+hSSKrSSKrSSKrSSKJr SSKJrJrJ r J r J r J r SSK rSSKrSSKrSSKJs Jr SSKJrJrJr SSKJr SSKJr SSKJr SSK J!r!J"r"J#r#J$r$J%r% SS K&J'r' S S K(J)r) S S K*J+r+ S SK,J-r- S SK.J/r/ \""5(aSSK0J1r1 \#"5(aSSK2r2SSK J3r3 \3"5(a SSK4J5s J6r7 Sr8OSr8\$Rr"\:5r;Sr<"SS\)\5r=g)N)AnyCallableDictListOptionalUnion)CLIPImageProcessorT5EncoderModel T5Tokenizer)StableDiffusionLoraLoaderMixin)UNet2DConditionModel) DDPMScheduler)BACKENDS_MAPPINGis_bs4_availableis_ftfy_availableloggingreplace_example_docstring) randn_tensor)DiffusionPipeline)IFPipelineOutput)IFSafetyChecker) IFWatermarker) BeautifulSoup)is_torch_xla_availableTFa$ Examples: ```py >>> from diffusers import IFPipeline, IFSuperResolutionPipeline, DiffusionPipeline >>> from diffusers.utils import pt_to_pil >>> import torch >>> pipe = IFPipeline.from_pretrained("DeepFloyd/IF-I-XL-v1.0", variant="fp16", torch_dtype=torch.float16) >>> pipe.enable_model_cpu_offload() >>> prompt = 'a photo of a kangaroo wearing an orange hoodie and blue sunglasses standing in front of the eiffel tower holding a sign that says "very deep learning"' >>> prompt_embeds, negative_embeds = pipe.encode_prompt(prompt) >>> image = pipe(prompt_embeds=prompt_embeds, negative_prompt_embeds=negative_embeds, output_type="pt").images >>> # save intermediate image >>> pil_image = pt_to_pil(image) >>> pil_image[0].save("./if_stage_I.png") >>> super_res_1_pipe = IFSuperResolutionPipeline.from_pretrained( ... "DeepFloyd/IF-II-L-v1.0", text_encoder=None, variant="fp16", torch_dtype=torch.float16 ... ) >>> super_res_1_pipe.enable_model_cpu_offload() >>> image = super_res_1_pipe( ... image=image, prompt_embeds=prompt_embeds, negative_prompt_embeds=negative_embeds ... ).images >>> image[0].save("./if_stage_II.png") ``` c+^\rSrSr%\\S'\\S'\\S'\\S'\\S'\ \ \S'\ \ \S'\ \ \S '\ R"S 5r/S QrS rS /rS0S\S\S\S\S\S\ \ S\ \ S \ \ S \4U4SjjjrS1SjrSr\R0"5S2S\\\\4S\S\S\ \R:S\ \\\\4S\ \R<S\ \R<S\4Sjj5rSr Sr!S3Sjr"Sr#Sr$\R0"5\%"\&5S4S\\\\4S \S!\S"\\'RPRP\)RT\R<4S#\S$\\S%\+S\ \\\\4S\ \S&\+S'\ \\RX\\RX4S\ \R<S\ \R<S(\ \S)\S*\ \-\\\R</S4S+\S,\ \.\\/4S-\S\4(S.jj55r0S/r1U=r2$)5IFSuperResolutionPipelineR tokenizer text_encoderunet schedulerimage_noising_schedulerfeature_extractorsafety_checker watermarkeru5[#®•©™&@·º½¾¿¡§~\)\(\]\[\}\{\|\\/\*]{1,})r!r"r'r&r(ztext_encoder->unetrequires_safety_checkerc L>[T U]5 Uc*U (a#[RSURS35 UbUc [ S5eUb/UR RS:wa[RS5 URUUUUUUUUS9 URU S9 g)Nz)You have disabled the safety checker for a by passing `safety_checker=None`. Ensure that you abide to the conditions of the IF license and do not expose unfiltered results in services or applications open to the public. Both the diffusers team and Hugging Face strongly recommend to keep the safety filter enabled in all public facing circumstances, disabling it only for use-cases that involve analyzing network behavior or auditing its results. For more information, please have a look at https://github.com/huggingface/diffusers/pull/254 .zMake sure to define a feature extractor when loading {self.