a\u5f00\u6e90\u3001\u672c\u5730\u90e8\u7f72\u3001\u793e\u533a\u9a71\u52a8\uff0cStable Diffusion \u8ba9\u6bcf\u4e2a\u4eba\u90fd\u80fd\u62e5\u6709\u79c1\u4eba\u5b9a\u5236\u7684 AI \u7ed8\u753b\u5de5\u5382\uff0c\u662f\u6280\u672f\u6781\u5ba2\u548c\u521b\u610f\u73a9\u5bb6\u7684\u7ec8\u6781\u753b\u677f\u3002<\/p>\n
\u6df1\u5ea6\u8bc4\u6d4b\u6b63\u6587<\/p>\n
\u5982\u679c Midjourney \u662f iPhone\uff0c\u90a3 Stable Diffusion \u5c31\u662f Android\u2014\u2014\u4e00\u4e2a\u5f00\u653e\u3001\u53ef\u5b9a\u5236\u3001\u9700\u8981\u4e00\u70b9\u52a8\u624b\u80fd\u529b\uff0c\u4f46\u4e0a\u9650\u6781\u9ad8\u7684\u5e73\u53f0\u3002\u4f5c\u4e3a AI \u5bfc\u822a\u7ad9\u7684\u9996\u5e2d\u5de5\u5177\u5206\u6790\u5e08\uff0c\u6211\u5fc5\u987b\u8bf4\uff0cStable Diffusion \u4e0d\u662f\u7ed9\u6240\u6709\u4eba\u7528\u7684\uff0c\u4f46\u5982\u679c\u4f60\u613f\u610f\u82b1\u65f6\u95f4\u6298\u817e\uff0c\u5b83\u80fd\u7ed9\u4f60\u5e26\u6765 Midjourney \u6c38\u8fdc\u65e0\u6cd5\u63d0\u4f9b\u7684\u521b\u4f5c\u81ea\u7531\u3002<\/p>\n
\u6838\u5fc3\u529f\u80fd\u4e0e\u6280\u672f\u4eae\u70b9<\/p>\n
Stable Diffusion \u7684\u6838\u5fc3\u662f\u4e00\u4e2a\u5f00\u6e90\u7684\u6f5c\u5728\u6269\u6563\u6a21\u578b\uff08Latent Diffusion Model\uff09\uff0c\u7531 Stability AI \u4e3b\u5bfc\u5f00\u53d1\u3002\u5b83\u7684\u6280\u672f\u5e95\u5ea7\u51b3\u5b9a\u4e86\u5b83\u7684\u4e24\u5927\u4f18\u52bf\uff1a\u53ef\u63a7\u6027\u548c\u53ef\u6269\u5c55\u6027\u3002<\/p>\n
\u9996\u5148\uff0c\u672c\u5730\u90e8\u7f72\u3002\u8fd9\u610f\u5473\u7740\u4f60\u7684\u6240\u6709\u6570\u636e\u90fd\u5728\u81ea\u5df1\u7535\u8111\u4e0a\uff0c\u6ca1\u6709\u4efb\u4f55\u9690\u79c1\u6cc4\u9732\u98ce\u9669\uff0c\u66f4\u4e0d\u4f1a\u53d7\u5230\u4e91\u7aef\u5ba1\u6838\u7684\u201c\u9609\u5272\u201d\u3002\u4e00\u5f20 8GB \u663e\u5b58\u7684 RTX 3070 \u663e\u5361\uff0c\u5c31\u80fd\u7528 512×512 \u5206\u8fa8\u7387\u6d41\u7545\u8dd1\u56fe\uff0c\u751f\u6210\u4e00\u5f20\u56fe\u5927\u6982\u5728 5-10 \u79d2\u3002\u5982\u679c\u4f60\u6709 12GB \u4ee5\u4e0a\u663e\u5b58\uff0c\u751a\u81f3\u53ef\u4ee5\u4e0a 1024×1024 \u7684\u9ad8\u6e05\u56fe\u6216\u8005\u8bad\u7ec3\u81ea\u5df1\u7684 LoRA \u6a21\u578b\u3002<\/p>\n
