Buckets:
| <meta charset="utf-8" /><meta name="hf:doc:metadata" content="{"title":"Text-to-image","local":"text-to-image","sections":[{"title":"Popular models","local":"popular-models","sections":[{"title":"Stable Diffusion v1.5","local":"stable-diffusion-v15","sections":[],"depth":3},{"title":"Stable Diffusion XL","local":"stable-diffusion-xl","sections":[],"depth":3},{"title":"Kandinsky 2.2","local":"kandinsky-22","sections":[],"depth":3},{"title":"ControlNet","local":"controlnet","sections":[],"depth":3}],"depth":2},{"title":"Configure pipeline parameters","local":"configure-pipeline-parameters","sections":[{"title":"Height and width","local":"height-and-width","sections":[],"depth":3},{"title":"Guidance scale","local":"guidance-scale","sections":[],"depth":3},{"title":"Negative prompt","local":"negative-prompt","sections":[],"depth":3},{"title":"Generator","local":"generator","sections":[],"depth":3}],"depth":2},{"title":"Control image generation","local":"control-image-generation","sections":[{"title":"Prompt weighting","local":"prompt-weighting","sections":[],"depth":3},{"title":"ControlNet","local":"controlnet","sections":[],"depth":3}],"depth":2},{"title":"Optimize","local":"optimize","sections":[],"depth":2}],"depth":1}"> | |
| <link href="/docs/diffusers/pr_12448/en/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_12448/en/_app/immutable/entry/start.77018737.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_12448/en/_app/immutable/chunks/scheduler.53228c21.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_12448/en/_app/immutable/chunks/singletons.5ccd8670.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_12448/en/_app/immutable/chunks/index.e93d0901.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_12448/en/_app/immutable/chunks/paths.e3119367.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_12448/en/_app/immutable/entry/app.30e12370.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_12448/en/_app/immutable/chunks/preload-helper.7a497b25.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_12448/en/_app/immutable/chunks/index.100fac89.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_12448/en/_app/immutable/nodes/0.62116836.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_12448/en/_app/immutable/chunks/each.e59479a4.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_12448/en/_app/immutable/nodes/325.a8aa356e.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_12448/en/_app/immutable/chunks/CopyLLMTxtMenu.88008e00.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_12448/en/_app/immutable/chunks/globals.7f7f1b26.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_12448/en/_app/immutable/chunks/IconCopy.38cf8f56.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_12448/en/_app/immutable/chunks/MermaidChart.svelte_svelte_type_style_lang.afa087fa.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_12448/en/_app/immutable/chunks/CodeBlock.d30a6509.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_12448/en/_app/immutable/chunks/DocNotebookDropdown.74a16910.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{"title":"Text-to-image","local":"text-to-image","sections":[{"title":"Popular models","local":"popular-models","sections":[{"title":"Stable Diffusion v1.5","local":"stable-diffusion-v15","sections":[],"depth":3},{"title":"Stable Diffusion XL","local":"stable-diffusion-xl","sections":[],"depth":3},{"title":"Kandinsky 2.2","local":"kandinsky-22","sections":[],"depth":3},{"title":"ControlNet","local":"controlnet","sections":[],"depth":3}],"depth":2},{"title":"Configure pipeline parameters","local":"configure-pipeline-parameters","sections":[{"title":"Height and width","local":"height-and-width","sections":[],"depth":3},{"title":"Guidance scale","local":"guidance-scale","sections":[],"depth":3},{"title":"Negative prompt","local":"negative-prompt","sections":[],"depth":3},{"title":"Generator","local":"generator","sections":[],"depth":3}],"depth":2},{"title":"Control image generation","local":"control-image-generation","sections":[{"title":"Prompt weighting","local":"prompt-weighting","sections":[],"depth":3},{"title":"ControlNet","local":"controlnet","sections":[],"depth":3}],"depth":2},{"title":"Optimize","local":"optimize","sections":[],"depth":2}],"depth":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> <div