3jdSSKJr SSKrSSKrSSKJrJr SSKrSSK r SSK J r J r J r Jr SSKJr SSKJr SSKJrJr SS KJr SS KJrJrJr SS KJr S S KJr SSK J!r! \"5(a SSK"J#s J$r% Sr&OSr&\RN"\(5r)Sr*SSjr+SSSjjr,"SS\5r-g)) annotationsN)AnyCallable) ByT5Tokenizer"Qwen2_5_VLForConditionalGenerationQwen2TokenizerT5EncoderModel)AdaptiveProjectedMixGuidance)VaeImageProcessor)AutoencoderKLHunyuanImageHunyuanImageTransformer2DModel)FlowMatchEulerDiscreteScheduler)is_torch_xla_availableloggingreplace_example_docstring) randn_tensor)DiffusionPipeline)HunyuanImagePipelineOutputTFa Examples: ```py >>> import torch >>> from diffusers import HunyuanImagePipeline >>> pipe = HunyuanImagePipeline.from_pretrained( ... "hunyuanvideo-community/HunyuanImage-2.1-Diffusers", torch_dtype=torch.bfloat16 ... ) >>> pipe.to("cuda") >>> prompt = "A cat holding a sign that says hello world" >>> # Depending on the variant being used, the pipeline call will slightly vary. >>> # Refer to the pipeline documentation for more details. >>> image = pipe(prompt, negative_prompt="", num_inference_steps=50).images[0] >>> image.save("hunyuanimage.png") ``` c/nSnSnSnSn[R"X 5n[R"X05n[R"X@5n[R"XP5n URU5 URU5 URU5 URU 5 U(a+SRUV s/sH n SU S3PM sn 5S-n U $Sn U $s sn f) a  Extract text enclosed in quotes for glyph rendering. Finds text in single quotes, double quotes, and Chinese quotes, then formats it for byT5 processing. Args: prompt: Input text prompt Returns: Formatted glyph text string or None if no quoted text found z \'(.*?)\'z \"(.*?)\"u ‘(.*?)’u “(.*?)”z. zText ""N)refindallextendjoin) prompttext_prompt_textspattern_quote_singlepattern_quote_doublepattern_quote_chinese_singlepattern_quote_chinese_doublematches_quote_singlematches_quote_doublematches_quote_chinese_singlematches_quote_chinese_doubletextglyph_text_formatteds q/home/wildlama/miniconda3/lib/python3.13/site-packages/diffusers/pipelines/hunyuan_image/pipeline_hunyuanimage.pyextract_glyph_textr+@s''#1 #1 ::&:C::&:C#%::.J#S #%::.J#S 12129:9:#yyGX)YGXtF4&*:GX)YZ]aa  $  *Zs=Cc UbUb [S5eUbS[[R"UR5R R 55;nU(d[SURS35eUR"S X2S.UD6 URn[U5nX14$UbS[[R"UR5R R 55;nU(d[SURS35eUR"S XBS.UD6 URn[U5nX14$UR"U4S U0UD6 URnX14$) a Calls the scheduler's `set_timesteps` method and retrieves timesteps from the scheduler after the call. Handles custom timesteps. Any kwargs will be supplied to `scheduler.set_timesteps`. Args: scheduler (`SchedulerMixin`): The scheduler to get timesteps from. num_inference_steps (`int`): The number of diffusion steps used when generating samples with a pre-trained model. If used, `timesteps` must be `None`. device (`str` or `torch.device`, *optional*): The device to which the timesteps should be moved to. If `None`, the timesteps are not moved. timesteps (`list[int]`, *optional*): Custom timesteps used to override the timestep spacing strategy of the scheduler. If `timesteps` is passed, `num_inference_steps` and `sigmas` must be `None`. sigmas (`list[float]`, *optional*): Custom sigmas used to override the timestep spacing strategy of the scheduler. If `sigmas` is passed, `num_inference_steps` and `timesteps` must be `None`. Returns: `tuple[torch.Tensor, int]`: A tuple where the first element is the timestep schedule from the scheduler and the second element is the number of inference steps. zYOnly