wijddlmZmZmZmZddlZddlmZddlm Z ddl m Z m Z Gdd e Z dS) )ListOptionalTupleUnionN) DDIMScheduler) randn_tensor)DiffusionPipelineImagePipelineOutputceZdZdZdZfdZej dd ed e e ej e ej fd e d ede ede edede eeffdZxZS) 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`]. unetcttj|j}|||dS)N)r scheduler)super__init__r from_configconfigregister_modules)selfrr __class__s v/root/.openclaw/workspace/chatterbox_venv_py311/lib/python3.11/site-packages/diffusers/pipelines/ddim/pipeline_ddim.pyrzDDIMPipeline.__init__)sM "-i.>??  49=====N2pilT batch_size generatoretanum_inference_stepsuse_clipped_model_output output_type return_dictreturnc t|jjjtr4||jjj|jjj|jjjf}n%||jjjg|jjjR}t|t r6t||kr#tdt|d|dt|||j |jj } |j |||j jD]B} || | j} |j | | | |||j} C| dz dzdd } | ddd d } |d kr|| } |s| fSt1| S) uU 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://arxiv.org/abs/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.)r devicedtype)r!r#r r g?rrrr)images) isinstancerr sample_sizeint in_channelslistlen ValueErrorr _execution_devicer)r set_timesteps progress_bar timestepssamplestep prev_sampleclampcpupermutenumpy numpy_to_pilr ) rrr r!r"r#r$r% image_shapeimaget model_outputs r__call__zDDIMPipeline.__call__1sB di&2C 8 8 d  ,  ,  , KK&ty'7'CcdiFVFbccK i & & 3y>>Z+G+Gi#i..ii&iii  [IdF\dhdmdsttt $$%8999""4>#;<<  A99UA..5L N''aCJbnw( ES''1-- ##Aq!Q//5577 %  %%e,,E 8O"%0000r)rNrrNrT)__name__ __module__ __qualname____doc__model_cpu_offload_seqrtorchno_gradr-rr Generatorrfloatboolstrr rrB __classcell__)rs@rrrs  #>>>>>U]__MQ#%37%* h1h1h1E%/43H"HIJh1 h1 ! h1 #+4. h1c]h1h1 "E) *h1h1h1_h1h1h1h1h1rr)typingrrrrrH schedulersrutils.torch_utilsr pipeline_utilsr r rrrrTs0/////////// ''''''------CCCCCCCCB1B1B1B1B1$B1B1B1B1B1r