diffusers/main/en/api/pipelines/ernie_image.html

<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;Ernie-Image&quot;,&quot;local&quot;:&quot;ernie-image&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;ERNIE-Image&quot;,&quot;local&quot;:&quot;ernie-image&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;ERNIE-Image-Turbo&quot;,&quot;local&quot;:&quot;ernie-image-turbo&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;ErnieImagePipeline&quot;,&quot;local&quot;:&quot;ernieimagepipeline&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.41033924.js">
		<link rel="modulepreload" href="/docs/diffusers/main/en/_app/immutable/chunks/scheduler.53228c21.js">
		<link rel="modulepreload" href="/docs/diffusers/main/en/_app/immutable/chunks/singletons.b56a5ba7.js">
		<link rel="modulepreload" href="/docs/diffusers/main/en/_app/immutable/chunks/index.e93d0901.js">
		<link rel="modulepreload" href="/docs/diffusers/main/en/_app/immutable/chunks/paths.ccb7bf69.js">
		<link rel="modulepreload" href="/docs/diffusers/main/en/_app/immutable/entry/app.aa03abd2.js">
		<link rel="modulepreload" href="/docs/diffusers/main/en/_app/immutable/chunks/preload-helper.5c375679.js">
		<link rel="modulepreload" href="/docs/diffusers/main/en/_app/immutable/chunks/index.100fac89.js">
		<link rel="modulepreload" href="/docs/diffusers/main/en/_app/immutable/nodes/0.2bd329ef.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/142.ce68ff8a.js">
		<link rel="modulepreload" href="/docs/diffusers/main/en/_app/immutable/chunks/CopyLLMTxtMenu.37908ba4.js">
		<link rel="modulepreload" href="/docs/diffusers/main/en/_app/immutable/chunks/globals.7f7f1b26.js">
		<link rel="modulepreload" href="/docs/diffusers/main/en/_app/immutable/chunks/IconCopy.38cf8f56.js">
		<link rel="modulepreload" href="/docs/diffusers/main/en/_app/immutable/chunks/MermaidChart.svelte_svelte_type_style_lang.0a9663c0.js">
		<link rel="modulepreload" href="/docs/diffusers/main/en/_app/immutable/chunks/CodeBlock.0adb3827.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;Ernie-Image&quot;,&quot;local&quot;:&quot;ernie-image&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;ERNIE-Image&quot;,&quot;local&quot;:&quot;ernie-image&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;ERNIE-Image-Turbo&quot;,&quot;local&quot;:&quot;ernie-image-turbo&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;ErnieImagePipeline&quot;,&quot;local&quot;:&quot;ernieimagepipeline&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 h-7 max-sm:h-7 px-2 max-sm:px-1.5 text-sm 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 hover:text-gray-800 dark:hover:text-gray-200"><svg class="sm:size-3.5 size-3" 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-7 max-sm:h-7 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 sm:size-3.5 size-3 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="ernie-image" 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="#ernie-image"><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>Ernie-Image</span></h1> <div class="flex flex-wrap space-x-1" data-svelte-h="svelte-si9ct8"><img alt="LoRA" src="https://img.shields.io/badge/LoRA-d8b4fe?style=flat"></div> <p data-svelte-h="svelte-1ctw5l6">[ERNIE-Image] is a powerful and highly efficient image generation model with 8B parameters. Currently there’s only two models to be released:</p> <table data-svelte-h="svelte-ol15kr"><thead><tr><th>Model</th> <th>Hugging Face</th></tr></thead> <tbody><tr><td>ERNIE-Image</td> <td><a href="https://huggingface.co/baidu/ERNIE-Image" rel="nofollow">https://huggingface.co/baidu/ERNIE-Image</a></td></tr> <tr><td>ERNIE-Image-Turbo</td> <td><a href="https://huggingface.co/baidu/ERNIE-Image-Turbo" rel="nofollow">https://huggingface.co/baidu/ERNIE-Image-Turbo</a></td></tr></tbody></table>  <h2 class="relative group"><a id="ernie-image" 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="#ernie-image"><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>ERNIE-Image</span></h2> <p data-svelte-h="svelte-e9r35z">ERNIE-Image is designed with a relatively compact architecture and solid instruction-following capability, emphasizing parameter efficiency. Based on an 8B DiT backbone, it provides performance that is comparable in some scenarios to larger (20B+) models, while maintaining reasonable parameter efficiency. It offers a relatively stable level of performance in instruction understanding and execution, text generation (e.g., English / Chinese / Japanese), and overall stability.</p>  <h2 class="relative group"><a id="ernie-image-turbo" 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="#ernie-image-turbo"><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>ERNIE-Image-Turbo</span></h2> <p data-svelte-h="svelte-1mgkt88">ERNIE-Image-Turbo is a distilled variant of ERNIE-Image, requiring only 8 NFEs (Number of Function Evaluations) and offering a more efficient alternative with relatively comparable performance to the full model in certain cases.</p>  <h2 class="relative group"><a id="ernieimagepipeline" 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="#ernieimagepipeline"><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>ErnieImagePipeline</span></h2> <p data-svelte-h="svelte-etigmt">Use [ErnieImagePipeline] to generate images from text prompts. The pipeline supports Prompt Enhancer (PE) by default, which enhances the user’s raw prompt to improve output quality, though it may reduce instruction-following accuracy.</p> <p data-svelte-h="svelte-8yxakn">We provide a pretrained 3B-parameter PE model; however, using larger language models (e.g., Gemini or ChatGPT) for prompt enhancement may yield better results. The system prompt template is available at: <a href="https://huggingface.co/baidu/ERNIE-Image/blob/main/pe/chat_template.jinja" rel="nofollow">https://huggingface.co/baidu/ERNIE-Image/blob/main/pe/chat_template.jinja</a>.</p> <p data-svelte-h="svelte-1suhr09">If you prefer not to use PE, set use_pe=False.</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="language-python "><!-- HTML_TAG_START --><span class="hljs-keyword">import</span> torch
<span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> ErnieImagePipeline
<span class="hljs-keyword">from</span> diffusers.utils <span class="hljs-keyword">import</span> load_image