\u5176\u6b21\uff0c\u793e\u533a\u6a21\u578b\u5e93 Civitai \u662f\u5b83\u7684\u7075\u9b42\u3002\u622a\u81f3\u76ee\u524d\uff0cCivitai \u4e0a\u5df2\u7ecf\u6709\u8d85\u8fc7 200 \u4e07\u4e2a\u6a21\u578b\uff0c\u6db5\u76d6\u5199\u5b9e\u3001\u4e8c\u6b21\u5143\u30013D\u3001\u50cf\u7d20\u98ce\u3001\u6c34\u58a8\u98ce\u7b49\u4efb\u4f55\u4f60\u80fd\u60f3\u5230\u7684\u98ce\u683c\u3002\u6bcf\u4e2a\u6a21\u578b\u80cc\u540e\u90fd\u6709\u8be6\u7ec6\u7684\u53c2\u6570\u548c\u793a\u4f8b\u56fe\uff0c\u4f60\u53ef\u4ee5\u76f4\u63a5\u4e0b\u8f7d\u4f7f\u7528\u3002\u6bd4\u5982\u6700\u8fd1\u5927\u706b\u7684\u201cRealistic Vision V5.1\u201d\u6a21\u578b\uff0c\u751f\u6210\u7684\u5199\u5b9e\u4eba\u50cf\u51e0\u4e4e\u53ef\u4ee5\u4ee5\u5047\u4e71\u771f\uff0c\u76ae\u80a4\u7eb9\u7406\u548c\u5149\u5f71\u7ec6\u8282\u6bd4 Midjourney V6 \u8fd8\u8981\u81ea\u7136\u3002<\/p>\n
\u6280\u672f\u53c2\u6570\u4e0a\uff0cStable Diffusion \u652f\u6301 ControlNet\u3001LoRA\u3001Textual Inversion \u7b49\u9ad8\u7ea7\u6280\u672f\u3002ControlNet \u5141\u8bb8\u4f60\u901a\u8fc7\u7ebf\u7a3f\u3001\u6df1\u5ea6\u56fe\u3001\u59ff\u6001\u9aa8\u9abc\u56fe\u6765\u7cbe\u786e\u63a7\u5236\u56fe\u50cf\u751f\u6210\uff0c\u6bd4\u5982\u201c\u8ba9\u8fd9\u4e2a\u89d2\u8272\u6446\u51fa\u540c\u6837\u7684\u59ff\u52bf\uff0c\u4f46\u6362\u4e2a\u80cc\u666f\u548c\u8863\u670d\u201d\u3002LoRA \u5219\u8ba9\u4f60\u7528 10-20 \u5f20\u56fe\u7247\u8bad\u7ec3\u4e00\u4e2a\u4e13\u5c5e\u98ce\u683c\u6216\u89d2\u8272\uff0c\u8bad\u7ec3\u65f6\u95f4\u53ea\u8981 30 \u5206\u949f\u3002<\/p>\n
\u5178\u578b\u4f7f\u7528\u573a\u666f<\/p>\n
1. \u6e38\u620f\u89d2\u8272\u6982\u5ff5\u8bbe\u8ba1\uff1a\u72ec\u7acb\u6e38\u620f\u5f00\u53d1\u8005\u5c0f\u5f20\uff0c\u9700\u8981\u4e3a\u4e00\u4e2a\u4e2d\u4e16\u7eaa\u5947\u5e7b\u6e38\u620f\u8bbe\u8ba1 100 \u4e2a NPC \u89d2\u8272\u3002\u4ed6\u5148\u7528 ControlNet \u7684 OpenPose \u63d2\u4ef6\u56fa\u5b9a\u89d2\u8272\u59ff\u6001\uff0c\u518d\u7ed3\u5408\u4e0d\u540c\u7684 LoRA \u6a21\u578b\u751f\u6210\u670d\u88c5\u548c\u9762\u90e8\u7279\u5f81\u3002\u6574\u4e2a\u8fc7\u7a0b\u53ea\u7528\u4e86 3 \u5929\uff0c\u800c\u5916\u5305\u7ed9\u753b\u5e08\u81f3\u5c11\u8981 2 \u5468\uff0c\u6210\u672c\u66f4\u662f\u5929\u58e4\u4e4b\u522b\u3002<\/p>\n