__class__} if you want to use the safety checker. If you do not want to use the safety checker, you can pass `'safety_checker=None'` instead.aQIt seems like you have loaded a checkpoint that shall not be used for super resolution from {unet.config._name_or_path} as it accepts {unet.config.in_channels} input channels instead of 6. Please make sure to pass a super resolution checkpoint as the `'unet'`: IFSuperResolutionPipeline.from_pretrained(unet=super_resolution_unet, ...)`.)r!r"r#r$r%r'r&r()r)) super__init__loggerwarning __class__ ValueErrorconfig in_channelsregister_modulesregister_to_config) selfr!r"r#r$r%r'r&r(r)r0s v/home/james-whalen/.local/lib/python3.13/site-packages/diffusers/pipelines/deepfloyd_if/pipeline_if_superresolution.pyr-"IFSuperResolutionPipeline.__init__ss   !&= NN;DNN;KLjj   %*;*Cx    7 71 < NNd  %$;)/#   8OPc^^T(aT[5(dE[R[SSR S55 [RS5 SmT(aT[ 5(dE[R[SSR S55 [RS5 Sm[ U[[45(dU/nS[4UU4SjjnUVs/sH oC"U5PM sn$s snf) Nbs4zSetting `clean_caption=True`z#Setting `clean_caption` to False...Fftfytextc>T(a$TRU5nTRU5nU$UR5R5nU$)N)_clean_captionlowerstrip)r> clean_captionr6s r7process>IFSuperResolutionPipeline._text_preprocessing..processsH**40**40Kzz|))+Kr9) rr.r/rformatr isinstancetupleliststr)r6r>rCrDts` ` r7_text_preprocessing-IFSuperResolutionPipeline._text_preprocessings !1!3!3 NN+E226==>\] ^ NN@ A!M !2!4!4 NN+F3B7>>?]^ _ NN@ A!M$ ..6D #  %))Dq D)))s*C>c^ [U5n[R"U5nUR5R 5n[ R "SSU5n[ R "SSU5n[ R "SSU5n[USS9Rn[ R "SSU5n[ R "S SU5n[ R "S SU5n[ R "S SU5n[ R "S SU5n[ R "S SU5n[ R "SSU5n[ R "SSU5n[ R "SSU5n[ R "SSU5n[ R "SSU5n[ R "SSU5n[ R "SSU5n[ R "SSU5n[ R "SSU5n[ R "SSU5n[ R "SSU5n[ R "SSU5n[ R "SSU5n[ R "SSU5n[ R "S SU5n[ R "S!SU5n[ R "URSU5n[ R "S"SU5n[ R"S#5n[[ R"X!55S$:a[ R "USU5n[R"U5n[R "[R "U55n[ R "S%SU5n[ R "S&SU5n[ R "S'SU5n[ R "S(SU5n[ R "S)SU5n[ R "S*SU5n[ R "S+SU5n[ R "S,SU5n[ R "S-SU5n[ R "S.SU5n[ R "S/S0U5n[ R "S1S2U5n[ R "S3SU5nUR5 [ R "S4S5U5n[ R "S6SU5n[ R "S7SU5n[ R "S8SU5nUR5$)9Nzpersonzk\b((?:https?:(?:\/{1,3}|[a-zA-Z0-9%])|[a-zA-Z0-9.\-]+[.](?:com|co|ru|net|org|edu|gov|it)[\w/-]*\b\/?(?!@)))zh\b((?:www:(?:\/{1,3}|[a-zA-Z0-9%])|[a-zA-Z0-9.\-]+[.](?:com|co|ru|net|org|edu|gov|it)[\w/-]*\b\/?(?!@)))z html.parser)featuresz @[\w\d]+\bz[\u31c0-\u31ef]+z[\u31f0-\u31ff]+z[\u3200-\u32ff]+z[\u3300-\u33ff]+z[\u3400-\u4dbf]+z[\u4dc0-\u4dff]+z[\u4e00-\u9fff]+z|[\u002D\u058A\u05BE\u1400\u1806\u2010-\u2015\u2E17\u2E1A\u2E3A\u2E3B\u2E40\u301C\u3030\u30A0\uFE31\uFE32\uFE58\uFE63\uFF0D]+-u[`´«»“”¨]"u[‘’]'z"?z&z"\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3} z \d:\d\d\s+$z\\nz #\d{1,3}\bz #\d{5,}\bz \b\d{6,}\bz0[\S]+\.(?:png|jpg|jpeg|bmp|webp|eps|pdf|apk|mp4)z [\"\']{2,}z[\.]{2,}z\s+\.\s+z (?:\-|\_)r z\b[a-zA-Z]{1,3}\d{3,15}\bz\b[a-zA-Z]+\d+[a-zA-Z]+\bz\b\d+[a-zA-Z]+\d+\bz!(worldwide\s+)?