o ۷i@sPddlZddlmZddlmZddlmZddlmZm Z Gdd d eZ dS) N) UNet2DModel) PNDMScheduler) randn_tensor)DiffusionPipelineImagePipelineOutputcseZdZUdZeed<eed<dedeffdd Ze    dd e d e d ej e ej BdBde dBdedeeBf ddZZS) 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 schedulercs(tt|j}|j||ddS)N)r r )super__init__r from_configconfigregister_modules)selfr r  __class__g/home/ubuntu/vllm_env/lib/python3.10/site-packages/diffusers/pipelines/deprecated/pndm/pipeline_pndm.pyr )s  zPNDMPipeline.__init__2NpilT batch_sizenum_inference_steps generator output_type return_dictreturnc Kst||jjj|jjj|jjjf||jd}|j|||jj D]}|||j } |j | ||j }q"|dd dd}|dddd}|dkrT||}|sY|fSt|dS) 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?rrrr)images)rr r in_channels sample_sizerr set_timesteps progress_bar timestepssamplestep prev_sampleclampcpupermutenumpy numpy_to_pilr) rrrrrrkwargsimaget model_outputrrr__call__0s 3   zPNDMPipeline.__call__)rrNrT)__name__ __module__ __qualname____doc__r__annotations__rr torchno_gradint Generatorliststrboolrtupler3 __classcell__rrrrr s0  r ) r9modelsr schedulersrutils.torch_utilsrpipeline_utilsrrr rrrrs