class="flex space-x-1 " style="float: right; margin-left: 10px; display: inline-flex; position: relative; z-index: 10;"> <div class="relative colab-dropdown "> <button class=" " type="button"> <img alt="Open In Colab" class="!m-0" src="https://colab.research.google.com/assets/colab-badge.svg"> </button> </div> <div class="relative colab-dropdown "> <button class=" " type="button"> <img alt="Open In Studio Lab" class="!m-0" src="https://studiolab.sagemaker.aws/studiolab.svg"> </button> </div></div> <h1 class="relative group"><a id="text-to-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="#text-to-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>Text-to-image</span></h1> <p data-svelte-h="svelte-1l46gj3">When you think of diffusion models, text-to-image is usually one of the first things that come to mind. Text-to-image generates an image from a text description (for example, “Astronaut in a jungle, cold color palette, muted colors, detailed, 8k”) which is also known as a <em>prompt</em>.</p> <p data-svelte-h="svelte-1t2ibrh">From a very high level, a diffusion model takes a prompt and some random initial noise, and iteratively removes the noise to construct an image. The <em>denoising</em> process is guided by the prompt, and once the denoising process ends after a predetermined number of time steps, the image representation is decoded into an image.</p> <blockquote class="tip" data-svelte-h="svelte-v57mtj"><p>Read the <a href="https://huggingface.co/blog/stable_diffusion#how-does-stable-diffusion-work" rel="nofollow">How does Stable Diffusion work?</a> blog post to learn more about how a latent diffusion model works.</p></blockquote> <p data-svelte-h="svelte-1n6nnyu">You can generate images from a prompt in 🤗 Diffusers in two steps:</p> <ol data-svelte-h="svelte-1fqmxia"><li>Load a checkpoint into the <a href="/docs/diffusers/pr_12448/en/api/pipelines/auto_pipeline#diffusers.AutoPipelineForText2Image">AutoPipelineForText2Image</a> class, which automatically detects the appropriate pipeline class to use based on the checkpoint:</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 class=""><!-- HTML_TAG_START --><span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> AutoPipelineForText2Image | |
| <span class="hljs-keyword">import</span> torch | |
| pipeline = AutoPipelineForText2Image.from_pretrained( | |
| <span class="hljs-string">"stable-diffusion-v1-5/stable-diffusion-v1-5"</span>, torch_dtype=torch.float16, variant=<span class="hljs-string">"fp16"</span> | |
| ).to(<span class="hljs-string">"cuda"</span>)<!-- HTML_TAG_END --></pre></div> <ol start="2" data-svelte-h="svelte-omo4p8"><li>Pass a prompt to the pipeline to generate an image:</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 class=""><!-- HTML_TAG_START -->image = pipeline( | |
| <span class="hljs-string">"stained glass of darth vader, backlight, centered composition, masterpiece, photorealistic, 8k"</span> | |
| ).images[<span class="hljs-number">0</span>] | |
| image<!-- HTML_TAG_END --></pre></div> <div class="flex justify-center" data-svelte-h="svelte-12i7yhb"><img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/text2img-vader.png"></div> <h2 class="relative group"><a id="popular-models" 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="#popular-models"><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>Popular models</span></h2> <p data-svelte-h="svelte-bqc02k">The most common text-to-image models are <a href="https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5" rel="nofollow">Stable Diffusion v1.5</a>, <a href="https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0" rel="nofollow">Stable Diffusion XL (SDXL)</a>, and <a href="https://huggingface.co/kandinsky-community/kandinsky-2-2-decoder" rel="nofollow">Kandinsky 2.2</a>. There are also ControlNet models or adapters that can be used with text-to-image models for more direct control in generating images. The results from each model are slightly different because of their architecture and training process, but no matter which model you choose, their usage is more or less the same. Let’s use the same prompt for each model and compare their results.</p> <h3 class="relative group"><a id="stable-diffusion-v15" 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="#stable-diffusion-v15"><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>Stable Diffusion v1.5</span></h3> <p data-svelte-h="svelte-14zve4s"><a href="https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5" rel="nofollow">Stable Diffusion v1.5</a> is a latent diffusion model initialized from <a href="https://huggingface.co/CompVis/stable-diffusion-v1-4" rel="nofollow">Stable Diffusion v1-4</a>, and finetuned for 595K steps on 512x512 images from the LAION-Aesthetics V2 dataset. You can use this model like:</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> AutoPipelineForText2Image | |