one of `timesteps` or `sigmas` can be passed. Please choose one to set custom values timestepszThe current scheduler class zx's `set_timesteps` does not support custom timestep schedules. Please check whether you are using the correct scheduler.)r-devicesigmaszv's `set_timesteps` does not support custom sigmas schedules. Please check whether you are using the correct scheduler.)r/r.r.) ValueErrorsetinspect signature set_timesteps parameterskeys __class__r-len) schedulernum_inference_stepsr.r-r/kwargsaccepts_timesteps accept_sigmass r*retrieve_timestepsr?es}>!3tuu'3w/@/@AXAX/Y/d/d/i/i/k+ll .y/B/B.CDab  M)MfM'' !)n  ))   C(9(9):Q:Q(R(](](b(b(d$ee .y/B/B.CD_`  GvGG'' !)n  ))  3MFMfM''  ))cP^\rSrSrSrSrSS/rSS/rSSU4S jjjrSSS jjr SSS jjr S S!S jjr S"Sjr S#Sjr \S5r\S5r\S5r\S5r\R("5\"\5SSSSSSSS SSSSSSSSSSSSSSS/4S$Sjj55rSrU=r$)%HunyuanImagePipelineaZ The HunyuanImage pipeline for text-to-image generation. Args: transformer ([`HunyuanImageTransformer2DModel`]): Conditional Transformer (MMDiT) architecture to denoise the encoded image latents. scheduler ([`FlowMatchEulerDiscreteScheduler`]): A scheduler to be used in combination with `transformer` to denoise the encoded image latents. vae ([`AutoencoderKLHunyuanImage`]): Variational Auto-Encoder (VAE) Model to encode and decode images to and from latent representations. text_encoder ([`Qwen2.5-VL-7B-Instruct`]): [Qwen2.5-VL-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-VL-7B-Instruct), specifically the [Qwen2.5-VL-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-VL-7B-Instruct) variant. tokenizer (`Qwen2Tokenizer`): Tokenizer of class [Qwen2Tokenizer]. text_encoder_2 ([`T5EncoderModel`]): [T5EncoderModel](https://huggingface.co/docs/transformers/en/model_doc/t5#transformers.T5EncoderModel) variant. tokenizer_2 (`ByT5Tokenizer`): Tokenizer of class [ByT5Tokenizer] guider ([`AdaptiveProjectedMixGuidance`]): [AdaptiveProjectedMixGuidance]to be used to guide the image generation. ocr_guider ([`AdaptiveProjectedMixGuidance`], *optional*): [AdaptiveProjectedMixGuidance] to be used to guide the image generation when text rendering is needed. z.text_encoder->text_encoder_2->transformer->vaelatents prompt_embeds ocr_guiderguiderNc 8>[T U]5 URUUUUUUUUU S9 [USS5(a URR R OSUl[URS9Ul SUl SUl SUl SUl S Ulg) N) vae text_encoder tokenizertext_encoder_2 tokenizer_2 transformerr:rGrFrI )vae_scale_factor<|im_start|>system Describe the image by detailing the color, shape, size, texture, quantity, text, spatial relationships of the objects and background:<|im_end|> <|im_start|>user {}<|im_end|>"@)super__init__register_modulesgetattrrIconfigspatial_compression_ratiorPr image_processortokenizer_max_lengthtokenizer_2_max_lengthprompt_template_encode prompt_template_encode_start_idxdefault_sample_size) selfr:rIrJrKrLrMrNrGrFr8s r*rWHunyuanImagePipeline.__init__s  %)##!  NUUY[`bfMgMg I Imo0$BWBWX$(!&)#'l#02-#% r@c U=(d URnU=(d URn[U[5(aU/OUnUV s/sHoR U 5PM n n U"XU-SSSS9R U5n U"U R U RSS9n U RU S-*nUSS2US24nU RSS2US24nUR XTS9nUR US9nX4$s sn f) N max_lengthTpt)repadding truncationreturn_tensors) input_idsattention_maskoutput_hidden_statesrdtyper.r.) _execution_devicern isinstancestrformattorjrk hidden_states)rbrKrJrr.rnr]templatedrop_idxhidden_state_skip_layeretxt txt_tokensencoder_hidden_statesrEencoder_attention_masks r*_get_qwen_prompt_embeds,HunyuanImagePipeline._get_qwen_prompt_embedss1411+++'44&&+126aq!62 8;\^bsw "V* !