+hV4:SSKrSSKJr SSKJrJrJr SSKrSSK r SSK r SSK J r Jr SSKJr SSKJr SSKJrJrJrJr SS KJr S S KJr S S KJr \"5(a SSKJs J r! Sr"OSr"\RF"\$5r%Sr&\"SS\55r'"SS\5r(g)N) dataclass)ListOptionalUnion)CLIPTextModelWithProjection CLIPTokenizer)PriorTransformer)HeunDiscreteScheduler) BaseOutputis_torch_xla_availableloggingreplace_example_docstring) randn_tensor)DiffusionPipeline) ShapERendererTFa Examples: ```py >>> import torch >>> from diffusers import DiffusionPipeline >>> from diffusers.utils import export_to_gif >>> device = torch.device("cuda" if torch.cuda.is_available() else "cpu") >>> repo = "openai/shap-e" >>> pipe = DiffusionPipeline.from_pretrained(repo, torch_dtype=torch.float16) >>> pipe = pipe.to(device) >>> guidance_scale = 15.0 >>> prompt = "a shark" >>> images = pipe( ... prompt, ... guidance_scale=guidance_scale, ... num_inference_steps=64, ... frame_size=256, ... ).images >>> gif_path = export_to_gif(images[0], "shark_3d.gif") ``` c\rSrSr%Sr\\\\RR\\\ R4\ S'Sr g)ShapEPipelineOutputKz Output class for [`ShapEPipeline`] and [`ShapEImg2ImgPipeline`]. Args: images (`torch.Tensor`) A list of images for 3D rendering. imagesN) __name__ __module__ __qualname____firstlineno____doc__rrPILImagenpndarray__annotations____static_attributes__rd/home/james-whalen/.local/lib/python3.13/site-packages/diffusers/pipelines/shap_e/pipeline_shap_e.pyrrKs9 $tCIIOO,-tD4D/EE FFr%rc8^\rSrSrSrSrS/rS\S\S\ S\ S\ 4 U4S jjr S r S r\R "5\"\5SS \S \S\S\\\R.\\R.4S\\R2S\S\S\\S\4Sjj55rSrU=r$) ShapEPipelineXa Pipeline for generating latent representation of a 3D asset and rendering with the NeRF method. This model inherits from [`DiffusionPipeline`]. Check the superclass documentation for the generic methods implemented for all pipelines (downloading, saving, running on a particular device, etc.). Args: prior ([`PriorTransformer`]): The canonical unCLIP prior to approximate the image embedding from the text embedding. text_encoder ([`~transformers.CLIPTextModelWithProjection`]): Frozen text-encoder. tokenizer ([`~transformers.CLIPTokenizer`]): A `CLIPTokenizer` to tokenize text. scheduler ([`HeunDiscreteScheduler`]): A scheduler to be used in combination with the `prior` model to generate image embedding. shap_e_renderer ([`ShapERenderer`]): Shap-E renderer projects the generated latents into parameters of a MLP to create 3D objects with the NeRF rendering method. ztext_encoder->priorshap_e_rendererprior text_encoder tokenizer schedulercH>[TU]5 URUUUUUS9 g)N)r+r,r-r.r*)super__init__register_modules)selfr+r,r-r.r* __class__s r&r1ShapEPipeline.__init__ps2  %+  r%cUc [XX2S9nO>66q$..JiJilmJmprJrGr7stL NNNN334Il^M  #//0A0A&0IJ+77 %778MST7U % (9(9-RY](9(^^ &%*%5%5m%D " "II'=&MNM -"5"5a"89MI r%r_r`num_inference_stepsr7r>guidance_scale frame_size output_type return_dictc [U[5(aSn O8[U[5(a [U5n O[ S[ U535eUR n X-n US:n URXX,5n URRX;S9 URRnURRRnURRRnURXU-4U R U UUUR5nUR#UR$SUU5n['UR)U55HunnU (a[*R,"U/S-5OUnURR/UU5nURUUU S9R0nUR3UR$SSS9unnU (aUR5S5unnUUUU- --nURR7UUUS 9R8n[:(dM[<R>"5 M URA5 US ;a[ S U35eUS :Xa [CUS 9$/nUS:XaJ['U5H:unnURDRGUSSS24U 5nURIU5 M< O['U5H9unnURDRKUSSS24U US9nURIU5 M; [*RL"U5nURO5RQ5nUS:Xa!UVs/sHnURSU5PM nnU (dU4$[CUS 9$s snf)ai The call function to the pipeline for generation. Args: prompt (`str` or `List[str]`): The prompt or prompts to guide the image generation. num_images_per_prompt (`int`, *optional*, defaults to 1): The number of images to generate per prompt. num_inference_steps (`int`, *optional*, defaults to 25): The number of denoising steps. More denoising steps usually lead to a higher quality image at the expense of slower inference. generator (`torch.Generator` or `List[torch.Generator]`, *optional*): A [`torch.Generator`](https://pytorch.org/docs/stable/generated/torch.Generator.html) to make generation deterministic. latents (`torch.Tensor`, *optional*): Pre-generated noisy latents sampled from a Gaussian distribution, to be used as inputs for image generation. Can be used to tweak the same generation with different prompts. If not provided, a latents tensor is generated by sampling using the supplied random `generator`. guidance_scale (`float`, *optional*, defaults to 4.0): A higher guidance scale value encourages the model to generate images closely linked to the text `prompt` at the expense of lower image quality. Guidance scale is enabled when `guidance_scale > 1`. frame_size (`int`, *optional*, default to 64): The width and height of each image frame of the generated 3D output. output_type (`str`, *optional*, defaults to `"pil"`): The output format of the generated image. Choose between `"pil"` (`PIL.Image.Image`), `"np"` (`np.array`), `"latent"` (`torch.Tensor`), or mesh ([`MeshDecoderOutput`]). return_dict (`bool`, *optional*, defaults to `True`): Whether or not to return a [`~pipelines.shap_e.pipeline_shap_e.ShapEPipelineOutput`] instead of a plain tuple. Examples: Returns: [`~pipelines.shap_e.pipeline_shap_e.ShapEPipelineOutput`] or `tuple`: If `return_dict` is `True`, [`~pipelines.shap_e.pipeline_shap_e.ShapEPipelineOutput`] is returned, otherwise a `tuple` is returned where the first element is a list with the generated images. rz2`prompt` has to be of type `str` or `list` but is g?)r8rr)timestepproj_embeddingrI)rqsample)r!pillatentmeshzUOnly the output types `pil`, `np`, `latent` and `mesh` are supported not output_type=ru)rrvN)sizert)*rLstrrMrNr;type_execution_devicerir. set_timesteps timestepsr+confignum_embeddings embedding_dimr?r9reshaper: enumerate progress_barrRr\scale_model_inputpredicted_image_embeddingsplitchunkstep prev_sample XLA_AVAILABLExm mark_stepmaybe_free_model_hooksrr*decode_to_meshappenddecode_to_imagestackcpunumpy numpy_to_pil)r3r_r`rkr7r>rlrmrnro batch_sizer8rargr|r~ritlatent_model_inputscaled_model_input noise_pred_noise_pred_uncondrrurvimages r&__call__ShapEPipeline.__call__swh fc " "J  % %VJQRVW]R^Q_`a a''7 &4s&:#++Frs !(( C&/ ..#))MM   H %8  G* G  GB2%B2r%