| <span class="hljs-keyword">import</span> torch | |
| pipeline = AutoPipelineForText2Image.from_pretrained( | |
| <span class="hljs-string">"stable-diffusion-v1-5/stable-diffusion-v1-5"</span>, torch_dtype=torch.float16, variant=<span class="hljs-string">"fp16"</span> | |
| ).to(<span class="hljs-string">"cuda"</span>) | |
| generator = torch.Generator(<span class="hljs-string">"cuda"</span>).manual_seed(<span class="hljs-number">31</span>) | |
| image = pipeline(<span class="hljs-string">"Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"</span>, generator=generator).images[<span class="hljs-number">0</span>] | |
| image<!-- HTML_TAG_END --></pre></div> <h3 class="relative group"><a id="stable-diffusion-xl" 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="#stable-diffusion-xl"><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>Stable Diffusion XL</span></h3> <p data-svelte-h="svelte-16df6ya">SDXL is a much larger version of the previous Stable Diffusion models, and involves a two-stage model process that adds even more details to an image. It also includes some additional <em>micro-conditionings</em> to generate high-quality images centered subjects. Take a look at the more comprehensive <a href="sdxl">SDXL</a> guide to learn more about how to use it. In general, you can use SDXL like:</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> AutoPipelineForText2Image | |
| <span class="hljs-keyword">import</span> torch | |
| pipeline = AutoPipelineForText2Image.from_pretrained( | |
| <span class="hljs-string">"stabilityai/stable-diffusion-xl-base-1.0"</span>, torch_dtype=torch.float16, variant=<span class="hljs-string">"fp16"</span> | |
| ).to(<span class="hljs-string">"cuda"</span>) | |
| generator = torch.Generator(<span class="hljs-string">"cuda"</span>).manual_seed(<span class="hljs-number">31</span>) | |
| image = pipeline(<span class="hljs-string">"Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"</span>, generator=generator).images[<span class="hljs-number">0</span>] | |
| image<!-- HTML_TAG_END --></pre></div> <h3 class="relative group"><a id="kandinsky-22" 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="#kandinsky-22"><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>Kandinsky 2.2</span></h3> <p data-svelte-h="svelte-4hv0fs">The Kandinsky model is a bit different from the Stable Diffusion models because it also uses an image prior model to create embeddings that are used to better align text and images in the diffusion model.</p> <p data-svelte-h="svelte-11xg80m">The easiest way to use Kandinsky 2.2 is:</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> AutoPipelineForText2Image | |
| <span class="hljs-keyword">import</span> torch | |
| pipeline = AutoPipelineForText2Image.from_pretrained( | |
| <span class="hljs-string">"kandinsky-community/kandinsky-2-2-decoder"</span>, torch_dtype=torch.float16 | |
| ).to(<span class="hljs-string">"cuda"</span>) | |
| generator = torch.Generator(<span class="hljs-string">"cuda"</span>).manual_seed(<span class="hljs-number">31</span>) | |
| image = pipeline(<span class="hljs-string">"Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"</span>, generator=generator).images[<span class="hljs-number">0</span>] | |
