bi6nddlmZmZmZmZddlZddlmZddlm Z ddl m Z ddl m Z mZGd d e Zy) )ListOptionalTupleUnionN) UNet2DModel) PNDMScheduler) randn_tensor)DiffusionPipelineImagePipelineOutputceZdZUdZeed<eed<dedeffd Zej d de de de e ejeejfde ed ed e eeff d ZxZS) PNDMPipelinea Pipeline for unconditional image generation. 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.). Parameters: unet ([`UNet2DModel`]): A `UNet2DModel` to denoise the encoded image latents. scheduler ([`PNDMScheduler`]): A `PNDMScheduler` to be used in combination with `unet` to denoise the encoded image. unet schedulerct|tj|j}|j ||y)N)rr)super__init__r from_configconfigregister_modules)selfrr __class__s l/home/cdr/jupyterlab/.venv/lib/python3.12/site-packages/diffusers/pipelines/deprecated/pndm/pipeline_pndm.pyrzPNDMPipeline.__init__+s7 !--i.>.>?  49= batch_sizenum_inference_steps generator output_type return_dictreturnc t||jjj|jjj|jjjf||j }|j j||j|j jD]E}|j||j} |j j| ||j}G|dz dzjdd}|jjddddj!}|dk(r|j#|}|s|fSt%|S) aX The call function to the pipeline for generation. Args: batch_size (`int`, `optional`, defaults to 1): The number of images to generate. num_inference_steps (`int`, `optional`, defaults to 50): The number of denoising steps. More denoising steps usually lead to a higher quality image at the expense of slower inference. generator (`torch.Generator`, `optional`): A [`torch.Generator`](https://pytorch.org/docs/stable/generated/torch.Generator.html) to make generation deterministic. output_type (`str`, `optional`, defaults to `"pil"`): The output format of the generated image. Choose between `PIL.Image` or `np.array`. return_dict (`bool`, *optional*, defaults to `True`): Whether or not to return a [`ImagePipelineOutput`] instead of a plain tuple. Example: ```py >>> from diffusers import PNDMPipeline >>> # load model and scheduler >>> pndm = PNDMPipeline.from_pretrained("google/ddpm-cifar10-32") >>> # run pipeline in inference (sample random noise and denoise) >>> image = pndm().images[0] >>> # save image >>> image.save("pndm_generated_image.png") ``` Returns: [`~pipelines.ImagePipelineOutput`] or `tuple`: If `return_dict` is `True`, [`~pipelines.ImagePipelineOutput`] is returned, otherwise a `tuple` is returned where the first element is a list with the generated images. )rdeviceg?rr pil)images)r rr in_channels sample_sizer#r set_timesteps progress_bar timestepssamplestep prev_sampleclampcpupermutenumpy numpy_to_pilr ) rrrrrr kwargsimaget model_outputs r__call__zPNDMPipeline.__call__2s5f ))55tyy7G7G7S7SUYU^U^UeUeUqUq r;;  $$%89""4>>#;#;< LA99UA.55LNN'' a?KKE L S''1- ##Aq!Q/557 % %%e,E8O"%00r)r%2Nr&T)__name__ __module__ __qualname____doc__r__annotations__r rtorchno_gradintrr Generatorrstrboolr rr9 __classcell__)rs@rrrs  >[>]>U]]_#%MQ%* F1F1!F1E%//43H"HIJ F1 c] F1  F1 "E) *F1F1rr)typingrrrrr@modelsr schedulersr utils.torch_utilsr pipeline_utilsr r rrrrMs+ 0/ "(.D_1$_1r