(free\s+)?shippingz(free\s)?download(\sfree)?z\bclick\b\s(?:for|on)\s\w+z9\b(?:png|jpg|jpeg|bmp|webp|eps|pdf|apk|mp4)(\simage[s]?)?z\bpage\s+\d+\bz*\b\d*[a-zA-Z]+\d+[a-zA-Z]+\d+[a-zA-Z\d]*\bu\b\d+\.?\d*[xх×]\d+\.?\d*\bz \b\s+\:\s+z: z (\D[,\./])\bz\1 z\s+z^[\"\']([\w\W]+)[\"\']$z\1z ^[\'\_,\-\:;]z[\'\_,\-\:\-\+]$z^\.\S+$)rJul unquote_plusrBrAresubrr>bad_punct_regexcompilelenfindallr=fix_texthtmlunescape)r6captionregex2s r7r@(IFSuperResolutionPipeline._clean_captionsg,//'*--/'')&&Xw7&& z    && w     -@EE&&G4&&,b':&&,b':&&,b':&&,b':&&,b':&&,b':&&,b':&& L   &&-sG<&&c73&&R1&&"g.&&>WM&&W5&&g.&&G4&&r73&&G4&&LbRYZ&&g6&&dG4&&--tW=&&dG4L) rzz&* +a /ffVS'2G--(-- g 67&&5r7C&&5r7C&&/W=&&=r7K&&6GD&&6GD&&UWY[bc&&*B8&&FgV&&92wG&&w7&&&':&&g. &&3UGD&&)38&&,c7;&&R1}}r9Npromptdo_classifier_free_guidancenum_images_per_promptdevicenegative_prompt prompt_embedsnegative_prompt_embedsrCc Ub>Ub;[U5[U5La$[S[U5S[U5S35eUc URnUb[U[5(aSn O3Ub![U[ 5(a [ U5n OURSn Sn UGcURXS9nURUS U S S S S 9n U Rn URUS S S9Rn U RSU RS:a][R"X5(dBURRU SS2U S- S245n[RSU SU35 U R R#U5nUR%U R#U5US9nUSnUR$bUR$R&nO&UR(bUR(R&nOSnUR#UUS9nURunnnUR+SUS5nUR-UU-US5nU(aUcUcS/U -nOK[U[5(aU/nO2U [ U5:wa![/SUS[ U5SUSU S3 5eUnURUUS9nURSn URUS U S S S S S9nUR R#U5nUR%URR#U5US9nUSnU(aJURSnUR#UUS9nUR+SUS5nUR-X-US5nXg4$SnXg4$)a Encodes the prompt into text encoder hidden states. Args: prompt (`str` or `List[str]`, *optional*): prompt to be encoded do_classifier_free_guidance (`bool`, *optional*, defaults to `True`): whether to use classifier free guidance or not num_images_per_prompt (`int`, *optional*, defaults to 1): number of images that should be generated per prompt device: (`torch.device`, *optional*): torch device to place the resulting embeddings on negative_prompt (`str` or `List[str]`, *optional*): The prompt or prompts not to guide the image generation. If not defined, one has to pass `negative_prompt_embeds`. instead. If not defined, one has to pass `negative_prompt_embeds`. instead. Ignored when not using guidance (i.e., ignored if `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. clean_caption (bool, defaults to `False`): If `True`, the function will preprocess and clean the provided caption before encoding. Nz?`negative_prompt` should be the same type to `prompt`, but got z != .rrM)rC max_lengthTpt)paddingrn truncationadd_special_tokensreturn_tensorslongest)rprsr<z\The following part of your input was truncated because CLIP can only handle sequences up to z tokens: )attention_mask)dtypergrPz`negative_prompt`: z has batch size z, but `prompt`: zT. Please make sure that passed `negative_prompt` matches the batch size of `prompt`.)rprnrqreturn_attention_maskrrrs)type TypeError_execution_devicerGrJrIr\shaperLr! input_idstorchequal batch_decoder.r/rutor"rvr#repeatviewr1)r6rdrerfrgrhrirjrC batch_sizern text_inputstext_input_idsuntruncated_ids removed_textrurvbs_embedseq_len_ uncond_tokens uncond_inputs r7 encode_prompt'IFSuperResolutionPipeline.encode_prompt.sN  /"=F|4#88UVZ[jVkUlmV ~Q( >++F  *VS"9"9J  Jvt$<$<VJ&,,Q/J  --f-RF..