2. \u7535\u5546\u4ea7\u54c1\u56fe\u6279\u91cf\u751f\u6210\uff1a\u4e00\u5bb6\u5356\u624b\u5de5\u9999\u85b0\u8721\u70db\u7684\u5c0f\u5e97\uff0c\u5e97\u4e3b\u7528 Stable Diffusion \u7684 Inpainting \u529f\u80fd\uff0c\u628a\u4ea7\u54c1\u56fe\u653e\u5230\u4e0d\u540c\u7684\u80cc\u666f\u4e2d\u2014\u2014\u5317\u6b27\u98ce\u5ba2\u5385\u3001\u65e5\u5f0f\u8336\u5ba4\u3001\u68ee\u7cfb\u82b1\u56ed\u3002\u53ea\u9700\u8981\u4e00\u5f20\u539f\u56fe\uff0c\u5c31\u80fd\u751f\u6210 50 \u5f20\u4e0d\u540c\u573a\u666f\u7684\u5c55\u793a\u56fe\uff0c\u800c\u4e14\u5b8c\u5168\u514d\u8d39\u3002\u76f8\u6bd4\u4e4b\u4e0b\uff0cMidjourney \u7684 Vary Region \u529f\u80fd\u867d\u7136\u4e5f\u80fd\u505a\uff0c\u4f46\u4e00\u6b21\u53ea\u80fd\u6539\u4e00\u5c0f\u5757\u533a\u57df\uff0c\u800c\u4e14\u9700\u8981\u4ed8\u8d39\u3002<\/p>\n
3. AI \u7ed8\u753b\u6559\u5b66\u4e0e\u5b9e\u9a8c\uff1a\u67d0\u5927\u5b66\u7684\u6570\u5b57\u5a92\u4f53\u827a\u672f\u8bfe\u7a0b\uff0c\u6559\u6388\u8ba9\u5b66\u751f\u7528 Stable Diffusion \u7684 WebUI \u754c\u9762\uff0c\u8c03\u6574\u4e0d\u540c\u7684\u91c7\u6837\u5668\uff08\u5982 DPM++ 2M Karras vs Euler a\uff09\u548c CFG Scale\uff0c\u89c2\u5bdf\u53c2\u6570\u53d8\u5316\u5bf9\u56fe\u50cf\u7684\u5f71\u54cd\u3002\u8fd9\u79cd\u201c\u6253\u5f00\u9ed1\u76d2\u201d\u7684\u5b66\u4e60\u4f53\u9a8c\uff0c\u662f\u4efb\u4f55\u95ed\u6e90\u5de5\u5177\u65e0\u6cd5\u63d0\u4f9b\u7684\u3002<\/p>\n
\u4e0e\u540c\u7c7b\u5de5\u5177\u6a2a\u5411\u5bf9\u6bd4<\/p>\n
Stable Diffusion vs Midjourney\uff1a\u8fd9\u662f\u6700\u7ecf\u5178\u7684\u5bf9\u6bd4\u3002Midjourney \u7684\u4f18\u70b9\u662f\u201c\u50bb\u74dc\u5f0f\u201d\u597d\u7528\uff0c\u8f93\u5165\u4e00\u53e5 prompt \u5c31\u80fd\u51fa\u60ca\u8273\u7684\u56fe\uff0c\u793e\u533a\u6c1b\u56f4\u6781\u597d\uff0c\u9002\u5408\u5feb\u901f\u4ea7\u51fa\u793e\u4ea4\u5a92\u4f53\u7d20\u6750\u3002\u4f46\u5b83\u4e5f\u6709\u786c\u4f24\uff1a\u65e0\u6cd5\u672c\u5730\u90e8\u7f72\uff0c\u654f\u611f\u5185\u5bb9\u88ab\u4e25\u683c\u8fc7\u6ee4\uff0c\u4e14\u65e0\u6cd5\u7cbe\u786e\u63a7\u5236\u6784\u56fe\u3002Stable Diffusion \u5219\u5b8c\u5168\u76f8\u53cd\uff0c\u4e0a\u624b\u95e8\u69db\u9ad8\uff0c\u9700\u8981\u914d\u7f6e\u73af\u5883\u3001\u7406\u89e3\u6a21\u578b\u3001\u8c03\u53c2\uff0c\u4f46\u4e00\u65e6\u638c\u63e1\uff0c\u4f60\u80fd\u505a\u5230 Midjourney \u505a\u4e0d\u5230\u7684\u4e8b\u60c5\uff0c\u6bd4\u5982\u201c\u8ba9\u8fd9\u4e2a\u89d2\u8272\u7684\u5de6\u624b\u62ac\u5230 45 \u5ea6\u89d2\uff0c\u80cc\u666f\u865a\u5316\u5230 f\/1.8 \u7684\u6548\u679c\u201d\u3002<\/p>\n