| image<!-- HTML_TAG_END --></pre></div> <h3 class="relative group"><a id="controlnet" 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="#controlnet"><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>ControlNet</span></h3> <p data-svelte-h="svelte-b1h4vi">ControlNet models are auxiliary models or adapters that are finetuned on top of text-to-image models, such as <a href="https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5" rel="nofollow">Stable Diffusion v1.5</a>. Using ControlNet models in combination with text-to-image models offers diverse options for more explicit control over how to generate an image. With ControlNet, you add an additional conditioning input image to the model. For example, if you provide an image of a human pose (usually represented as multiple keypoints that are connected into a skeleton) as a conditioning input, the model generates an image that follows the pose of the image. Check out the more in-depth <a href="controlnet">ControlNet</a> guide to learn more about other conditioning inputs and how to use them.</p> <p data-svelte-h="svelte-sut514">In this example, let’s condition the ControlNet with a human pose estimation image. Load the ControlNet model pretrained on human pose estimations:</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> ControlNetModel, AutoPipelineForText2Image | |
| <span class="hljs-keyword">from</span> diffusers.utils <span class="hljs-keyword">import</span> load_image | |
| <span class="hljs-keyword">import</span> torch | |
| controlnet = ControlNetModel.from_pretrained( | |
| <span class="hljs-string">"lllyasviel/control_v11p_sd15_openpose"</span>, torch_dtype=torch.float16, variant=<span class="hljs-string">"fp16"</span> | |
| ).to(<span class="hljs-string">"cuda"</span>) | |
| pose_image = load_image(<span class="hljs-string">"https://huggingface.co/lllyasviel/control_v11p_sd15_openpose/resolve/main/images/control.png"</span>)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-ajsupk">Pass the <code>controlnet</code> to the <a href="/docs/diffusers/pr_12448/en/api/pipelines/auto_pipeline#diffusers.AutoPipelineForText2Image">AutoPipelineForText2Image</a>, and provide the prompt and pose estimation image:</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 -->pipeline = AutoPipelineForText2Image.from_pretrained( | |
| <span class="hljs-string">"stable-diffusion-v1-5/stable-diffusion-v1-5"</span>, controlnet=controlnet, torch_dtype=torch.float16, variant=<span class="hljs-string">"fp16"</span> | |
| ).to(<span class="hljs-string">"cuda"</span>) | |
| generator = torch.Generator(<span class="hljs-string">"cuda"</span>).manual_seed(<span class="hljs-number">31</span>) | |
| image = pipeline(<span class="hljs-string">"Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"</span>, image=pose_image, generator=generator).images[<span class="hljs-number">0</span>] | |
| image<!-- HTML_TAG_END --></pre></div> <div class="flex flex-row gap-4" data-svelte-h="svelte-16c2hir"><div class="flex-1"><img class="rounded-xl" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/text2img-1.png"> <figcaption class="mt-2 text-center text-sm text-gray-500">Stable Diffusion v1.5</figcaption></div> <div class="flex-1"><img class="rounded-xl" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/sdxl-text2img.png"> <figcaption class="mt-2 text-center text-sm text-gray-500">Stable Diffusion XL</figcaption></div> <div class="flex-1"><img class="rounded-xl" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/text2img-2.png"> <figcaption class="mt-2 text-center text-sm text-gray-500">Kandinsky 2.2</figcaption></div> <div class="flex-1"><img class="rounded-xl" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/text2img-3.png"> <figcaption class="mt-2 text-center text-sm text-gray-500">ControlNet (pose conditioning)</figcaption></div></div> <h2 class="relative group"><a id="configure-pipeline-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-pipeline-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 pipeline parameters</span></h2> <p data-svelte-h="svelte-eshh8b">There are a number of parameters that can be configured in the pipeline that affect how an image is generated. You can change the image’s output size, specify a negative prompt to improve image quality, and more. This section dives deeper into how to use these parameters.</p> <h3 class="relative group"><a id="height-and-width" 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="#height-and-width"><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>Height and width</span></h3> <p data-svelte-h="svelte-1qwh4hb">The <code>height</code> and <code>width</code> parameters control the height and width (in pixels) of the generated image. By default, the Stable Diffusion v1.5 model outputs 512x512 images, but you can change this to any size that is a multiple of 8. For example, to create a rectangular image:</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> AutoPipelineForText2Image | |
