diffusers/pr_11739/zh/training/adapt_a_model.html

<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;将模型适配至新任务&quot;,&quot;local&quot;:&quot;将模型适配至新任务&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;配置 UNet2DConditionModel 参数&quot;,&quot;local&quot;:&quot;配置-unet2dconditionmodel-参数&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2}],&quot;depth&quot;:1}">
		<link href="/docs/diffusers/pr_11739/zh/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload">
		<link rel="modulepreload" href="/docs/diffusers/pr_11739/zh/_app/immutable/entry/start.95a8faef.js">
		<link rel="modulepreload" href="/docs/diffusers/pr_11739/zh/_app/immutable/chunks/scheduler.e4ff9b64.js">
		<link rel="modulepreload" href="/docs/diffusers/pr_11739/zh/_app/immutable/chunks/singletons.0a6f1d19.js">
		<link rel="modulepreload" href="/docs/diffusers/pr_11739/zh/_app/immutable/chunks/index.f9be34a7.js">
		<link rel="modulepreload" href="/docs/diffusers/pr_11739/zh/_app/immutable/chunks/paths.37f6e25a.js">
		<link rel="modulepreload" href="/docs/diffusers/pr_11739/zh/_app/immutable/entry/app.a988cdaf.js">
		<link rel="modulepreload" href="/docs/diffusers/pr_11739/zh/_app/immutable/chunks/preload-helper.3e2c3f46.js">
		<link rel="modulepreload" href="/docs/diffusers/pr_11739/zh/_app/immutable/chunks/index.09f1bca0.js">
		<link rel="modulepreload" href="/docs/diffusers/pr_11739/zh/_app/immutable/nodes/0.0ec3fec6.js">
		<link rel="modulepreload" href="/docs/diffusers/pr_11739/zh/_app/immutable/chunks/each.e59479a4.js">
		<link rel="modulepreload" href="/docs/diffusers/pr_11739/zh/_app/immutable/nodes/41.d7409ae4.js">
		<link rel="modulepreload" href="/docs/diffusers/pr_11739/zh/_app/immutable/chunks/MermaidChart.svelte_svelte_type_style_lang.f5199cd9.js">
		<link rel="modulepreload" href="/docs/diffusers/pr_11739/zh/_app/immutable/chunks/CodeBlock.1680a1fd.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;将模型适配至新任务&quot;,&quot;local&quot;:&quot;将模型适配至新任务&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;配置 UNet2DConditionModel 参数&quot;,&quot;local&quot;:&quot;配置-unet2dconditionmodel-参数&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2}],&quot;depth&quot;:1}"><!-- HEAD_svelte-u9bgzb_END -->      <p></p>  <div class="items-center shrink-0 min-w-[100px] max-sm:min-w-[50px] justify-end ml-auto flex" style="float: right; margin-left: 10px; display: inline-flex; position: relative; z-index: 10;"><div class="inline-flex rounded-md max-sm:rounded-sm"><button class="inline-flex items-center gap-1 max-sm:gap-0.5 h-6 max-sm:h-5 px-2 max-sm:px-1.5 text-[11px] max-sm:text-[9px] font-medium text-gray-800 border border-r-0 rounded-l-md max-sm:rounded-l-sm border-gray-200 bg-white hover:shadow-inner dark:border-gray-850 dark:bg-gray-950 dark:text-gray-200 dark:hover:bg-gray-800" aria-live="polite"><span class="inline-flex items-center justify-center rounded-md p-0.5 max-sm:p-0"><svg class="w-3 h-3 max-sm:w-2.5 max-sm:h-2.5" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg></span> <span>Copy page</span></button> <button class="inline-flex items-center justify-center w-6 max-sm:w-5 h-6 max-sm:h-5 disabled:pointer-events-none text-sm text-gray-500 hover:text-gray-700 dark:hover:text-white rounded-r-md max-sm:rounded-r-sm border border-l transition border-gray-200 bg-white hover:shadow-inner dark:border-gray-850 dark:bg-gray-950 dark:text-gray-200 dark:hover:bg-gray-800" aria-haspopup="menu" aria-expanded="false" aria-label="Open copy menu"><svg class="transition-transform text-gray-400 overflow-visible w-3 h-3 max-sm:w-2.5 max-sm:h-2.5 rotate-0" width="1em" height="1em" viewBox="0 0 12 7" fill="none" xmlns="http://www.w3.org/2000/svg"><path d="M1 1L6 6L11 1" stroke="currentColor"></path></svg></button></div> </div>  <h1 class="relative group"><a id="将模型适配至新任务" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#将模型适配至新任务"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>将模型适配至新任务</span></h1> <p data-svelte-h="svelte-10h8vrc">许多扩散系统共享相同的组件架构，这使得您能够将针对某一任务预训练的模型调整适配至完全不同的新任务。</p> <p data-svelte-h="svelte-1g75zm2">本指南将展示如何通过初始化并修改预训练 <code>UNet2DConditionModel</code> 的架构，将文生图预训练模型改造为图像修复(inpainting)模型。</p>  <h2 class="relative group"><a id="配置-unet2dconditionmodel-参数" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#配置-unet2dconditionmodel-参数"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>配置 UNet2DConditionModel 参数</span></h2> <p data-svelte-h="svelte-nklbqh">默认情况下，<code>UNet2DConditionModel</code> 的<a href="https://huggingface.co/docs/diffusers/v0.16.0/en/api/models#diffusers.UNet2DConditionModel.in_channels" rel="nofollow">输入样本</a>接受4个通道。例如加载 <a href="https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5" rel="nofollow"><code>stable-diffusion-v1-5/stable-diffusion-v1-5</code></a> 这样的文生图预训练模型，查看其 <code>in_channels</code> 参数值：</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5   text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> StableDiffusionPipeline