Stable Diffusion vs DALL-E 3\uff1aDALL-E 3 \u7684\u6587\u672c\u7406\u89e3\u80fd\u529b\u662f\u76ee\u524d\u6700\u5f3a\u7684\uff0c\u4f60\u8bf4\u201c\u4e00\u4e2a\u6234\u7740\u5e3d\u5b50\u7684\u732b\u5728\u5403\u62ab\u8428\uff0c\u62ab\u8428\u4e0a\u6709\u51e4\u68a8\u201d\uff0c\u5b83\u80fd 100% \u8fd8\u539f\u3002\u4f46\u5b83\u7684\u53ef\u5b9a\u5236\u6027\u51e0\u4e4e\u4e3a\u96f6\uff0c\u4e0d\u80fd\u8bad\u7ec3\u81ea\u5df1\u7684\u6a21\u578b\uff0c\u4e5f\u4e0d\u80fd\u63a7\u5236\u51fa\u56fe\u98ce\u683c\u3002Stable Diffusion \u7684\u6587\u672c\u7406\u89e3\u80fd\u529b\u7a0d\u5f31\uff0c\u5c24\u5176\u662f\u5728\u590d\u6742\u573a\u666f\u4e0b\u5bb9\u6613\u201c\u8111\u8865\u201d\uff0c\u4f46\u901a\u8fc7 LoRA \u548c ControlNet \u7684\u7ec4\u5408\uff0c\u4f60\u53ef\u4ee5\u5b9e\u73b0\u8fdc\u8d85 DALL-E 3 \u7684\u7cbe\u51c6\u63a7\u5236\u3002<\/p>\n
\u5b9a\u4ef7\u6027\u4ef7\u6bd4\u5206\u6790<\/p>\n
Stable Diffusion \u5b8c\u5168\u514d\u8d39\uff0c\u8fd9\u662f\u5b83\u6700\u5927\u7684\u4f18\u52bf\u3002\u4f60\u53ea\u9700\u8981\u4e00\u53f0\u6709\u72ec\u7acb\u663e\u5361\u7684\u7535\u8111\uff08\u5efa\u8bae\u663e\u5b58 8GB \u4ee5\u4e0a\uff09\uff0c\u6216\u8005\u79df\u7528\u4e91 GPU\uff08\u5982 AutoDL\u3001RunPod\uff09\uff0c\u6bcf\u5c0f\u65f6\u6210\u672c\u5927\u7ea6 1-2 \u5143\u4eba\u6c11\u5e01\u3002\u5bf9\u6bd4 Midjourney \u6bcf\u6708 10 \u7f8e\u5143\uff08\u7ea6 72 \u5143\u4eba\u6c11\u5e01\uff09\u7684\u5165\u95e8\u5957\u9910\uff0c\u5982\u679c\u4f60\u6bcf\u5929\u751f\u6210 50 \u5f20\u56fe\uff0cStable Diffusion \u7684\u6210\u672c\u51e0\u4e4e\u4e3a\u96f6\u3002<\/p>\n
\u4f46\u8981\u6ce8\u610f\uff0c\u514d\u8d39\u662f\u6709\u4ee3\u4ef7\u7684\uff1a\u4f60\u9700\u8981\u81ea\u5df1\u82b1\u65f6\u95f4\u5b66\u4e60\u914d\u7f6e\u3001\u8c03\u8bd5\u3001\u7ef4\u62a4\u3002\u5bf9\u975e\u6280\u672f\u7528\u6237\u6765\u8bf4\uff0c\u8fd9\u4e2a\u65f6\u95f4\u6210\u672c\u53ef\u80fd\u6bd4\u8ba2\u9605\u8d39\u8fd8\u9ad8\u3002<\/p>\n
\u9002\u5408\u4eba\u7fa4\u4e0e\u4e0d\u9002\u5408\u4eba\u7fa4<\/p>\n
