{
    "componentChunkName": "component---src-templates-note-note-js",
    "path": "/notes/DDIM",
    "result": {"data":{"mdx":{"body":"var _excluded = [\"components\"];\nfunction _extends() { _extends = Object.assign ? Object.assign.bind() : function (target) { for (var i = 1; i < arguments.length; i++) { var source = arguments[i]; for (var key in source) { if (Object.prototype.hasOwnProperty.call(source, key)) { target[key] = source[key]; } } } return target; }; return _extends.apply(this, arguments); }\nfunction _objectWithoutProperties(source, excluded) { if (source == null) return {}; var target = _objectWithoutPropertiesLoose(source, excluded); var key, i; if (Object.getOwnPropertySymbols) { var sourceSymbolKeys = Object.getOwnPropertySymbols(source); for (i = 0; i < sourceSymbolKeys.length; i++) { key = sourceSymbolKeys[i]; if (excluded.indexOf(key) >= 0) continue; if (!Object.prototype.propertyIsEnumerable.call(source, key)) continue; target[key] = source[key]; } } return target; }\nfunction _objectWithoutPropertiesLoose(source, excluded) { if (source == null) return {}; var target = {}; var sourceKeys = Object.keys(source); var key, i; for (i = 0; i < sourceKeys.length; i++) { key = sourceKeys[i]; if (excluded.indexOf(key) >= 0) continue; target[key] = source[key]; } return target; }\n/* @jsxRuntime classic */\n/* @jsx mdx */\n\nvar _frontmatter = {\n  \"aliases\": [\"Denoising Diffusion Implicit Models\"]\n};\nvar layoutProps = {\n  _frontmatter: _frontmatter\n};\nvar MDXLayout = \"wrapper\";\nreturn function MDXContent(_ref) {\n  var components = _ref.components,\n    props = _objectWithoutProperties(_ref, _excluded);\n  return mdx(MDXLayout, _extends({}, layoutProps, props, {\n    components: components,\n    mdxType: \"MDXLayout\"\n  }), mdx(\"p\", null, \"DDIM stands for Denoising Diffusion Implicit Models. It is a type of generative model used in image generation tasks. DDIMs are an extension of Denoising Diffusion Probabilistic Models (DDPMs), which are based on the idea of gradually adding noise to data and then learning to reverse this process to generate new data samples.\"), mdx(\"p\", null, \"The key difference with DDIMs is that they introduce a \", mdx(\"a\", {\n    parentName: \"p\",\n    \"href\": \"/notes/non-Markovian\",\n    \"title\": \"non-Markovian\"\n  }, \"non-Markovian\"), \" \", mdx(\"a\", {\n    parentName: \"p\",\n    \"href\": \"/notes/diffusion-process\",\n    \"title\": \"diffusion process\"\n  }, \"diffusion process\"), \", which allows for a more efficient sampling process. This means that DDIMs can generate high-quality images with fewer steps compared to traditional DDPMs, making them faster and more \", mdx(\"a\", {\n    parentName: \"p\",\n    \"href\": \"/notes/computationally-efficient\",\n    \"title\": \"computationally efficient\"\n  }, \"computationally efficient\"), \" while maintaining or even improving the quality of the generated images.\"));\n}\n;\nMDXContent.isMDXComponent = true;","inboundReferences":[{"id":"4dc023c8-19d0-5294-aba8-6bdb2658b280","slug":"DDPM-versus-DDIM"},{"id":"ad9a93c0-934e-595d-a28f-b855c72a789e","slug":"flow-based-image-models"}]}},"pageContext":{"slug":"DDIM","node":{"childMdx":{"slug":"DDIM"}}}},
    "staticQueryHashes": []}