| <span class="hljs-keyword">import</span> torch | |
| pipeline = AutoPipelineForText2Image.from_pretrained( | |
| <span class="hljs-string">"stable-diffusion-v1-5/stable-diffusion-v1-5"</span>, torch_dtype=torch.float16, variant=<span class="hljs-string">"fp16"</span> | |
| ).to(<span class="hljs-string">"cuda"</span>) | |
| image = pipeline( | |
| <span class="hljs-string">"Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"</span>, height=<span class="hljs-number">768</span>, width=<span class="hljs-number">512</span> | |
| ).images[<span class="hljs-number">0</span>] | |
| image<!-- HTML_TAG_END --></pre></div> <div class="flex justify-center" data-svelte-h="svelte-oonymb"><img class="rounded-xl" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/text2img-hw.png"></div> <blockquote class="warning" data-svelte-h="svelte-kgwc7t"><p>Other models may have different default image sizes depending on the image sizes in the training dataset. For example, SDXL’s default image size is 1024x1024 and using lower <code>height</code> and <code>width</code> values may result in lower quality images. Make sure you check the model’s API reference first!</p></blockquote> <h3 class="relative group"><a id="guidance-scale" 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="#guidance-scale"><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>Guidance scale</span></h3> <p data-svelte-h="svelte-bwviyb">The <code>guidance_scale</code> parameter affects how much the prompt influences image generation. A lower value gives the model “creativity” to generate images that are more loosely related to the prompt. Higher <code>guidance_scale</code> values push the model to follow the prompt more closely, and if this value is too high, you may observe some artifacts in the generated image.</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> AutoPipelineForText2Image | |
| <span class="hljs-keyword">import</span> torch | |
| pipeline = AutoPipelineForText2Image.from_pretrained( | |
| <span class="hljs-string">"stable-diffusion-v1-5/stable-diffusion-v1-5"</span>, torch_dtype=torch.float16 | |
| ).to(<span class="hljs-string">"cuda"</span>) | |
| image = pipeline( | |
| <span class="hljs-string">"Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"</span>, guidance_scale=<span class="hljs-number">3.5</span> | |
| ).images[<span class="hljs-number">0</span>] | |
| image<!-- HTML_TAG_END --></pre></div> <div class="flex flex-row gap-4" data-svelte-h="svelte-yknxlr"><div class="flex-1"><img class="rounded-xl" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/text2img-guidance-scale-2.5.png"> <figcaption class="mt-2 text-center text-sm text-gray-500">guidance_scale = 2.5</figcaption></div> <div class="flex-1"><img class="rounded-xl" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/text2img-guidance-scale-7.5.png"> <figcaption class="mt-2 text-center text-sm text-gray-500">guidance_scale = 7.5</figcaption></div> <div class="flex-1"><img class="rounded-xl" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/text2img-guidance-scale-10.5.png"> <figcaption class="mt-2 text-center text-sm text-gray-500">guidance_scale = 10.5</figcaption></div></div> <h3 class="relative group"><a id="negative-prompt" 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="#negative-prompt"><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>Negative prompt</span></h3> <p data-svelte-h="svelte-10oi6q0">Just like how a prompt guides generation, a <em>negative prompt</em> steers the model away from things you don’t want the model to generate. This is commonly used to improve overall image quality by removing poor or bad image features such as “low resolution” or “bad details”. You can also use a negative prompt to remove or modify the content and style of an image.</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> AutoPipelineForText2Image | |
| <span class="hljs-keyword">import</span> torch | |
| pipeline = AutoPipelineForText2Image.from_pretrained( | |
| <span class="hljs-string">"stable-diffusion-v1-5/stable-diffusion-v1-5"</span>, torch_dtype=torch.float16 | |
| ).to(<span class="hljs-string">"cuda"</span>) | |
| image = pipeline( | |
| prompt=<span class="hljs-string">"Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"</span>, | |