- **%44!%!  .;;>UXY>Y > ^=> >  +#   "V* % **%44::<   &((u(D !+!:!:!=!=V!=!L44r@rc U=(d URnUcS/U-n[U[5(aU/OUnUcIURURUR UUUR URURS9upVUGc/n /n UV s/sHn [U 5PM n n U Hn U cq[R"SURURRR4US9n[R"SUR4U[R S9nO3UR#UR$URU UURS9upU R'U5 U R'U5 M [R("U SS9n[R("U SS9nUR*unnnUR-SUS5nUR/X4-US 5nUR-SUS5nUR/X4-U5nUR*unnnUR-SUS5nUR/X4-US 5nUR-SUS5nUR/X4-U5nXVXx4$s sn f) a> Args: prompt (`str` or `list[str]`, *optional*): prompt to be encoded device: (`torch.device`): torch device batch_size (`int`): batch size of prompts, defaults to 1 num_images_per_prompt (`int`): number of images that should be generated per prompt prompt_embeds (`torch.Tensor`, *optional*): Pre-generated text embeddings. If not provided, text embeddings will be generated from `prompt` input argument. prompt_embeds_mask (`torch.Tensor`, *optional*): Pre-generated text mask. If not provided, text mask will be generated from `prompt` input argument. prompt_embeds_2 (`torch.Tensor`, *optional*): Pre-generated glyph text embeddings from ByT5. If not provided, will be generated from `prompt` input argument using self.tokenizer_2 and self.text_encoder_2. prompt_embeds_mask_2 (`torch.Tensor`, *optional*): Pre-generated glyph text mask from ByT5. If not provided, will be generated from `prompt` input argument using self.tokenizer_2 and self.text_encoder_2. )rKrJrr.r]rvrwrror.rn)rKrJrr.r]r)dim)rprqrrr~rKrJr]r_r`r+torchzerosr^rLrZd_modelint64rrMappendcatshaperepeatview)rbrr. batch_sizenum_images_per_promptrEprompt_embeds_maskprompt_embeds_2prompt_embeds_mask_2prompt_embeds_2_listprompt_embeds_mask_2_listp glyph_texts glyph_textglyph_text_embedsglyph_text_embeds_mask_seq_len seq_len_2s r* encode_prompt"HunyuanImagePipeline.encode_prompt(sD1411 >TJ&F'44&&  040L0L..!..%)%>%>44>>1M1 -M  "#% (* %:@A&Q-a0&KA) %(- D779L9L9S9S9[9[\ek)%.3[[D778u{{.*AE@\@\"&"2"2%)%8%8)%-1-H-H A]A=%%++,=>)001GH%*($ii(SUVW3889[]fg/WWIBsI&c *^UTRS--S:wdUTRS--S:wa,[RSTRS-SUSUS35 U bW[U4SjU 55(d=[ STR S U Vs/sHoTR ;dMUPM sn35eUbUb[ S US US 35eUcUc [ S 5eUbA[ U[5(d,[ U[5(d[ S[U535eUbUb[ SUSUS 35eUbUc [ S5eUbUc [ S5eUcU c [ S5eU bU c [ S5eU bU c [ S5eggs snf)Nrrz-`height` and `width` have to be divisible by z but are z and z(. Dimensions will be resized accordinglyc3@># UHoTR;v M g7fN)_callback_tensor_inputs).0krbs r* 4HunyuanImagePipeline.check_inputs..sF 7Y!-- -7Ysz2`callback_on_step_end_tensor_inputs` has to be in z , but found zCannot 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`: zIf `prompt_embeds` are provided, `prompt_embeds_mask` also have to be passed. Make sure to generate `prompt_embeds_mask` from the same text encoder that was used to generate `prompt_embeds`.zIf `negative_prompt_embeds` are provided, `negative_prompt_embeds_mask` also have to be passed. Make sure to generate `negative_prompt_embeds_mask` from the same text encoder that was used to generate `negative_prompt_embeds`.ziProvide either `prompt` or `prompt_embeds_2`. Cannot leave both `prompt` and `prompt_embeds_2` undefined.zIf `prompt_embeds_2` are provided, `prompt_embeds_mask_2` also have to be passed. Make sure to generate `prompt_embeds_mask_2` from the same text encoder that was used to generate `prompt_embeds_2`.zIf `negative_prompt_embeds_2` are provided, `negative_prompt_embeds_mask_2` also have to be passed. Make sure to generate `negative_prompt_embeds_mask_2` from the same text encoder that was used to generate `negative_prompt_embeds_2`.) rPloggerwarningallr1rrqrrrtype)rbrheightwidthnegative_promptrEnegative_prompt_embedsrnegative_prompt_embeds_maskrrnegative_prompt_embeds_2negative_prompt_embeds_mask_2"callback_on_step_end_tensor_inputsrs` r* check_inputs!HunyuanImagePipeline.check_inputss T**Q. /1 4AVAVYZAZ8[_`8` NN?@U@UXY@Y?ZZcdjckkpqvpwx`a  . 9#F 7YF C C DTEaEaDbbn|^pH|^vwkokGkGbGpq|^pHoIJ   -";08N}o^00 ^ 5w  FC)@)@TZ\`IaIaQRVW]R^Q_`a a  &+A+M9/9JK*++]_   $);)CQ  " -2M2Uu  >o5{   &+?+GY  $ /4Q4Y} 5Z /OpHs F%Fc $[U5UR-n[U5UR-nXX44n UbURXeS9$[U[5(a*[ U5U:wa[ S[ U5SUS35e[XXeS9nU$)Nrz/You have passed a list of generators of length z+, but requested an effective batch size of z@. Make sure the batch size matches the length of the generators.) generatorr.rn)intrPrtrqrr9r1r) rbrnum_channels_latentsrrrnr.rrDrs r*prepare_latents$HunyuanImagePipeline.prepare_latentssV 5 55E d3336A  ::V:9 9 i & &3y>Z+GA#i.AQR&<'gi  u&Vr@cUR$r)_attention_kwargsrbs r*attention_kwargs%HunyuanImagePipeline.attention_kwargs%%%r@cUR$r)_num_timestepsrs r* num_timesteps"HunyuanImagePipeline.num_timestepss"""r@cUR$r)_current_timesteprs r*current_timestep%HunyuanImagePipeline.current_timesteprr@cUR$r) _interruptrs r* interruptHunyuanImagePipeline.interrupts r@2g @pilTc|U=(d URUR-nU=(d URUR-nURUUUUU U U UUUUUUS9 UUlSUlSUlUb[ U[5(aSnO3Ub![ U[5(a [U5nOU RSnURnURUU U UUUUUS9upnnU RURR5n URURR5n[ R""US:H5(dUR$b UR$nO#UR&b UR&nO [)SS9nUR*(auUR,S:aeURUU UUUUUUS9un nnnU RURR5n URURR5nURR.R0nUR3UU-UUUU RUU U S9n Uc[4R6"S S US-5SS OUn[9UR:UUUS 9unn[=[U5XPR:R>-- S5n[U5Ul URR.RB(aUc [ES 5eURR.RB(a?[ RF"U/U RS-URRUS9S-nOSnURHc0UlUR:RKS5 URMUS9n[OU5GH%un n!URP(aMU!UlU!RSU RS5RU R5n"URR.RT(aiU [U5S- :Xa[ RF"S /US9n#OUU S-n#U#RSU RS5RU R5n#OSn#X4X4UU4UU4S.n$URWU UU!S9 URYU$5n%U%Hn&UR[UR5 U$R]5V's0sHn'U'[_U&U'5_M n(n'[_U&UR`5n)URRcU)5 UR"SU U"U#UURHSS.U(D6SU&l2SSS5 URgUR5 M U"U%5Sn*U Rn+UR:RiU*U!U SS9Sn U RU+:wa>[ RjRlRo5(aU RU+5n UbJ0n,UHn-[q5U-U,U-'M U"UU U!U,5n.U.RsSU 5n U.RsSU 5n U [U5S- :Xd)U S-U:a0U S-UR:R>-S:XaURu5 [v(dGM[xRz"5 GM( SSS5 SUlUS:XaU n/O}U RUR|R5UR|R.R~- n UR|RU SS9Sn/URRU/US9n/UR5 U(dU/4$[U/S9$s sn'f!,(df  GN/=f!,(df  N=f)a Function invoked when calling the pipeline for generation. Args: prompt (`str` or `list[str]`, *optional*): The prompt or prompts to guide the image generation. If not defined, one has to pass `prompt_embeds`. instead. negative_prompt (`str` or `list[str]`, *optional*): The prompt or prompts not to guide the image generation. If not defined and negative_prompt_embeds is not provided, will use an empty negative prompt. Ignored when not using guidance. ). height (`int`, *optional*, defaults to self.unet.config.sample_size * self.vae_scale_factor): The height in pixels of the generated image. This is set to 1024 by default for the best results. width (`int`, *optional*, defaults to self.unet.config.sample_size * self.vae_scale_factor): The width in pixels of the generated image. This is set to 1024 by default for the best results. 