Buckets:

rtrm's picture
download
raw
28.6 kB
<meta charset="utf-8" /><meta http-equiv="content-security-policy" content=""><meta name="hf:doc:metadata" content="{&quot;local&quot;:&quot;shape&quot;,&quot;sections&quot;:[{&quot;local&quot;:&quot;textto3d&quot;,&quot;title&quot;:&quot;Text-to-3D&quot;},{&quot;local&quot;:&quot;imageto3d&quot;,&quot;title&quot;:&quot;Image-to-3D&quot;},{&quot;local&quot;:&quot;generate-mesh&quot;,&quot;title&quot;:&quot;Generate mesh&quot;}],&quot;title&quot;:&quot;Shap-E&quot;}" data-svelte="svelte-1phssyn">
<link rel="modulepreload" href="/docs/diffusers/v0.21.0/en/_app/assets/pages/__layout.svelte-hf-doc-builder.css">
<link rel="modulepreload" href="/docs/diffusers/v0.21.0/en/_app/start-hf-doc-builder.js">
<link rel="modulepreload" href="/docs/diffusers/v0.21.0/en/_app/chunks/vendor-hf-doc-builder.js">
<link rel="modulepreload" href="/docs/diffusers/v0.21.0/en/_app/chunks/paths-hf-doc-builder.js">
<link rel="modulepreload" href="/docs/diffusers/v0.21.0/en/_app/pages/__layout.svelte-hf-doc-builder.js">
<link rel="modulepreload" href="/docs/diffusers/v0.21.0/en/_app/pages/using-diffusers/shap-e.mdx-hf-doc-builder.js">
<link rel="modulepreload" href="/docs/diffusers/v0.21.0/en/_app/chunks/Tip-hf-doc-builder.js">
<link rel="modulepreload" href="/docs/diffusers/v0.21.0/en/_app/chunks/IconCopyLink-hf-doc-builder.js">
<link rel="modulepreload" href="/docs/diffusers/v0.21.0/en/_app/chunks/CodeBlock-hf-doc-builder.js">
<link rel="modulepreload" href="/docs/diffusers/v0.21.0/en/_app/chunks/DocNotebookDropdown-hf-doc-builder.js">
<h1 class="relative group"><a id="shape" 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="#shape"><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>Shap-E
</span></h1>
<div class="flex space-x-1 absolute z-10 right-0 top-0">
<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>
<p>Shap-E is a conditional model for generating 3D assets which could be used for video game development, interior design, and architecture. It is trained on a large dataset of 3D assets, and post-processed to render more views of each object and produce 16K instead of 4K point clouds. The Shap-E model is trained in two steps:</p>
<ol><li>a encoder accepts the point clouds and rendered views of a 3D asset and outputs the parameters of implicit functions that represent the asset</li>
<li>a diffusion model is trained on the latents produced by the encoder to generate either neural radiance fields (NeRFs) or a textured 3D mesh, making it easier to render and use the 3D asset in downstream applications</li></ol>
<p>This guide will show you how to use Shap-E to start generating your own 3D assets!</p>
<p>Before you begin, make sure you have the following libraries installed:</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 --><span class="hljs-comment"># uncomment to install the necessary libraries in Colab</span>
<span class="hljs-comment">#!pip install diffusers transformers accelerate safetensors trimesh</span><!-- HTML_TAG_END --></pre></div>
<h2 class="relative group"><a id="textto3d" 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="#textto3d"><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-3D
</span></h2>
<p>To generate a gif of a 3D object, pass a text prompt to the <a href="/docs/diffusers/v0.21.0/en/api/pipelines/shap_e#diffusers.ShapEPipeline">ShapEPipeline</a>. The pipeline generates a list of image frames which are used to create the 3D object.</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 --><span class="hljs-keyword">import</span> torch
<span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> ShapEPipeline
device = torch.device(<span class="hljs-string">&quot;cuda&quot;</span> <span class="hljs-keyword">if</span> torch.cuda.is_available() <span class="hljs-keyword">else</span> <span class="hljs-string">&quot;cpu&quot;</span>)
pipe = ShapEPipeline.from_pretrained(<span class="hljs-string">&quot;openai/shap-e&quot;</span>, torch_dtype=torch.float16, variant=<span class="hljs-string">&quot;fp16&quot;</span>, use_safetensors=<span class="hljs-literal">True</span>)
pipe = pipe.to(device)
guidance_scale = <span class="hljs-number">15.0</span>
prompt = [<span class="hljs-string">&quot;A firecracker&quot;</span>, <span class="hljs-string">&quot;A birthday cupcake&quot;</span>]
images = pipe(
prompt,
guidance_scale=guidance_scale,
num_inference_steps=<span class="hljs-number">64</span>,
frame_size=<span class="hljs-number">256</span>,
).images<!-- HTML_TAG_END --></pre></div>
<p>Now use the <a href="/docs/diffusers/v0.21.0/en/api/utilities#diffusers.utils.export_to_gif">export_to_gif()</a> function to turn the list of image frames into a gif of the 3D object.</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 --><span class="hljs-keyword">from</span> diffusers.utils <span class="hljs-keyword">import</span> export_to_gif
