+h?^SSKJr SSKJr SSKJrJrJrJrJ r SSK r SSK r SSK JrJr SSKJr SSKJr SS KJrJrJrJrJr SS KJr S S KJr S SKJr \"5(a SSK J!s J"r# Sr$OSr$\RJ"\&5r'\("\ RR"SSS55\("\ RR"SSS55S S-r*Sr+\"SS\55r,"SS\\5r-g)) dataclass)ceil)CallableDictListOptionalUnionN) CLIPTextModel CLIPTokenizer)StableDiffusionLoraLoaderMixin)DDPMWuerstchenScheduler) BaseOutput deprecateis_torch_xla_availableloggingreplace_example_docstring) randn_tensor)DiffusionPipeline)WuerstchenPriorTF?gUUUUUU?g a Examples: ```py >>> import torch >>> from diffusers import WuerstchenPriorPipeline >>> prior_pipe = WuerstchenPriorPipeline.from_pretrained( ... "warp-ai/wuerstchen-prior", torch_dtype=torch.float16 ... ).to("cuda") >>> prompt = "an image of a shiba inu, donning a spacesuit and helmet" >>> prior_output = pipe(prompt) ``` cV\rSrSr%Sr\\R\R4\ S'Sr g)WuerstchenPriorPipelineOutput;z Output class for WuerstchenPriorPipeline. Args: image_embeddings (`torch.Tensor` or `np.ndarray`) Prior image embeddings for text prompt image_embeddingsN) __name__ __module__ __qualname____firstlineno____doc__r torchTensornpndarray__annotations____static_attributes__r r/home/james-whalen/.local/lib/python3.13/site-packages/diffusers/pipelines/wuerstchen/pipeline_wuerstchen_prior.pyrr;s!ELL"**455r,rc%^\rSrSrSrSrSrSr/SQrSS/r S-S\ S\ S\ S\ S \S \S \S S 4U4SjjjrSrS.S\\R&S\\R&4SjjrS/Sjr\S5r\S5r\S5r\R4"5\"\5S SSSS SS S S SS S SSS S/4S\\\\\4S\ S \ S!\ S"\\S#\S$\\\\\4S\\R&S\\R&S%\\ S&\\\RB\\RB4S\\R&S'\\S(\"S)\\#\ \ \$/S 4S*\\4 S+jj55r%S,r&U=r'$)0WuerstchenPriorPipelineIaQ Pipeline for generating image prior for Wuerstchen. This model inherits from [`DiffusionPipeline`]. Check the superclass documentation for the generic methods the library implements for all the pipelines (such as downloading or saving, running on a particular device, etc.) The pipeline also inherits the following loading methods: - [`~loaders.StableDiffusionLoraLoaderMixin.load_lora_weights`] for loading LoRA weights - [`~loaders.StableDiffusionLoraLoaderMixin.save_lora_weights`] for saving LoRA weights Args: prior ([`Prior`]): The canonical unCLIP prior to approximate the image embedding from the text embedding. text_encoder ([`CLIPTextModelWithProjection`]): Frozen text-encoder. tokenizer (`CLIPTokenizer`): Tokenizer of class [CLIPTokenizer](https://huggingface.co/docs/transformers/v4.21.0/en/model_doc/clip#transformers.CLIPTokenizer). scheduler ([`DDPMWuerstchenScheduler`]): A scheduler to be used in combination with `prior` to generate image embedding. latent_mean ('float', *optional*, defaults to 42.0): Mean value for latent diffusers. latent_std ('float', *optional*, defaults to 1.0): Standard value for latent diffusers. resolution_multiple ('float', *optional*, defaults to 42.67): Default resolution for multiple images generated. prior text_encoderztext_encoder->prior)latentstext_encoder_hidden_statesnegative_prompt_embeds tokenizer scheduler latent_mean latent_stdresolution_multiplereturnNcf>[TU]5 URUUUUS9 URXVUS9 g)N)r6r2r1r7)r8r9r:)super__init__register_modulesregister_to_config) selfr6r2r1r7r8r9r: __class__s r-r> WuerstchenPriorPipeline.__init__lsJ  %  #Pc  r,cUc [XX2S9nO>::# )K)22N(77N"nnVYW[n\ffO$$R(N,@,@,DDU[[NN $~~::#At~~'F'F'JR'O$OP  778 ,Q"03TT^^5T5T3T0T!U!/3TT^^5T5T3T0T!U"&"3"3!!&).:K:KF:S#4# 0AAM%((t/@/@/F/Fv(V %778MST7U ! ).I&!