diffusers/v0.19.3/en/using-diffusers/control_brightness.html

<meta charset="utf-8" /><meta http-equiv="content-security-policy" content=""><meta name="hf:doc:metadata" content="{&quot;local&quot;:&quot;control-image-brightness&quot;,&quot;title&quot;:&quot;Control image brightness&quot;}" data-svelte="svelte-1phssyn">
	<link rel="modulepreload" href="/docs/diffusers/v0.19.3/en/_app/assets/pages/__layout.svelte-hf-doc-builder.css">
	<link rel="modulepreload" href="/docs/diffusers/v0.19.3/en/_app/start-hf-doc-builder.js">
	<link rel="modulepreload" href="/docs/diffusers/v0.19.3/en/_app/chunks/vendor-hf-doc-builder.js">
	<link rel="modulepreload" href="/docs/diffusers/v0.19.3/en/_app/chunks/paths-hf-doc-builder.js">
	<link rel="modulepreload" href="/docs/diffusers/v0.19.3/en/_app/pages/__layout.svelte-hf-doc-builder.js">
	<link rel="modulepreload" href="/docs/diffusers/v0.19.3/en/_app/pages/using-diffusers/control_brightness.mdx-hf-doc-builder.js">
	<link rel="modulepreload" href="/docs/diffusers/v0.19.3/en/_app/chunks/Tip-hf-doc-builder.js">
	<link rel="modulepreload" href="/docs/diffusers/v0.19.3/en/_app/chunks/IconCopyLink-hf-doc-builder.js">
	<link rel="modulepreload" href="/docs/diffusers/v0.19.3/en/_app/chunks/CodeBlock-hf-doc-builder.js"> 





<h1 class="relative group"><a id="control-image-brightness" 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="#control-image-brightness"><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>Control image brightness
	</span></h1>

<p>The Stable Diffusion pipeline is mediocre at generating images that are either very bright or dark as explained in the <a href="https://huggingface.co/papers/2305.08891" rel="nofollow">Common Diffusion Noise Schedules and Sample Steps are Flawed</a> paper. The solutions proposed in the paper are currently implemented in the <a href="/docs/diffusers/v0.19.3/en/api/schedulers/ddim#diffusers.DDIMScheduler">DDIMScheduler</a> which you can use to improve the lighting in your images.</p>


<div class="course-tip  bg-gradient-to-br dark:bg-gradient-to-r before:border-green-500 dark:before:border-green-800 from-green-50 dark:from-gray-900 to-white dark:to-gray-950 border border-green-50 text-green-700 dark:text-gray-400"><p>💡 Take a look at the paper linked above for more details about the proposed solutions!</p></div>
<p>One of the solutions is to train a model with <em>v prediction</em> and <em>v loss</em>. Add the following flag to the <a href="https://github.com/huggingface/diffusers/blob/main/examples/text_to_image/train_text_to_image.py" rel="nofollow"><code>train_text_to_image.py</code></a> or <a href="https://github.com/huggingface/diffusers/blob/main/examples/text_to_image/train_text_to_image_lora.py" rel="nofollow"><code>train_text_to_image_lora.py</code></a> scripts to enable <code>v_prediction</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><!-- HTML_TAG_START -->--prediction_type=<span class="hljs-string">&quot;v_prediction&quot;</span><!-- HTML_TAG_END --></pre></div>
<p>For example, let’s use the <a href="https://huggingface.co/ptx0/pseudo-journey-v2" rel="nofollow"><code>ptx0/pseudo-journey-v2</code></a> checkpoint which has been finetuned with <code>v_prediction</code>.</p>
<p>Next, configure the following parameters in the <a href="/docs/diffusers/v0.19.3/en/api/schedulers/ddim#diffusers.DDIMScheduler">DDIMScheduler</a>:</p>
<ol><li><code>rescale_betas_zero_snr=True</code>, rescales the noise schedule to zero terminal signal-to-noise ratio (SNR)</li>
<li><code>timestep_spacing=&quot;trailing&quot;</code>, starts sampling from the last timestep</li></ol>

	<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><!-- HTML_TAG_START --><span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> DiffusionPipeline, DDIMScheduler

<span class="hljs-meta">&gt;&gt;&gt; </span>pipeline = DiffusionPipeline.from_pretrained(<span class="hljs-string">&quot;ptx0/pseudo-journey-v2&quot;</span>)
<span class="hljs-comment"># switch the scheduler in the pipeline to use the DDIMScheduler</span>

<span class="hljs-meta">&gt;&gt;&gt; </span>pipeline.scheduler = DDIMScheduler.from_config(
<span class="hljs-meta">... </span>    pipeline.scheduler.config, rescale_betas_zero_snr=<span class="hljs-literal">True</span>, timestep_spacing=<span class="hljs-string">&quot;trailing&quot;</span>
<span class="hljs-meta">... </span>)
<span class="hljs-meta">&gt;&gt;&gt; </span>pipeline.to(<span class="hljs-string">&quot;cuda&quot;</span>)<!-- HTML_TAG_END --></pre></div>
<p>Finally, in your call to the pipeline, set <code>guidance_rescale</code> to prevent overexposure:</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><!-- HTML_TAG_START -->prompt = <span class="hljs-string">&quot;A lion in galaxies, spirals, nebulae, stars, smoke, iridescent, intricate detail, octane render, 8k&quot;</span>
image = pipeline(prompt, guidance_rescale=<span class="hljs-number">0.7</span>).images[<span class="hljs-number">0</span>]<!-- HTML_TAG_END --></pre></div>
<div class="flex justify-center"><img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/zero_snr.png"></div>


		<script type="module" data-hydrate="hffsei">
		import { start } from "/docs/diffusers/v0.19.3/en/_app/start-hf-doc-builder.js";
		start({
			target: document.querySelector('[data-hydrate="hffsei"]').parentNode,
			paths: {"base":"/docs/diffusers/v0.19.3/en","assets":"/docs/diffusers/v0.19.3/en"},
			session: {},
			route: false,
			spa: false,
			trailing_slash: "never",
			hydrate: {
				status: 200,
				error: null,
				nodes: [
					import("/docs/diffusers/v0.19.3/en/_app/pages/__layout.svelte-hf-doc-builder.js"),
						import("/docs/diffusers/v0.19.3/en/_app/pages/using-diffusers/control_brightness.mdx-hf-doc-builder.js")
				],
				params: {}
			}
		});
	</script>