pipeline = StableDiffusionPipeline.from_pretrained(<span class="hljs-string">&quot;stable-diffusion-v1-5/stable-diffusion-v1-5&quot;</span>, use_safetensors=<span class="hljs-literal">True</span>)
pipeline.unet.config[<span class="hljs-string">&quot;in_channels&quot;</span>]
<span class="hljs-number">4</span><!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-cgy9ux">而图像修复任务需要输入样本具有9个通道。您可以在 <a href="https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-inpainting" rel="nofollow"><code>stable-diffusion-v1-5/stable-diffusion-inpainting</code></a> 这样的预训练修复模型中验证此参数：</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5   text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> StableDiffusionPipeline

pipeline = StableDiffusionPipeline.from_pretrained(<span class="hljs-string">&quot;stable-diffusion-v1-5/stable-diffusion-inpainting&quot;</span>, use_safetensors=<span class="hljs-literal">True</span>)
pipeline.unet.config[<span class="hljs-string">&quot;in_channels&quot;</span>]
<span class="hljs-number">9</span><!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-i2n3iv">要将文生图模型改造为修复模型，您需要将 <code>in_channels</code> 参数从4调整为9。</p> <p data-svelte-h="svelte-6bo6ng">初始化一个加载了文生图预训练权重的 <code>UNet2DConditionModel</code>，并将 <code>in_channels</code> 设为9。由于输入通道数变化导致张量形状改变，需要设置 <code>ignore_mismatched_sizes=True</code> 和 <code>low_cpu_mem_usage=False</code> 来避免尺寸不匹配错误。</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5   text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> AutoModel

model_id = <span class="hljs-string">&quot;stable-diffusion-v1-5/stable-diffusion-v1-5&quot;</span>
unet = AutoModel.from_pretrained(
    model_id,
    subfolder=<span class="hljs-string">&quot;unet&quot;</span>,
    in_channels=<span class="hljs-number">9</span>,
    low_cpu_mem_usage=<span class="hljs-literal">False</span>,
    ignore_mismatched_sizes=<span class="hljs-literal">True</span>,
    use_safetensors=<span class="hljs-literal">True</span>,
)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-qygtll">此时文生图模型的其他组件权重仍保持预训练状态，但UNet的输入卷积层权重(<code>conv_in.weight</code>)会随机初始化。由于这一关键变化，必须对模型进行修复任务的微调，否则模型将仅会输出噪声。</p> <a class="!text-gray-400 !no-underline text-sm flex items-center not-prose mt-4" href="https://github.com/huggingface/diffusers/blob/main/docs/source/zh/training/adapt_a_model.md" target="_blank"><svg class="mr-1" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M31,16l-7,7l-1.41-1.41L28.17,16l-5.58-5.59L24,9l7,7z"></path><path d="M1,16l7-7l1.41,1.41L3.83,16l5.58,5.59L8,23l-7-7z"></path><path d="M12.419,25.484L17.639,6.552l1.932,0.518L14.351,26.002z"></path></svg> <span data-svelte-h="svelte-zjs2n5"><span class="underline">Update</span> on GitHub</span></a>  <p></p> 
			
			<script>
				{
					__sveltekit_pa8cr6 = {
						assets: "/docs/diffusers/pr_11739/zh",
						base: "/docs/diffusers/pr_11739/zh",
						env: {}
					};

					const element = document.currentScript.parentElement;

					const data = [null,null];

					Promise.all([
						import("/docs/diffusers/pr_11739/zh/_app/immutable/entry/start.95a8faef.js"),
						import("/docs/diffusers/pr_11739/zh/_app/immutable/entry/app.a988cdaf.js")
					]).then(([kit, app]) => {
						kit.start(app, element, {
							node_ids: [0, 41],
							data,
							form: null,
							error: null
						});
					});
				}
			</script>