#z 1 fT/%::UVZ[jVkUlmV ~Q(OS11!0 1 s?33 )/)::J3K_J`ax/ |<33 !0 >>$>>::# *L:>9J9J&&))&1,B]B]B`B`agBh:K: 6&P%a%a " &,2215G%;%>%>TEVEVE\E\ek%>%l "%;%B%B1F[]^%_ "%;%@%@Acelnp%q "44r,cUbUb[SUSUS35eUcUc [S5eUbA[U[5(d,[U[5(d[S[ U535eUbUb[SUSUS35eUbCUb@UR UR :wa&[SUR S UR S 35e[U[ 5(d[S [ U5S 35eg) NzCannot forward both `prompt`: z and `prompt_embeds`: z2. Please make sure to only forward one of the two.zeProvide either `prompt` or `prompt_embeds`. Cannot leave both `prompt` and `prompt_embeds` undefined.z2`prompt` has to be of type `str` or `list` but is z'Cannot forward both `negative_prompt`: z and `negative_prompt_embeds`: zu`prompt_embeds` and `negative_prompt_embeds` must have the same shape when passed directly, but got: `prompt_embeds` z != `negative_prompt_embeds` rZz5'num_inference_steps' must be of type 'int', but got zo In Case you want to provide explicit timesteps, please use the 'timesteps' argument.)rIr[r\r]rgrHintrh)rArmrnnum_inference_stepsrlrNr5s r- check_inputs$WuerstchenPriorPipeline.check_inputss[  -";08N}o^00 ^ 5w  FC)@)@TZ\`IaIaQRVW]R^Q_`a a  &+A+M9/9JK*++]_   $)?)K""&<&B&BB --:-@-@,AB.445Q8 -s33GM`HaGbcpq 4r,cUR$N_guidance_scalerAs r-guidance_scale&WuerstchenPriorPipeline.guidance_scales###r,c URS:$)Nrrrs r-rl3WuerstchenPriorPipeline.do_classifier_free_guidances##a''r,cUR$r)_num_timestepsrs r- num_timesteps%WuerstchenPriorPipeline.num_timestepss"""r,i<g @rrQTr3rmheightwidthr} timestepsrrnrkrE output_type return_dictcallback_on_step_end"callback_on_step_end_tensor_inputsc  ^URSS5nURSS5nUb [SSS5 Ub [SSS5 UbX[U4SjU55(d>[STRS UVs/sHnUTR;dMUPM sn35eTR nUTlUb[U[5(aS nO3Ub![U[5(a [U5nOURS nUbF[U[5(d1[U[5(aU/nO[S [U5S 35eTR(aIUbF[U[5(d1[U[5(aU/nO[S[U5S 35eTRUUUTRUU S9 TR!UUU TRUUU S9upU b["R$"X/5OUnUR&n[)UTR*R,- 5n[)UTR*R,- 5nTR.R*R0nU U-UUU4nUb<TR2R5UUS9 TR2R6n[U5nO0TR2R5UUS9 TR2R6nTR9UUUXTR25n [USS5Tl[=TR?USS55GHunnURAU RCS 55REU5nTR/TR(a["R$"U /S-5OU TR(a["R$"U/S-5OUUS9n TR(a6U RGS5un!n"["RH"U"U!TRJ5n TR2RMU UU U S9RNn Ub\0n#UHn[Q5UU#U'M U"TUUU#5n$U$RSU 5n U$RSU5nU$RSU 5n Ub-UU-S :Xa$U[STR2SS 5-n%U"U%UU 5 [T(dGM[VRX"5 GM U TR*RZ-TR*R\- n TR_5 U S:Xa,U Ra5Rc5Re5n U(dU 4$[gU 5$s snf)a: Function invoked when calling the pipeline for generation. Args: prompt (`str` or `List[str]`): The prompt or prompts to guide the image generation. height (`int`, *optional*, defaults to 1024): The height in pixels of the generated image. width (`int`, *optional*, defaults to 1024): The width in pixels of the generated image. num_inference_steps (`int`, *optional*, defaults to 60): 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. guidance_scale (`float`, *optional*, defaults to 8.0): Guidance scale as defined in [Classifier-Free Diffusion Guidance](https://huggingface.co/papers/2207.12598). `decoder_guidance_scale` is defined as `w` of equation 2. of [Imagen Paper](https://huggingface.co/papers/2205.11487). Guidance scale is enabled by setting `decoder_guidance_scale > 1`. Higher guidance scale encourages to generate images that are closely linked to the text `prompt`, usually at the expense of lower image quality. negative_prompt (`str` or `List[str]`, *optional*): The prompt or prompts not to guide the image generation. Ignored when not using guidance (i.e., ignored if `decoder_guidance_scale` is less than `1`). prompt_embeds (`torch.Tensor`, *optional*): Pre-generated text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not provided, text embeddings will be generated from `prompt` input argument. negative_prompt_embeds (`torch.Tensor`, *optional*): Pre-generated negative text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not provided, negative_prompt_embeds will be generated from `negative_prompt` input argument. num_images_per_prompt (`int`, *optional*, defaults to 1): The number of images to generate per prompt. generator (`torch.Generator` or `List[torch.Generator]`, *optional*): One or a list of [torch generator(s)](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 