\u9002\u5408\u4eba\u7fa4\uff1a\u6280\u672f\u6781\u5ba2\u3001\u6e38\u620f\u5f00\u53d1\u8005\u3001\u72ec\u7acb\u827a\u672f\u5bb6\u3001AI \u7814\u7a76\u8005\u3001\u5bf9\u9690\u79c1\u6709\u9ad8\u8981\u6c42\u7684\u7528\u6237\u3002\u5982\u679c\u4f60\u559c\u6b22\u201c\u6298\u817e\u201d\u4e14\u4eab\u53d7\u638c\u63a7\u611f\uff0cStable Diffusion \u662f\u4f60\u7684\u5929\u5802\u3002<\/p>\n
\u4e0d\u9002\u5408\u4eba\u7fa4\uff1a\u53ea\u60f3\u201c\u4e00\u952e\u51fa\u56fe\u201d\u7684\u666e\u901a\u7528\u6237\u3001\u6ca1\u6709\u72ec\u7acb\u663e\u5361\u7684\u7b14\u8bb0\u672c\u7528\u6237\u3001\u5bf9\u7248\u6743\u548c\u6a21\u578b\u5408\u89c4\u6027\u4e0d\u654f\u611f\u7684\u4f01\u4e1a\u7528\u6237\u3002\u5982\u679c\u4f60\u8fde Python \u73af\u5883\u90fd\u4e0d\u60f3\u88c5\uff0c\u5efa\u8bae\u76f4\u63a5\u8ba2\u9605 Midjourney\u3002<\/p>\n
\u5b58\u8bc1\u4ef7\u503c\u63d0\u793a\uff1a\u5982\u679c\u4f60\u7528 Stable Diffusion \u751f\u6210\u4e86\u6709\u5546\u4e1a\u4ef7\u503c\u7684\u827a\u672f\u4f5c\u54c1\uff0c\u901a\u8fc7 AI\u521b\u4f5c\u793e \u5bf9\u8be5\u5de5\u5177\u751f\u6210\u7684\u4f5c\u54c1\u8fdb\u884c\u7248\u6743\u5b58\u8bc1\uff0c\u53ef\u83b7\u5f97\u5b8c\u6574\u7684\u521b\u4f5c\u8fc7\u7a0b\u8bc1\u660e\u94fe\uff0c\u6709\u6548\u4fdd\u62a4\u6570\u5b57\u8d44\u4ea7\u3002<\/p>\n
PM \u6d4b\u8bc4\u7ed3\u8bba<\/p>\n
\u63a8\u8350\u6307\u6570\uff1a\u2605\u2605\u2605\u2605\u2606<\/p>\n
\u4e00\u53e5\u8bdd\u63a8\u8350\u7406\u7531\uff1a\u5f00\u6e90\u514d\u8d39\uff0c\u4e0a\u9650\u6781\u9ad8\uff0c\u4f46\u9700\u52a8\u624b\u80fd\u529b\u3002<\/p>\n
\u9002\u7528\u573a\u666f\u6807\u7b7e\uff1a\u8bbe\u8ba1\u8f85\u52a9\uff0c\u6e38\u620f\u5f00\u53d1\uff0cAI \u7814\u7a76<\/p>\n
—
\n**\u7248\u6743\u63d0\u793a**\uff1a\u4f7f\u7528\u8be5\u5de5\u5177\u521b\u4f5c\u540e\uff0c\u8bf7\u52a1\u5fc5\u524d\u5f80 [AI\u521b\u4f5c\u793e](https:\/\/www.aichuangzuoshe.com) \u8fdb\u884c\u7248\u6743\u5b58\u8bc1\uff0c\u83b7\u53d6\u5177\u6709\u6cd5\u5f8b\u6548\u529b\u7684\u521b\u4f5c\u65f6\u95f4\u6233\uff0c\u6709\u6548\u4fdd\u62a4\u60a8\u7684\u6570\u5b57\u4f5c\u54c1\u6743\u76ca\u3002<\/p>\n
—