| negative_prompt=<span class="hljs-string">"ugly, deformed, disfigured, poor details, bad anatomy"</span>, | |
| ).images[<span class="hljs-number">0</span>] | |
| image<!-- HTML_TAG_END --></pre></div> <div class="flex flex-row gap-4" data-svelte-h="svelte-1y3fehm"><div class="flex-1"><img class="rounded-xl" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/text2img-neg-prompt-1.png"> <figcaption class="mt-2 text-center text-sm text-gray-500">negative_prompt = "ugly, deformed, disfigured, poor details, bad anatomy"</figcaption></div> <div class="flex-1"><img class="rounded-xl" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/text2img-neg-prompt-2.png"> <figcaption class="mt-2 text-center text-sm text-gray-500">negative_prompt = "astronaut"</figcaption></div></div> <h3 class="relative group"><a id="generator" 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="#generator"><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>Generator</span></h3> <p data-svelte-h="svelte-am7ub1">A <a href="https://pytorch.org/docs/stable/generated/torch.Generator.html#generator" rel="nofollow"><code>torch.Generator</code></a> object enables reproducibility in a pipeline by setting a manual seed. You can use a <code>Generator</code> to generate batches of images and iteratively improve on an image generated from a seed as detailed in the <a href="reusing_seeds">Improve image quality with deterministic generation</a> guide.</p> <p data-svelte-h="svelte-11rytjg">You can set a seed and <code>Generator</code> as shown below. Creating an image with a <code>Generator</code> should return the same result each time instead of randomly generating a new image.</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> AutoPipelineForText2Image | |
| <span class="hljs-keyword">import</span> torch | |
| pipeline = AutoPipelineForText2Image.from_pretrained( | |
| <span class="hljs-string">"stable-diffusion-v1-5/stable-diffusion-v1-5"</span>, torch_dtype=torch.float16 | |
| ).to(<span class="hljs-string">"cuda"</span>) | |
| generator = torch.Generator(device=<span class="hljs-string">"cuda"</span>).manual_seed(<span class="hljs-number">30</span>) | |
| image = pipeline( | |
| <span class="hljs-string">"Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"</span>, | |
| generator=generator, | |
| ).images[<span class="hljs-number">0</span>] | |
| image<!-- HTML_TAG_END --></pre></div> <h2 class="relative group"><a id="control-image-generation" 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-generation"><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 generation</span></h2> <p data-svelte-h="svelte-nhxl1e">There are several ways to exert more control over how an image is generated outside of configuring a pipeline’s parameters, such as prompt weighting and ControlNet models.</p> <h3 class="relative group"><a id="prompt-weighting" 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="#prompt-weighting"><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>Prompt weighting</span></h3> <p data-svelte-h="svelte-16kzvf0">Prompt weighting is a technique for increasing or decreasing the importance of concepts in a prompt to emphasize or minimize certain features in an image. We recommend using the <a href="https://github.com/damian0815/compel" rel="nofollow">Compel</a> library to help you generate the weighted prompt embeddings.</p> <blockquote class="tip" data-svelte-h="svelte-eowuo7"><p>Learn how to create the prompt embeddings in the <a href="weighted_prompts">Prompt weighting</a> guide. This example focuses on how to use the prompt embeddings in the pipeline.</p></blockquote> <p data-svelte-h="svelte-3641kw">Once you’ve created the embeddings, you can pass them to the <code>prompt_embeds</code> (and <code>negative_prompt_embeds</code> if you’re using a negative prompt) parameter in the pipeline.</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> AutoPipelineForText2Image | |
| <span class="hljs-keyword">import</span> torch | |
| pipeline = AutoPipelineForText2Image.from_pretrained( | |
| <span class="hljs-string">"stable-diffusion-v1-5/stable-diffusion-v1-5"</span>, torch_dtype=torch.float16 | |
| ).to(<span class="hljs-string">"cuda"</span>) | |
| image = pipeline( | |
| prompt_embeds=prompt_embeds, <span class="hljs-comment"># generated from Compel</span> | |