will ge generated by sampling using the supplied random `generator`. output_type (`str`, *optional*, defaults to `"pil"`): The output format of the generate image. Choose between: `"pil"` (`PIL.Image.Image`), `"np"` (`np.array`) or `"pt"` (`torch.Tensor`). return_dict (`bool`, *optional*, defaults to `True`): Whether or not to return a [`~pipelines.ImagePipelineOutput`] instead of a plain tuple. callback_on_step_end (`Callable`, *optional*): A function that calls at the end of each denoising steps during the inference. The function is called with the following arguments: `callback_on_step_end(self: DiffusionPipeline, step: int, timestep: int, callback_kwargs: Dict)`. `callback_kwargs` will include a list of all tensors as specified by `callback_on_step_end_tensor_inputs`. callback_on_step_end_tensor_inputs (`List`, *optional*): The list of tensor inputs for the `callback_on_step_end` function. The tensors specified in the list will be passed as `callback_kwargs` argument. You will only be able to include variables listed in the `._callback_tensor_inputs` attribute of your pipeline class. Examples: Returns: [`~pipelines.WuerstchenPriorPipelineOutput`] or `tuple` [`~pipelines.WuerstchenPriorPipelineOutput`] if `return_dict` is True, otherwise a `tuple`. When returning a tuple, the first element is a list with the generated image embeddings. callbackNcallback_stepsz1.0.0zhPassing `callback` as an input argument to `__call__` is deprecated, consider use `callback_on_step_end`znPassing `callback_steps` as an input argument to `__call__` is deprecated, consider use `callback_on_step_end`c3@># UHoTR;v M g7fr)_callback_tensor_inputs).0krAs r- 3WuerstchenPriorPipeline.__call__..sF 7Y!-- -7Ysz2`callback_on_step_end_tensor_inputs` has to be in z , but found rrz2'prompt' must be of type 'list' or 'str', but got rZz;'negative_prompt' must be of type 'list' or 'str', but got )rNr5)rmrFrkrlrnrNr5)rrF)rFrVr)rc) model_outputtimestepsamplerEr3r4r5orderr()4poprallrIr_execution_devicerr[r\r]r^rHrhrgrlr~ryr&catrGrconfigr:r1c_inr7 set_timestepsrrLr enumerate progress_barexpandsizerJchunklerprstep prev_samplelocalsgetattr XLA_AVAILABLExm mark_stepr8r9maybe_free_model_hookscpufloatnumpyr)&rArmrrr}rrrnrNr5rkrEr3rrrrkwargsrrrrFror4rG latent_height latent_width num_channelseffnet_features_shapeitratiopredicted_image_embeddingpredicted_image_embedding_text predicted_image_embedding_uncondcallback_kwargscallback_outputsstep_idxs&` r-__call__ WuerstchenPriorPipeline.__call__!sl::j$/$4d;   z   %  A  . 9#F 7YF C C DTEaEaDbbn|^pH|^vwbckokGkGbGpq|^pHoIJ  ''-  *VS"9"9J  Jvt$<$<VJ&,,Q/J  j&>&>&#&& "TUYZ`UaTbbc dee  + +*:ot3T3Tos33'6&7O#UVZ[jVkUllmn      , ,'#9  150B0B"7(,(H(H+'#91C1 - CYBdEII}= >jw # +00Vdkk&E&EEF EDKK$C$CCD zz((-- !6!C\S`bn o  NN ( (9V ( L00I"%i.  NN ( ()VXn)o&#N(:a(? CC1g.} UAZDKK333dkk6L6LL ##% $ kkm))+113G: ,W55KpHs :U?U?)rr)gE@rg(\UE@)NNNN)NN)(r!r"r#r$r% unet_nametext_encoder_namemodel_cpu_offload_seqr_lora_loadable_modulesr r rrrr>rLrr&r'ryr~propertyrrlrno_gradrEXAMPLE_DOC_STRINGr r\rr| Generatorboolrrrr+ __classcell__)rBs@r-r/r/Is8I&1a%~6"%*   $   +     #    ,  049=]5  -]5!) 6]5J#'R$$((## ]]_1237#%!% #;?049=/0MQ*.%) KO9B #m6sDI~./m6m6 m6 ! m6 ; m6m6"%T#Y"78m6  -m6!) 6m6 (}m6E%//43H"HIJm6%,,'m6c]m6m6 'xc40@$0F'GH!m6"-1I#m63m6r,r/). dataclassesrmathrtypingrrrrr rr(r& transformersr r loadersr schedulersrutilsrrrrrutils.torch_utilsrpipeline_utilsrmodeling_wuerstchen_priorrtorch_xla.core.xla_modelcore xla_modelrr get_loggerr!rcr]linspaceDEFAULT_STAGE_C_TIMESTEPSrrr/r r,r-rs"88 551ff-.6))MM   H %!S%!<=R[[QVX[]_E`@abcbd@ee    6J 6  6G6/1OG6r,