export_to_gif(images[<span class="hljs-number">0</span>], <span class="hljs-string">&quot;firecracker_3d.gif&quot;</span>)
export_to_gif(images[<span class="hljs-number">1</span>], <span class="hljs-string">&quot;cake_3d.gif&quot;</span>)<!-- HTML_TAG_END --></pre></div>
<div class="flex gap-4"><div><img class="rounded-xl" src="https://huggingface.co/datasets/hf-internal-testing/diffusers-images/resolve/main/shap_e/firecracker_out.gif">
<figcaption class="mt-2 text-center text-sm text-gray-500">firecracker</figcaption></div>
<div><img class="rounded-xl" src="https://huggingface.co/datasets/hf-internal-testing/diffusers-images/resolve/main/shap_e/cake_out.gif">
<figcaption class="mt-2 text-center text-sm text-gray-500">cupcake</figcaption></div></div>
<h2 class="relative group"><a id="imageto3d" 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="#imageto3d"><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>Image-to-3D
</span></h2>
<p>To generate a 3D object from another image, use the <a href="/docs/diffusers/v0.21.0/en/api/pipelines/shap_e#diffusers.ShapEImg2ImgPipeline">ShapEImg2ImgPipeline</a>. You can use an existing image or generate an entirely new one. Let’s use the the <a href="../api/pipelines/kandinsky">Kandinsky 2.1</a> model to generate 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><!-- HTML_TAG_START --><span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> DiffusionPipeline
<span class="hljs-keyword">import</span> torch
prior_pipeline = DiffusionPipeline.from_pretrained(<span class="hljs-string">&quot;kandinsky-community/kandinsky-2-1-prior&quot;</span>, torch_dtype=torch.float16, use_safetensors=<span class="hljs-literal">True</span>).to(<span class="hljs-string">&quot;cuda&quot;</span>)
pipeline = DiffusionPipeline.from_pretrained(<span class="hljs-string">&quot;kandinsky-community/kandinsky-2-1&quot;</span>, torch_dtype=torch.float16, use_safetensors=<span class="hljs-literal">True</span>).to(<span class="hljs-string">&quot;cuda&quot;</span>)
prompt = <span class="hljs-string">&quot;A cheeseburger, white background&quot;</span>
image_embeds, negative_image_embeds = prior_pipeline(prompt, guidance_scale=<span class="hljs-number">1.0</span>).to_tuple()
image = pipeline(
prompt,
image_embeds=image_embeds,
negative_image_embeds=negative_image_embeds,
).images[<span class="hljs-number">0</span>]
image.save(<span class="hljs-string">&quot;burger.png&quot;</span>)<!-- HTML_TAG_END --></pre></div>
<p>Pass the cheeseburger to the <a href="/docs/diffusers/v0.21.0/en/api/pipelines/shap_e#diffusers.ShapEImg2ImgPipeline">ShapEImg2ImgPipeline</a> to generate a 3D representation of it.</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 --><span class="hljs-keyword">from</span> PIL <span class="hljs-keyword">import</span> Image
<span class="hljs-keyword">from</span> diffusers.utils <span class="hljs-keyword">import</span> export_to_gif
pipe = ShapEImg2ImgPipeline.from_pretrained(<span class="hljs-string">&quot;openai/shap-e-img2img&quot;</span>, torch_dtype=torch.float16, variant=<span class="hljs-string">&quot;fp16&quot;</span>).to(<span class="hljs-string">&quot;cuda&quot;</span>)
guidance_scale = <span class="hljs-number">3.0</span>
image = Image.<span class="hljs-built_in">open</span>(<span class="hljs-string">&quot;burger.png&quot;</span>).resize((<span class="hljs-number">256</span>, <span class="hljs-number">256</span>))
images = pipe(
image,
guidance_scale=guidance_scale,
num_inference_steps=<span class="hljs-number">64</span>,
frame_size=<span class="hljs-number">256</span>,
).images
gif_path = export_to_gif(images[<span class="hljs-number">0</span>], <span class="hljs-string">&quot;burger_3d.gif&quot;</span>)<!-- HTML_TAG_END --></pre></div>
<div class="flex gap-4"><div><img class="rounded-xl" src="https://huggingface.co/datasets/hf-internal-testing/diffusers-images/resolve/main/shap_e/burger_in.png">
<figcaption class="mt-2 text-center text-sm text-gray-500">cheeseburger</figcaption></div>
<div><img class="rounded-xl" src="https://huggingface.co/datasets/hf-internal-testing/diffusers-images/resolve/main/shap_e/burger_out.gif">
<figcaption class="mt-2 text-center text-sm text-gray-500">3D cheeseburger</figcaption></div></div>
<h2 class="relative group"><a id="generate-mesh" 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="#generate-mesh"><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>Generate mesh
</span></h2>