\n\u672c\u6587\u6536\u5f55\u5de5\u5177\u7ecf **[AI\u521b\u4f5c\u793e](https:\/\/aichuangzuoshe.com) \u7248\u6743\u4fdd\u62a4\u534f\u8bae**\u8ba4\u8bc1\u3002\u8be5\u5de5\u5177\u751f\u6210\u7684\u4f5c\u54c1\u5df2\u63a5\u5165 AI \u521b\u4f5c\u793e\u7248\u6743\u4fdd\u62a4\u901a\u9053\uff0c\u4f7f\u7528 AI \u521b\u4f5c\u793e\u53ef\u5bf9\u60a8\u7684\u6570\u5b57\u4f5c\u54c1\u8fdb\u884c\u4e00\u952e\u5b58\u8bc1\uff0c\u4fdd\u62a4\u521b\u4f5c\u6743\u76ca\u3002<\/p>\n
> **\u26a0\ufe0f \u7248\u6743\u63d0\u793a**\uff1a\u672c\u5de5\u5177\u751f\u6210\u7684\u56fe\u50cf\/\u89c6\u9891\/\u97f3\u4e50\u4f5c\u54c1\u6d89\u53ca\u7248\u6743\u5f52\u5c5e\u95ee\u9898\u3002\u5efa\u8bae\u901a\u8fc7 **[AI\u521b\u4f5c\u793e](https:\/\/aichuangzuoshe.com)** \u5bf9\u60a8\u7684 AI \u521b\u4f5c\u8fdb\u884c\u53f8\u6cd5\u5b58\u8bc1\uff0c\u83b7\u53d6\u5177\u6709\u6cd5\u5f8b\u6548\u529b\u7684\u521b\u4f5c\u65f6\u95f4\u6233\u8bc1\u660e\uff0c\u6709\u6548\u5e94\u5bf9\u4fb5\u6743\u7ea0\u7eb7\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"
AI\u7ed8\u753b\uff0c\u5f00\u6e90\uff0c\u672c\u5730\u90e8\u7f72<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_ai_cert_trace_id":"","_ai_cert_hash":"","_ai_cert_time":"","footnotes":""},"categories":[62],"tags":[10,11],"class_list":["post-2498","post","type-post","status-publish","format-standard","hentry","category-ai","tag-ai","tag-11"],"_links":{"self":[{"href":"https:\/\/nav.aichuangzuoshe.com\/index.php\/wp-json\/wp\/v2\/posts\/2498","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/nav.aichuangzuoshe.com\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/nav.aichuangzuoshe.com\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/nav.aichuangzuoshe.com\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/nav.aichuangzuoshe.com\/index.php\/wp-json\/wp\/v2\/comments?post=2498"}],"version-history":[{"count":0,"href":"https:\/\/nav.aichuangzuoshe.com\/index.php\/wp-json\/wp\/v2\/posts\/2498\/revisions"}],"wp:attachment":[{"href":"https:\/\/nav.aichuangzuoshe.com\/index.php\/wp-json\/wp\/v2\/media?parent=2498"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/nav.aichuangzuoshe.com\/index.php\/wp-json\/wp\/v2\/categories?post=2498"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/nav.aichuangzuoshe.com\/index.php\/wp-json\/wp\/v2\/tags?post=2498"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}