3j0SSKJr SSKrSSKJr SSKJr SSKJrJ r J r SSK J r SS K JrJr \"5(a SSKJs Jr S rOS r\ R*"\5rS r"S S\5rg))CallableN) UNet2DModel)CMStochasticIterativeScheduler)is_torch_xla_availableloggingreplace_example_docstring) randn_tensor)DiffusionPipelineImagePipelineOutputTFa Examples: ```py >>> import torch >>> from diffusers import ConsistencyModelPipeline >>> device = "cuda" >>> # Load the cd_imagenet64_l2 checkpoint. >>> model_id_or_path = "openai/diffusers-cd_imagenet64_l2" >>> pipe = ConsistencyModelPipeline.from_pretrained(model_id_or_path, torch_dtype=torch.float16) >>> pipe.to(device) >>> # Onestep Sampling >>> image = pipe(num_inference_steps=1).images[0] >>> image.save("cd_imagenet64_l2_onestep_sample.png") >>> # Onestep sampling, class-conditional image generation >>> # ImageNet-64 class label 145 corresponds to king penguins >>> image = pipe(num_inference_steps=1, class_labels=145).images[0] >>> image.save("cd_imagenet64_l2_onestep_sample_penguin.png") >>> # Multistep sampling, class-conditional image generation >>> # Timesteps can be explicitly specified; the particular timesteps below are from the original GitHub repo: >>> # https://github.com/openai/consistency_models/blob/main/scripts/launch.sh#L77 >>> image = pipe(num_inference_steps=None, timesteps=[22, 0], class_labels=145).images[0] >>> image.save("cd_imagenet64_l2_multistep_sample_penguin.png") ``` c^\rSrSrSrSrS\S\SS4U4SjjrSSjr SS \ RS \ 4S jjr SS jrS r\ R "5\"\5SS\S\ R\\-\-S-S\S\\S\ R*\\ R*-S-S\ RS-S \ S-S\S\\\\ R/S4S-S\4Sjj55rSrU=r$)ConsistencyModelPipelineCa: Pipeline for unconditional or class-conditional image generation. This model inherits from [`DiffusionPipeline`]. Check the superclass documentation for the generic methods implemented for all pipelines (downloading, saving, running on a particular device, etc.). Args: unet ([`UNet2DModel`]): A `UNet2DModel` to denoise the encoded image latents. scheduler ([`SchedulerMixin`]): A scheduler to be used in combination with `unet` to denoise the encoded image latents. Currently only compatible with [`CMStochasticIterativeScheduler`]. unet schedulerreturnNcP>[TU]5 URUUS9 SUlg)N)rr)super__init__register_modulessafety_checker)selfrr __class__s |/home/wildlama/miniconda3/lib/python3.13/site-packages/diffusers/pipelines/consistency_models/pipeline_consistency_models.pyr!ConsistencyModelPipeline.__init__Ts1    #c XX44n [U[5(a*[U5U:wa[S[U5SUS35eUc [ XXeS9nOUR XeS9nXR R-nU$)Nz/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.) generatordevicedtype)r r!) isinstancelistlen ValueErrorr torinit_noise_sigma) r batch_size num_channelsheightwidthr!r rlatentsshapes rprepare_latents(ConsistencyModelPipeline.prepare_latents^s69 i & &3y>Z+GA#i.AQR&<'gi  ?"5fZGjjj30O0OSaefSfGGWX(), Tg &rr(rFrNrOrr, return_dictcallbackrQc URRRn URn UR X4XaX5 UR UURRR U U URRU UUS9n URXUS9nUb;URRXLS9 URRn[U5nO1URRU5 URRnURUS9n[U5HunnURRU U5nURUUUSS9SnURR!UUXS 9Sn UR#5 U bX-S:Xa U "UUU 5 [$(dM[&R("5 M SSS5 UR+XS 9nUR-5 U(dU4$[/US 9$!,(df  N@=f) a Args: batch_size (`int`, *optional*, defaults to 1): The number of images to generate. class_labels (`torch.Tensor` or `list[int]` or `int`, *optional*): Optional class labels for conditioning class-conditional consistency models. Not used if the model is not class-conditional. num_inference_steps (`int`, *optional*, defaults to 1): The number of denoising steps. More denoising steps usually lead to a higher quality image at the expense of slower inference. timesteps (`list[int]`, *optional*): Custom timesteps to use for the denoising process. If not defined, equal spaced `num_inference_steps` timesteps are used. Must be in descending order. generator (`torch.Generator`, *optional*): A [`torch.Generator`](https://pytorch.org/docs/stable/generated/torch.Generator.html) to make generation deterministic. latents (`torch.Tensor`, *optional*): Pre-generated noisy latents sampled from a Gaussian distribution, to be used as inputs for image generation. Can be used to tweak the same generation with different prompts. If not provided, a latents tensor is generated by sampling using the supplied random `generator`. 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. callback (`Callable`, *optional*): A function that calls every `callback_steps` steps during inference. The function is called with the following arguments: `callback(step: int, timestep: int, latents: torch.Tensor)`. callback_steps (`int`, *optional*, defaults to 1): The frequency at which the `callback` function is called. If not specified, the callback is called at every step. Examples: 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. )r(r)r*r+r!r rr,)rFN)rOr )totalF)rFrUr)r)r1)images)rr@ sample_size_execution_devicerSr. in_channelsr!rGr set_timestepsrOr$ progress_bar enumeratescale_model_inputstepupdate XLA_AVAILABLExm mark_stepr<maybe_free_model_hooksr )rr(rFrNrOrr,r1rUrVrQrPr r0r^it scaled_sample model_outputimages r__call__!ConsistencyModelPipeline.__call__sl99##//'' -'xh%%!))55))//&  00R^0_   NN ( (9 ( L00I"%i.  NN ( ()< =00I  %8  9\!),1 $ @ @ K #yy bgyhijk ,,\1f,Z[\]##%'A,>!,CQ6* =LLN-: &&v&G ##%8O"%001: 9sBG<)G<< H )r)N)r5) r6Nr6NNNr5TNr6)__name__ __module__ __qualname____firstlineno____doc__model_cpu_offload_seqrrrr.rBTensorstrr<rGrSno_gradr EXAMPLE_DOC_STRINGrDr# Generatorboolrrl__static_attributes__ __classcell__)rs@rrrCsa ##[#5S#X\#$ 3( . ]]_12>B#$#DH'+"' DHm1m1llT#Y.4t;m1! m1 9 m1 ??T%//%::TA m1$m14Zm1m1Cell3T9:TAm1m13m1rr)typingrrBmodelsr schedulersrutilsrrr utils.torch_utilsr pipeline_utilsr r torch_xla.core.xla_modelcore xla_modelrdrc get_loggerrnrKrwrrrrsa !8OO-C))MM   H %>W10W1r