pipe = ErnieImagePipeline.from_pretrained(<span class="hljs-string">&quot;baidu/ERNIE-Image&quot;</span>, torch_dtype=torch.bfloat16)
pipe.to(<span class="hljs-string">&quot;cuda&quot;</span>)
<span class="hljs-comment"># If you are running low on GPU VRAM, you can enable offloading</span>
pipe.enable_model_cpu_offload()

prompt = <span class="hljs-string">&quot;一只黑白相间的中华田园犬&quot;</span>
images = pipe(
    prompt=prompt,
    height=<span class="hljs-number">1024</span>,
    width=<span class="hljs-number">1024</span>,
    num_inference_steps=<span class="hljs-number">50</span>,
    guidance_scale=<span class="hljs-number">4.0</span>,
    generator=torch.Generator(<span class="hljs-string">&quot;cuda&quot;</span>).manual_seed(<span class="hljs-number">42</span>),
    use_pe=<span class="hljs-literal">True</span>,
).images
images[<span class="hljs-number">0</span>].save(<span class="hljs-string">&quot;ernie-image-output.png&quot;</span>)<!-- HTML_TAG_END --></pre></div> <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="language-python "><!-- HTML_TAG_START --><span class="hljs-keyword">import</span> torch
<span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> ErnieImagePipeline
<span class="hljs-keyword">from</span> diffusers.utils <span class="hljs-keyword">import</span> load_image

pipe = ErnieImagePipeline.from_pretrained(<span class="hljs-string">&quot;baidu/ERNIE-Image-Turbo&quot;</span>, torch_dtype=torch.bfloat16)
pipe.to(<span class="hljs-string">&quot;cuda&quot;</span>)
<span class="hljs-comment"># If you are running low on GPU VRAM, you can enable offloading</span>
pipe.enable_model_cpu_offload()

prompt = <span class="hljs-string">&quot;一只黑白相间的中华田园犬&quot;</span>
images = pipe(
    prompt=prompt,
    height=<span class="hljs-number">1024</span>,
    width=<span class="hljs-number">1024</span>,
    num_inference_steps=<span class="hljs-number">8</span>,
    guidance_scale=<span class="hljs-number">1.0</span>,
    generator=torch.Generator(<span class="hljs-string">&quot;cuda&quot;</span>).manual_seed(<span class="hljs-number">42</span>),
    use_pe=<span class="hljs-literal">True</span>,
).images
images[<span class="hljs-number">0</span>].save(<span class="hljs-string">&quot;ernie-image-turbo-output.png&quot;</span>)<!-- HTML_TAG_END --></pre></div> <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/api/pipelines/ernie_image.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_etlpjl = {
						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.41033924.js"),
						import("/docs/diffusers/main/en/_app/immutable/entry/app.aa03abd2.js")
					]).then(([kit, app]) => {
						kit.start(app, element, {
							node_ids: [0, 142],
							data,
							form: null,
							error: null
						});
					});
				}
			</script>