| negative_prompt_embeds=negative_prompt_embeds, <span class="hljs-comment"># generated from Compel</span> | |
| ).images[<span class="hljs-number">0</span>]<!-- HTML_TAG_END --></pre></div> <h3 class="relative group"><a id="controlnet" 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="#controlnet"><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>ControlNet</span></h3> <p data-svelte-h="svelte-1egssiu">As you saw in the <a href="#controlnet">ControlNet</a> section, these models offer a more flexible and accurate way to generate images by incorporating an additional conditioning image input. Each ControlNet model is pretrained on a particular type of conditioning image to generate new images that resemble it. For example, if you take a ControlNet model pretrained on depth maps, you can give the model a depth map as a conditioning input and it’ll generate an image that preserves the spatial information in it. This is quicker and easier than specifying the depth information in a prompt. You can even combine multiple conditioning inputs with a <a href="controlnet#multicontrolnet">MultiControlNet</a>!</p> <p data-svelte-h="svelte-3yz46e">There are many types of conditioning inputs you can use, and 🤗 Diffusers supports ControlNet for Stable Diffusion and SDXL models. Take a look at the more comprehensive <a href="controlnet">ControlNet</a> guide to learn how you can use these models.</p> <h2 class="relative group"><a id="optimize" 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="#optimize"><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>Optimize</span></h2> <p data-svelte-h="svelte-jaf97h">Diffusion models are large, and the iterative nature of denoising an image is computationally expensive and intensive. But this doesn’t mean you need access to powerful - or even many - GPUs to use them. There are many optimization techniques for running diffusion models on consumer and free-tier resources. For example, you can load model weights in half-precision to save GPU memory and increase speed or offload the entire model to the GPU to save even more memory.</p> <p data-svelte-h="svelte-1xjfcov">PyTorch 2.0 also supports a more memory-efficient attention mechanism called <a href="../optimization/fp16#scaled-dot-product-attention"><em>scaled dot product attention</em></a> that is automatically enabled if you’re using PyTorch 2.0. You can combine this with <a href="https://pytorch.org/tutorials/intermediate/torch_compile_tutorial.html" rel="nofollow"><code>torch.compile</code></a> to speed your code up even more:</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> AutoPipelineForText2Image | |
| <span class="hljs-keyword">import</span> torch | |
| pipeline = AutoPipelineForText2Image.from_pretrained(<span class="hljs-string">"stable-diffusion-v1-5/stable-diffusion-v1-5"</span>, torch_dtype=torch.float16, variant=<span class="hljs-string">"fp16"</span>).to(<span class="hljs-string">"cuda"</span>) | |
| pipeline.unet = torch.<span class="hljs-built_in">compile</span>(pipeline.unet, mode=<span class="hljs-string">"reduce-overhead"</span>, fullgraph=<span class="hljs-literal">True</span>)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-u4svyh">For more tips on how to optimize your code to save memory and speed up inference, read the <a href="../optimization/fp16">Accelerate inference</a> and <a href="../optimization/memory">Reduce memory usage</a> guides.</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/using-diffusers/conditional_image_generation.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_n9i9q2 = { | |
| assets: "/docs/diffusers/pr_12448/en", | |
| base: "/docs/diffusers/pr_12448/en", | |
| env: {} | |
| }; | |
| const element = document.currentScript.parentElement; | |
| const data = [null,null]; | |
| Promise.all([ | |
| import("/docs/diffusers/pr_12448/en/_app/immutable/entry/start.77018737.js"), | |
| import("/docs/diffusers/pr_12448/en/_app/immutable/entry/app.30e12370.js") | |
| ]).then(([kit, app]) => { | |
| kit.start(app, element, { | |
| node_ids: [0, 325], | |
| data, | |
| form: null, | |
| error: null | |
| }); | |
| }); | |
| } | |
| </script> | |
Xet Storage Details
- Size:
- 64.1 kB
- Xet hash:
- 4f06208c532f32a5ecb2cce7b8a1577ff5e4f92fb754ff1de26bc2760a4b2ba8
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.