biddlmZmZmZmZddlZddlmZddlm Z ddl m Z ddl m Z dd lmZmZe r ddlmcmZd Znd ZGd d eZy))ListOptionalTupleUnionN) UNet2DModel) DDPMScheduler)is_torch_xla_available) randn_tensor)DiffusionPipelineImagePipelineOutputTFceZdZdZdZdedeffd Zej d de de e ejeejfde de ed ed e eeff d ZxZS) DDPMPipelinea1 Pipeline for 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 ([`SchedulerMixin`]): A scheduler to be used in combination with `unet` to denoise the encoded image. Can be one of [`DDPMScheduler`], or [`DDIMScheduler`]. unet schedulercHt||j||y)N)rr)super__init__register_modules)selfrr __class__s a/home/cdr/jupyterlab/.venv/lib/python3.12/site-packages/diffusers/pipelines/ddpm/pipeline_ddpm.pyrzDDPMPipeline.__init__4s!  49= batch_size generatornum_inference_steps output_type return_dictreturnct|jjjtra||jjj |jjj|jjjf}nC||jjj g|jjj}|j jdk(r>t|||jj}|j|j }n-t|||j |jj}|jj||j|jjD]b}|j||j} |jj!| |||j"}t$sOt'j(d|dz dzj+dd}|j-j/ddd dj1}|d k(r|j3|}|s|fSt5| S) aa The call function to the pipeline for generation. Args: batch_size (`int`, *optional*, defaults to 1): The number of images to generate. generator (`torch.Generator`, *optional*): A [`torch.Generator`](https://pytorch.org/docs/stable/generated/torch.Generator.html) to make generation deterministic. num_inference_steps (`int`, *optional*, defaults to 1000): The number of denoising steps. More denoising steps usually lead to a higher quality image at the expense of slower inference. output_type (`str`, *optional*, defaults to `"pil"`): The output format of the generated image. Choose between `PIL.Image` or `np.array`. return_dict (`bool`, *optional*, defaults to `True`): Whether or not to return a [`~pipelines.ImagePipelineOutput`] instead of a plain tuple. Example: ```py >>> from diffusers import DDPMPipeline >>> # load model and scheduler >>> pipe = DDPMPipeline.from_pretrained("google/ddpm-cat-256") >>> # run pipeline in inference (sample random noise and denoise) >>> image = pipe().images[0] >>> # save image >>> image.save("ddpm_generated_image.png") ``` Returns: [`~pipelines.ImagePipelineOutput`] or `tuple`: If `return_dict` is `True`, [`~pipelines.ImagePipelineOutput`] is returned, otherwise a `tuple` is returned where the first element is a list with the generated images mps)rdtype)rdevicer#)rr g?rrpil)images) isinstancerconfig sample_sizeint in_channelsr$typer r#tor set_timesteps progress_bar timestepssamplestep prev_sample XLA_AVAILABLExm mark_stepclampcpupermutenumpy numpy_to_pilr) rrrrrr image_shapeimaget model_outputs r__call__zDDPMPipeline.__call__8s^ dii&&22C 8   ,,   ,,   ,, K&tyy'7'7'C'CcdiiFVFVFbFbcK ;;  u $  YEHHT[[)E  $++]a]f]f]l]lmE $$%89""4>>#;#;< A99UA.55LNN'' a)'T``E  S''1- ##Aq!Q/557 % %%e,E8O"%00r)r%Nir&T)__name__ __module__ __qualname____doc__model_cpu_offload_seqrr rtorchno_gradr+rr GeneratorrstrboolrrrA __classcell__)rs@rrr#s #>[>]>U]]_MQ#'%* T1T1E%//43H"HIJT1! T1 c] T1  T1 "E) *T1T1rr)typingrrrrrGmodelsr schedulersr utilsr utils.torch_utilsr pipeline_utilsr rtorch_xla.core.xla_modelcore xla_modelr6r5rrrrWsF 0/ !'+-C))MMj1$j1r