<p>Shap-E is a flexible model that can also generate textured mesh outputs to be rendered for downstream applications. In this example, you’ll convert the output into a <code>glb</code> file because the 🤗 Datasets library supports mesh visualization of <code>glb</code> files which can be rendered by the <a href="https://huggingface.co/docs/hub/datasets-viewer#dataset-preview" rel="nofollow">Dataset viewer</a>.</p>
<p>You can generate mesh outputs for both the <a href="/docs/diffusers/v0.21.0/en/api/pipelines/shap_e#diffusers.ShapEPipeline">ShapEPipeline</a> and <a href="/docs/diffusers/v0.21.0/en/api/pipelines/shap_e#diffusers.ShapEImg2ImgPipeline">ShapEImg2ImgPipeline</a> by specifying the <code>output_type</code> parameter as <code>&quot;mesh&quot;</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 --><span class="hljs-keyword">import</span> torch
<span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> ShapEPipeline
device = torch.device(<span class="hljs-string">&quot;cuda&quot;</span> <span class="hljs-keyword">if</span> torch.cuda.is_available() <span class="hljs-keyword">else</span> <span class="hljs-string">&quot;cpu&quot;</span>)
pipe = ShapEPipeline.from_pretrained(<span class="hljs-string">&quot;openai/shap-e&quot;</span>, torch_dtype=torch.float16, variant=<span class="hljs-string">&quot;fp16&quot;</span>, use_safetensors=<span class="hljs-literal">True</span>)
pipe = pipe.to(device)
guidance_scale = <span class="hljs-number">15.0</span>
prompt = <span class="hljs-string">&quot;A birthday cupcake&quot;</span>
images = pipe(prompt, guidance_scale=guidance_scale, num_inference_steps=<span class="hljs-number">64</span>, frame_size=<span class="hljs-number">256</span>, output_type=<span class="hljs-string">&quot;mesh&quot;</span>).images<!-- HTML_TAG_END --></pre></div>
<p>Use the <code>export_to_ply()</code> function to save the mesh output as a <code>ply</code> file:</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>You can optionally save the mesh output as an <code>obj</code> file with the <code>export_to_obj()</code> function. The ability to save the mesh output in a variety of formats makes it more flexible for downstream usage!</p></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><!-- HTML_TAG_START --><span class="hljs-keyword">from</span> diffusers.utils <span class="hljs-keyword">import</span> export_to_ply
ply_path = export_to_ply(images[<span class="hljs-number">0</span>], <span class="hljs-string">&quot;3d_cake.ply&quot;</span>)
<span class="hljs-built_in">print</span>(<span class="hljs-string">f&quot;saved to folder: <span class="hljs-subst">{ply_path}</span>&quot;</span>)<!-- HTML_TAG_END --></pre></div>
<p>Then you can convert the <code>ply</code> file to a <code>glb</code> file with the trimesh library:</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 --><span class="hljs-keyword">import</span> trimesh
mesh = trimesh.load(<span class="hljs-string">&quot;3d_cake.ply&quot;</span>)
mesh.export(<span class="hljs-string">&quot;3d_cake.glb&quot;</span>, file_type=<span class="hljs-string">&quot;glb&quot;</span>)<!-- HTML_TAG_END --></pre></div>
<p>By default, the mesh output is focused from the bottom viewpoint but you can change the default viewpoint by applying a rotation transform:</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 --><span class="hljs-keyword">import</span> trimesh
<span class="hljs-keyword">import</span> numpy <span class="hljs-keyword">as</span> np
mesh = trimesh.load(<span class="hljs-string">&quot;3d_cake.ply&quot;</span>)
rot = trimesh.transformations.rotation_matrix(-np.pi / <span class="hljs-number">2</span>, [<span class="hljs-number">1</span>, <span class="hljs-number">0</span>, <span class="hljs-number">0</span>])
mesh = mesh.apply_transform(rot)
mesh.export(<span class="hljs-string">&quot;3d_cake.glb&quot;</span>, file_type=<span class="hljs-string">&quot;glb&quot;</span>)<!-- HTML_TAG_END --></pre></div>
<p>Upload the mesh file to your dataset repository to visualize it with the Dataset viewer!</p>
<div class="flex justify-center"><img class="rounded-xl" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/3D-cake.gif"></div>
<script type="module" data-hydrate="w6k8y">
import { start } from "/docs/diffusers/v0.21.0/en/_app/start-hf-doc-builder.js";
start({
target: document.querySelector('[data-hydrate="w6k8y"]').parentNode,
paths: {"base":"/docs/diffusers/v0.21.0/en","assets":"/docs/diffusers/v0.21.0/en"},
session: {},
route: false,
spa: false,
trailing_slash: "never",
hydrate: {
status: 200,
error: null,
nodes: [
import("/docs/diffusers/v0.21.0/en/_app/pages/__layout.svelte-hf-doc-builder.js"),
import("/docs/diffusers/v0.21.0/en/_app/pages/using-diffusers/shap-e.mdx-hf-doc-builder.js")
],
params: {}
}
});
</script>

Xet Storage Details

Size:
28.6 kB
·
Xet hash:
fba977edd281ed5d925cdaacc289a9481d0ea66f9b62c95636edd5251b25b509

Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.