biddlmZmZmZmZddlZddlmZddlm Z ddl m Z ddl m Z dd lmZmZe r ddlmcmZd Znd ZGd d eZy))ListOptionalTupleUnionN) UNet2DModel) DDIMScheduler)is_torch_xla_available) randn_tensor)DiffusionPipelineImagePipelineOutputTFceZdZdZdZdedeffd Zej dde de e ejeejfdede d e ed e ed ed e eeffd ZxZS) DDIMPipelinea1 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 schedulerct|tj|j}|j ||y)N)rr)super__init__r from_configconfigregister_modules)selfrr __class__s a/home/cdr/jupyterlab/.venv/lib/python3.12/site-packages/diffusers/pipelines/ddim/pipeline_ddim.pyrzDDIMPipeline.__init__3s9 "--i.>.>?  49= batch_size generatoretanum_inference_stepsuse_clipped_model_output output_type return_dictreturnc t|jjjtra||jjj |jjj|jjjf}nC||jjj g|jjj}t|t r)t||k7rtdt|d|dt|||j|jj} |jj||j|jjD]d} |j| | j } |jj#| | | |||j$} t&sQt)j*f| dz dzj-dd } | j/j1ddd d j3} |d k(r|j5| } |s| fSt7| S) u] 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. eta (`float`, *optional*, defaults to 0.0): Corresponds to parameter eta (η) from the [DDIM](https://huggingface.co/papers/2010.02502) paper. Only applies to the [`~schedulers.DDIMScheduler`], and is ignored in other schedulers. A value of `0` corresponds to DDIM and `1` corresponds to DDPM. 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. use_clipped_model_output (`bool`, *optional*, defaults to `None`): If `True` or `False`, see documentation for [`DDIMScheduler.step`]. If `None`, nothing is passed downstream to the scheduler (use `None` for schedulers which don't support this argument). 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 DDIMPipeline >>> import PIL.Image >>> import numpy as np >>> # load model and scheduler >>> pipe = DDIMPipeline.from_pretrained("fusing/ddim-lsun-bedroom") >>> # run pipeline in inference (sample random noise and denoise) >>> image = pipe(eta=0.0, num_inference_steps=50) >>> # process image to PIL >>> image_processed = image.cpu().permute(0, 2, 3, 1) >>> image_processed = (image_processed + 1.0) * 127.5 >>> image_processed = image_processed.numpy().astype(np.uint8) >>> image_pil = PIL.Image.fromarray(image_processed[0]) >>> # save image >>> image_pil.save("test.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 z/You have passed a list of generators of length z+, but requested an effective batch size of z@. Make sure the batch size matches the length of the generators.)rdevicedtype)rr!rr g?rrpil)images) isinstancerr sample_sizeint in_channelslistlen ValueErrorr _execution_devicer'r set_timesteps progress_bar timestepssamplestep prev_sample XLA_AVAILABLExm mark_stepclampcpupermutenumpy numpy_to_pilr) rrrrr r!r"r# image_shapeimaget model_outputs r__call__zDDIMPipeline.__call__;sB dii&&22C 8   ,,   ,,   ,, K&tyy'7'7'C'CcdiiFVFVFbFbcK i &3y>Z+GA#i.AQR&<'gi  [IdF\F\dhdmdmdsdst $$%89""4>>#;#;< A99UA.55L NN''aCJbnw(k   S''1- ##Aq!Q/557 % %%e,E8O"%00r)r(Ng2Nr)T)__name__ __module__ __qualname____doc__model_cpu_offload_seqrr rtorchno_gradr-rr GeneratorrfloatboolstrrrrE __classcell__)rs@rrr"s #>[>]>U]]_MQ#%37%* k1k1E%//43H"HIJk1 k1 ! k1 #+4. k1c]k1k1 "E) *k1k1rr)typingrrrrrLmodelsr schedulersr utilsr utils.torch_utilsr pipeline_utilsr rtorch_xla.core.xla_modelcore xla_modelr:r9rrrr]sF0/ !'+-C))MME1$E1r