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. sigmas (`list[float]`, *optional*): Custom sigmas to use for the denoising process with schedulers which support a `sigmas` argument in their `set_timesteps` method. If not defined, the default behavior when `num_inference_steps` is passed will be used. distilled_guidance_scale (`float`, *optional*, defaults to None): A guidance scale value for guidance distilled models. Unlike the traditional classifier-free guidance where the guidance scale is applied during inference through noise prediction rescaling, guidance distilled models take the guidance scale directly as an input parameter during forward pass. Guidance is enabled by setting `distilled_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. For guidance distilled models, this parameter is required. For non-distilled models, this parameter will be ignored. 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 be generated by sampling using the supplied random `generator`. 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. prompt_embeds_mask (`torch.Tensor`, *optional*): Pre-generated text embeddings mask. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not provided, text embeddings mask will be generated from `prompt` input argument. prompt_embeds_2 (`torch.Tensor`, *optional*): Pre-generated text embeddings for ocr. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not provided, text embeddings for ocr will be generated from `prompt` input argument. prompt_embeds_mask_2 (`torch.Tensor`, *optional*): Pre-generated text embeddings mask for ocr. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not provided, text embeddings mask for ocr 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. negative_prompt_embeds_mask (`torch.Tensor`, *optional*): Pre-generated negative text embeddings mask. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not provided, negative text embeddings mask will be generated from `negative_prompt` input argument. negative_prompt_embeds_2 (`torch.Tensor`, *optional*): Pre-generated negative text embeddings for ocr. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not provided, negative text embeddings for ocr will be generated from `negative_prompt` input argument. negative_prompt_embeds_mask_2 (`torch.Tensor`, *optional*): Pre-generated negative text embeddings mask for ocr. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not provided, negative text embeddings mask for ocr will be generated from `negative_prompt` input argument. output_type (`str`, *optional*, defaults to `"pil"`): The output format of the generate image. Choose between [PIL](https://pillow.readthedocs.io/en/stable/): `PIL.Image.Image` or `np.array`. return_dict (`bool`, *optional*, defaults to `True`): Whether or not to return a [`~pipelines.qwenimage.QwenImagePipelineOutput`] instead of a plain tuple. attention_kwargs (`dict`, *optional*): A kwargs dictionary that if specified is passed along to the `AttentionProcessor` as defined under `self.processor` in [diffusers.models.attention_processor](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/attention_processor.py). 