$%#'# )K)22N"nnVYW[n\ffO$$R(N,@,@,DDU[[NN $~~::?1j[\n_aNaKa;bc "|9\N< )77::6BN --!!&)-.M*!,M    (%%++E YY "IIOOEE%((uV(D ,22'1%,,Q0EqI %**86K+KWVXY  '+A+I&!#z 1 OS11!0 1 s?33 )/)::J3K_J`ax/ |<33 !0  44]R_4`M&,,Q/J>>$%&*#'#*L*88;;FCN%)%6%6&&))&1-&7& "& " &,2215G%;%>%>USY%>%Z "%;%B%B1F[]^%_ "%;%@%@Acelnp%q "44&* "44r9cURbYURURU5SS9RU5nURUURRUS9S9upnOSnSnXU4$)Nro)rs)rv)images clip_input)r'r& numpy_to_pilr pixel_values)r6imagergrvsafety_checker_input nsfw_detectedwatermark_detecteds r7run_safety_checker,IFSuperResolutionPipeline.run_safety_checkers    *#'#9#9$:K:KE:Rcg#9#h#k#klr#s 7;7J7J/<<??e?L8K8 4E"4 !M!% %777r9cnS[[R"URR5R R 55;n0nU(aX$S'S[[R"URR5R R 55;nU(aXS'U$)Neta generator)setinspect signaturer$step parameterskeys)r6rr accepts_etaextra_step_kwargsaccepts_generators r7prepare_extra_step_kwargs3IFSuperResolutionPipeline.prepare_extra_step_kwargss s7#4#4T^^5H5H#I#T#T#Y#Y#[\\  '*e $(3w/@/@ATAT/U/`/`/e/e/g+hh -6k *  r9c UbUb6[U[5(aUS::a[SUS[U5S35eUbUb[SUSUS35eUcUc [S5eUbA[U[5(d,[U[ 5(d[S [U535eUbUb[S US US35eUbCUb@UR UR :wa&[S UR S UR S35eUS:d#X@RRR:a0[SUSURRRS35e[U[ 5(aUSn OUn [U [R5(d_[U [RR5(d6[U [R5(d[S[U 535e[U[ 5(a [!U5n O[U[R5(aUR Sn O][U[RR5(aSn O1[U[R5(aUR Sn OeX::wa[SU SU35eg)Nrz5`callback_steps` has to be a positive integer but is z of type rlzCannot 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` z`noise_level`: z; must be a valid timestep in `self.noising_scheduler`, [0, )z_`image` has to be of type `torch.Tensor`, `PIL.Image.Image`, `np.ndarray`, or List[...] but is rzimage batch size: z# must be same as prompt batch size )rGintr1rxrJrIr{r%r2num_train_timestepsr}TensorPILImagenpndarrayr\) r6rdrr noise_levelcallback_stepsrhrirjcheck_image_typeimage_batch_sizes r7 check_inputs&IFSuperResolutionPipeline.check_inputss  "  & >30O0OSaefSfGGWX(),   -";08N}o^00 ^ 5w  FC)@)@TZ\`IaIaQRVW]R^Q_`a a  &+A+M9/9JK*++]_   $)?)K""&<&B&BB --:-@-@,AB.445Q8 ?k-I-I-P-P-d-dd!+.ijnkGkGkNkNkbkbjccde  eT " "$Qx $ +U\\::/AA/<<)*+-  eT " ""5z  u|| , ,${{1~  syy / /  rzz * *${{1~  5  )12B1CCfgqfrst t *r9cXX44n[U[5(a*[U5U:wa[S[U5SUS35e[ XXeS9n XR R -n U $)Nz/You have passed a list of generators of length z+, but requested an effective batch size of z@. Make sure the batch size matches the length of the generators.rrgrv)rGrIr\r1rr$init_noise_sigma) r6r num_channelsheightwidthrvrgrr{intermediate_imagess r7prepare_intermediate_images5IFSuperResolutionPipeline.prepare_intermediate_images9s{69 i & &3y>Z+GA#i.AQR&<'gi  +5fb2NN4S4SS""r9cN[U[R5(d[U[5(dU/n[US[R R 5(aUVs/sH<n[ R"U5R[ R5S- S- PM> nn[ R"USS9n[R"URSSSS55nGO[US[ R5(aS[ R"USS9nURS:XaUSn[R"URSSSS55nO[U[5(aw[US[R5(aUUSRnUS:Xa[R"USS 9nO*US :Xa[R"USS 9nO[!S U35eUR#X0R$R&S 9nUR)USS 9nU$s snf) Nrg_@?)axisr rrdimz/Image must have 3 or 4 dimensions, instead got )rgrv)rGr}rrIrrrarrayastypefloat32stack from_numpy