diffusers/main/en/training/adapt_a_model.html

<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;Adapt a model to a new task&quot;,&quot;local&quot;:&quot;adapt-a-model-to-a-new-task&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;Configure UNet2DConditionModel parameters&quot;,&quot;local&quot;:&quot;configure-unet2dconditionmodel-parameters&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2}],&quot;depth&quot;:1}">
		<link href="/docs/diffusers/main/en/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload">
		<link rel="modulepreload" href="/docs/diffusers/main/en/_app/immutable/entry/start.21e27d66.js">
		<link rel="modulepreload" href="/docs/diffusers/main/en/_app/immutable/chunks/scheduler.8c3d61f6.js">
		<link rel="modulepreload" href="/docs/diffusers/main/en/_app/immutable/chunks/singletons.1db06f6d.js">
		<link rel="modulepreload" href="/docs/diffusers/main/en/_app/immutable/chunks/index.0997d446.js">
		<link rel="modulepreload" href="/docs/diffusers/main/en/_app/immutable/chunks/paths.085e8bc8.js">
		<link rel="modulepreload" href="/docs/diffusers/main/en/_app/immutable/entry/app.de4fb612.js">
		<link rel="modulepreload" href="/docs/diffusers/main/en/_app/immutable/chunks/index.da70eac4.js">
		<link rel="modulepreload" href="/docs/diffusers/main/en/_app/immutable/nodes/0.f6117ae5.js">
		<link rel="modulepreload" href="/docs/diffusers/main/en/_app/immutable/chunks/each.e59479a4.js">
		<link rel="modulepreload" href="/docs/diffusers/main/en/_app/immutable/nodes/181.cfeb1744.js">
		<link rel="modulepreload" href="/docs/diffusers/main/en/_app/immutable/chunks/CodeBlock.00a903b3.js">
		<link rel="modulepreload" href="/docs/diffusers/main/en/_app/immutable/chunks/EditOnGithub.1e64e623.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;Adapt a model to a new task&quot;,&quot;local&quot;:&quot;adapt-a-model-to-a-new-task&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;Configure UNet2DConditionModel parameters&quot;,&quot;local&quot;:&quot;configure-unet2dconditionmodel-parameters&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2}],&quot;depth&quot;:1}"><!-- HEAD_svelte-u9bgzb_END -->      <p></p>  <h1 class="relative group"><a id="adapt-a-model-to-a-new-task" 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="#adapt-a-model-to-a-new-task"><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>Adapt a model to a new task</span></h1> <p data-svelte-h="svelte-3om45r">Many diffusion systems share the same components, allowing you to adapt a pretrained model for one task to an entirely different task.</p> <p data-svelte-h="svelte-plxekm">This guide will show you how to adapt a pretrained text-to-image model for inpainting by initializing and modifying the architecture of a pretrained <a href="/docs/diffusers/main/en/api/models/unet2d-cond#diffusers.UNet2DConditionModel">UNet2DConditionModel</a>.</p>  <h2 class="relative group"><a id="configure-unet2dconditionmodel-parameters" 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="#configure-unet2dconditionmodel-parameters"><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>Configure UNet2DConditionModel parameters</span></h2> <p data-svelte-h="svelte-17kub3x">A <a href="/docs/diffusers/main/en/api/models/unet2d-cond#diffusers.UNet2DConditionModel">UNet2DConditionModel</a> by default accepts 4 channels in the <a href="https://huggingface.co/docs/diffusers/v0.16.0/en/api/models#diffusers.UNet2DConditionModel.in_channels" rel="nofollow">input sample</a>. For example, load a pretrained text-to-image model like <a href="https://huggingface.co/runwayml/stable-diffusion-v1-5" rel="nofollow"><code>runwayml/stable-diffusion-v1-5</code></a> and take a look at the number of <code>in_channels</code>:</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;runwayml/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-ph2jy1">Inpainting requires 9 channels in the input sample. You can check this value in a pretrained inpainting model like <a href="https://huggingface.co/runwayml/stable-diffusion-inpainting" rel="nofollow"><code>runwayml/stable-diffusion-inpainting</code></a>:</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;runwayml/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-1p1x44t">To adapt your text-to-image model for inpainting, you’ll need to change the number of <code>in_channels</code> from 4 to 9.</p> <p data-svelte-h="svelte-1k8u2s">Initialize a <a href="/docs/diffusers/main/en/api/models/unet2d-cond#diffusers.UNet2DConditionModel">UNet2DConditionModel</a> with the pretrained text-to-image model weights, and change <code>in_channels</code> to 9. Changing the number of <code>in_channels</code> means you need to set <code>ignore_mismatched_sizes=True</code> and <code>low_cpu_mem_usage=False</code> to avoid a size mismatch error because the shape is different now.</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> UNet2DConditionModel

model_id = <span class="hljs-string">&quot;runwayml/stable-diffusion-v1-5&quot;</span>
unet = UNet2DConditionModel.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-6j6lxu">The pretrained weights of the other components from the text-to-image model are initialized from their checkpoints, but the input channel weights (<code>conv_in.weight</code>) of the <code>unet</code> are randomly initialized. It is important to finetune the model for inpainting because otherwise the model returns noise.</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/en/training/adapt_a_model.md" target="_blank"><span data-svelte-h="svelte-1kd6by1">&lt;</span> <span data-svelte-h="svelte-x0xyl0">&gt;</span> <span data-svelte-h="svelte-1dajgef"><span class="underline ml-1.5">Update</span> on GitHub</span></a>  <p></p> 
			
			<script>
				{
					__sveltekit_1eu7tzz = {
						assets: "/docs/diffusers/main/en",
						base: "/docs/diffusers/main/en",
						env: {}
					};

					const element = document.currentScript.parentElement;

					const data = [null,null];

					Promise.all([
						import("/docs/diffusers/main/en/_app/immutable/entry/start.21e27d66.js"),
						import("/docs/diffusers/main/en/_app/immutable/entry/app.de4fb612.js")
					]).then(([kit, app]) => {
						kit.start(app, element, {
							node_ids: [0, 181],
							data,
							form: null,
							error: null
						});
					});
				}
			</script>