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.hunyuan_image.HunyuanImagePipelineOutput`] or `tuple`: [`~pipelines.hunyuan_image.HunyuanImagePipelineOutput`] if `return_dict` is True, otherwise a `tuple`. When returning a tuple, the first element is a list with the generated images. ) rrErrrrrrrrNFrr)rrErr.rrrr)enabled)rrrrrnr.rrDg?gr)r/zD`distilled_guidance_scale` is required for guidance-distilled model.rmg@@)totalro)r|r}encoder_hidden_states_2encoder_attention_mask_2)stepr;timestep)rur timestep_rguidancer return_dict)rrDrElatent) output_type)imagesr0)ErarPrrrrrqrrrr9rrprrtrNrnrrrFrGr _enablednum_conditionsrZ in_channelsrnplinspacer?r:maxorderrguidance_embedsr1tensorrset_begin_index progress_bar enumeraterexpand use_meanflow set_stateprepare_inputsprepare_modelsr7rY_identifier_key cache_context noise_predcleanup_modelsrbackendsmps is_availablelocalspopupdate XLA_AVAILABLExm mark_steprIscaling_factordecoder\ postprocessmaybe_free_model_hooksr)0rbrrrrr;distilled_guidance_scaler/rrrDrErrrrrrrrrrcallback_on_step_endrrr.rGrr-num_warmup_stepsrritrr guider_inputs guider_stateguider_state_batch input_name cond_kwargs context_namer latents_dtypecallback_kwargsrcallback_outputsimages0 r*__call__HunyuanImagePipeline.__call__stK433d6K6KKI11D4I4II    +'#91(C/Q+!5%=*G  "2!%  *VS"9"9J  Jvt$<$<VJ&,,Q/J''TXSeSe'1!"7+!5Tf T P ?%&; 8%B#   &+(-&<%>%>t?O?O?U?U%V "'?'B'B4CSCSCYCY'Z $ $//66BB&&!$99!5%%'  IOS#':Q'>?D\b);DNNL_agpv)w& &s9~0CnnFZFZ0ZZ\]^!)n    " " 2 27O7Wcd d    " " 2 2 -.q1AAIYIYI_I_hn H  (%'D " &&q)   %8  9\!),1>>)*&88GMM!$4588G##**77C NQ..%*\\3%%G %.q1u%5 !+!2!27==3C!D!G!G !VJ!%J /<-T/A._0?AY/Z1EGd0e !   a=P[\ ] &44]C +7&))$*:*:;_l^p^p^r#^rPZ G,> $KK^r # $++=v?U?U#VL))77 E8<8H8H9*1%-'1%--1-B-B(- 9*99*5F))$*:*:;/+7L$L1!4 !( ..--j!WRW-XYZ[==M1~~))6688")**]";'3&(O?-3Xa[*@';D!Q'X$.229gFG$4$8$8-$XMI**A9I/IqSTuX\XfXfXlXlNlpqNq '') =LLNS-:X"& ( "Ejj0488??3Q3QQGHHOOGO?BE((44U 4TE ##%8O)77W# FEk: 9s>(E^-=^ 3^-,^ 3E ^-^-^- ^* %^-- ^;) rrrrrar\r_r`r^r]rP)NN)r:rrIr rJrrKrrLr rMrrNrrG#AdaptiveProjectedMixGuidance | NonerFr)NNNrQrSrTr)rKrrJrrstr | list[str]r.torch.device | Nonerntorch.dtype | Noner]rrvrrrwrrxr)NNrR) rKrrJr rrrr.rrnrr]r)NrrNNNN)rrr.rrrrrrEtorch.Tensor | Nonerrrrrr) NNNNNNNNNNr).rrrrr int | Nonerrr;rrz float | Noner/list[float] | Nonerrrz.torch.Generator | list[torch.Generator] | NonerDrrErrrrrrrrrrrrrrrrz str | Nonerboolrzdict[str, Any] | Nonerz!Callable[[int, int], None] | Nonerz list[str])__name__ __module__ __qualname____firstlineno____doc__model_cpu_offload_seqr_optional_componentsrWr~rrrrpropertyrrrrrno_gradrEXAMPLE_DOC_STRINGr__static_attributes__ __classcell__)r8s@r*rBrBs0M(/:((37;:> &2 &' &9 & " & ' &# &4 &4 &8 & &L#'&*$($(^'(#5!#59#5 #5 $ #5 " #5"#5#5#5"%#5T'+$($'"5 "5%"5 "5 $ "5 " "5""5N'+%&-126/348\X\X$\X \X # \X + \X0\X-\X2\XF#$(!!%&*+/C\:&&##&& ]]_12#'+/! #%15%)%&DH'+-1266:;?/3488<=A"' 26BF9B 1j8j8)j8 j8  j8 ! j8#/j8#j8 #j8Bj8%j8+j80j8!4j8&9j8 -!j8"2#j8$#6%j8&(;'j8( )j8*+j8,0-j8.@/j80-61j83j8r@rB)rrr)NNNN)r;rr.zstr | torch.device | Noner-zlist[int] | Noner/r). __future__rr3rtypingrrnumpyrr transformersrrrr guidersr r\r modelsr r schedulersrutilsrrrutils.torch_utilsrpipeline_utilsrpipeline_outputrtorch_xla.core.xla_modelcore xla_modelrr get_loggerrrr&r+r?rBr0r@r*r8s#  jj30O9OO-.7))MM   H %&! N'+(,"&!% 8*#8* &8* 8*  8*vD 8,D 8r@