transposerndimconcatr1rr#rvrepeat_interleave)r6rrfrgidimss r7preprocess_image*IFSuperResolutionPipeline.preprocess_imageGs%..z%7N7NGE eAh  0 0KPQ5aRXXa['' 3e;cA5EQHHU+E$$U__Q1a%@AE a"** - -HHU+EzzQa$$U__Q1a%@AE t $ $E!Hell)K)K8==Dqy Eq1 U2 #RSWRX!YZZiioo>''(=1'E 1Rs(AH"rrrnum_inference_steps timestepsguidance_scalerr output_type return_dictcallbackrcross_attention_kwargsrc  Ub[U[5(aSnO3Ub![U[5(a [U5nOU RSnUR UUUUUUU U 5 U=(d UR RRnU=(d UR RRnURnUS:nURUUU UUU U US9upU(a[R"X/5n Ub<URRUUS9 URRn[U5nO0URRUUS9 URRn[!URS5(aURR#S5 UR RR$S -nUR'UU -UUUU R(UU 5nUR+X5nUR-XIU5n[.R0"XBU4S S S 9n[R2"U/URS-UR4S9n[7URU UR4UR(S 9nUR8R;UUUS9nU(a[R"U/S -5n[!US5(a'UR<bUR<R?5 [U5XPRR@-- nURCUS9n[EU5GHunn [R"UU/SS9n!U(a[R"U!/S -5OU!n!URRGU!U 5n!UR U!U U UUSS9Sn"U(a|U"RIS 5un#n$U#RKU!RSS -SS9un#n%U$RKU!RSS -SS9un$n&U#UU$U#- --n"[R"U"U&/SS9n"URRRLS;a U"RKURSSS9un"n%URRN"U"U U40UDSS0D6SnU[U5S- :Xd)US-U:aFUS-URR@-S:Xa&URQ5 UbUU-S:Xa U"UU U5 [R(dGM[TRV"5 GM SSS5 UnUS:XaUS - S-RYSS5nUR[5R]SS SS5R_5Ra5nURcUUU R(5unn'n(UReU5nURfb9URfRiX@R RR5 OUS:Xa=Sn'Sn([!US5(a'URjbURjR?5 OwUS - S-RYSS5nUR[5R]SS SS5R_5Ra5nURcUUU R(5unn'n(URm5 U(dUU'U(4$[oUU'U(S9$!,(df  GN=f)uV 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. height (`int`, *optional*, defaults to None): The height in pixels of the generated image. width (`int`, *optional*, defaults to None): The width in pixels of the generated image. image (`PIL.Image.Image`, `np.ndarray`, `torch.Tensor`): The image to be upscaled. 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. timesteps (`List[int]`, *optional*, defaults to None): 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 4.0): Guidance scale as defined in [Classifier-Free Diffusion Guidance](https://huggingface.co/papers/2207.12598). `guidance_scale` is defined as `w` of equation 2. of [Imagen Paper](https://huggingface.co/papers/2205.11487). Guidance scale is enabled by setting `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. If not defined, one has to pass `negative_prompt_embeds` instead. Ignored when not using guidance (i.e., ignored if `guidance_scale` is less than `1`). num_images_per_prompt (`int`, *optional*, defaults to 1): The number of images to generate per prompt. eta (`float`, *optional*, defaults to 0.0): Corresponds to parameter eta (η) in the DDIM paper: https://huggingface.co/papers/2010.02502. Only applies to [`schedulers.DDIMScheduler`], will be ignored for others. 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. 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. 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.stable_diffusion.IFPipelineOutput`] instead of a plain tuple. callback (`Callable`, *optional*): A function that will be called every `callback_steps` steps during inference. The function will be 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 will be called. If not specified, the callback will be called at every step. cross_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). noise_level (`int`, *optional*, defaults to 250): The amount of noise to add to the upscaled image. Must be in the range `[0, 1000)` clean_caption (`bool`, *optional*, defaults to `True`): Whether or not to clean the caption before creating embeddings. Requires `beautifulsoup4` and `ftfy` to be installed. If the dependencies are not installed, the embeddings will be created from the raw prompt. Examples: Returns: [`~pipelines.stable_diffusion.IFPipelineOutput`] or `tuple`: [`~pipelines.stable_diffusion.IFPipelineOutput`] if `return_dict` is True, otherwise a `tuple. When returning a tuple, the first element is a list with the generated images, and the second element is a list of `bool`s denoting whether the corresponding generated image likely represents "not-safe-for-work" (nsfw) or watermarked content, according to the `safety_checker`. Nrrr)rfrgrhrirjrC)rrg)rgset_begin_indexrbilinearT)mode align_cornersr)rtext_encoder_offload_hook)totalrF)encoder_hidden_states class_labelsrr)learned learned_rangerpilg?r rounet_offload_hook)rrr)8rGrJrIr\r{rr#r2 sample_sizerzrr}catr$ set_timestepsrhasattrrr3rrvrrF interpolatetensorrgrr% add_noiseroffloadorder progress_bar enumeratescale_model_inputchunksplit variance_typerupdate XLA_AVAILABLExm mark_stepclampcpupermutefloatnumpyrrr(apply_watermarkrmaybe_free_model_hooksr))r6rdrrrrrrrhrfrrrirjrrrrrrrCrrgrerrrupscalednoisenum_warmup_stepsrrrK model_input noise_prednoise_pred_uncondnoise_pred_textrpredicted_variancerrs) r7__call__"IFSuperResolutionPipeline.__call__fsL  *VS"9"9J  Jvt$<$<VJ&,,Q/J         " 7499++775))55'' '5s&:#150B0B  '"7+'#9'1C 1 -  '!II'=&MNM  NN ( (9V ( L00I"%i.  NN ( ()>#4 5 5 NN * *1 -yy''33q8 ">> . .         !::9J%%eFK==jX\]llK=8>>!3D#DX__] X^^y`h`n`no//99(EU`9a &))[MA$56K 44 5 5$:X:X:d  * * 2 2 4y>,?..BVBV,VV   %8  9\!),1#ii)Yeii (9:_j "nn>>{AN "YY*7!,+A % ' /9C9I9I!9L6%+<+B+B;CTCTUVCW[\C\bc+B+d(%q:I:O:OP[PaPabcPdhiPiop:O:q7O%7!2^YjGj5k!kJ!&J8J+KQR!SJ>>((66>ZZ$.$4$45H5N5Nq5QWX$4$YMJ'+nn&9&9#6':K'Y^''# I**A9I/IqSTuX\XfXfXlXlNlpqNq '')+N0Ba0G A':; =LLNO-:T$ % QY_++Aq1EIIK''1a399;AACE8<7N7NuV\^k^q^q7r 4E="4%%e,E+  00 8H8H8T8TU D  M!% t011d6L6L6X&&..0QY_++Aq1EIIK''1a399;AACE8<7N7NuV\^k^q^q7r 4E="4 ##%=*<= =uM^pqq]: 9s(G[[ [-)T)F)TrNNNNF)NNN)NNNN2Ng@NrgNNNrTNrNT)3__name__ __module__ __qualname____firstlineno__r __annotations__r rrrr rrrXr[rZ_optional_componentsmodel_cpu_offload_seq_exclude_from_cpu_offloadboolr-rLr@r}no_gradrrJrrrgrrrrrrrrEXAMPLE_DOC_STRINGrrrrr Generatorrrrr __static_attributes__ __classcell__)r0s@r7rrRs  ** 233_---((jj O o0!.)--Q-Q%-Q# -Q ! -Q "/ -Q!1-Q$$67-Qm,-Q"&-Q-Q`*2pd ]]_ -1%&)-;?049=#W5c49n%W5&*W5 # W5 & W5 "%T#Y"78 W5  -W5!) 6W5W5W5t 8!0#Mu` #> ]]_12)-BF#%# #;?/0MQ049=%* GK;?"+Krc49n%KrKr Kr SYY__bjj%,,>? Kr ! Kr9KrKr"%T#Y"78Kr (}KrKrE%//43H"HIJKr  -Kr!) 6Krc]Kr !Kr"8S#u||$r_rrX urllib.parseparserVtypingrrrrrrrr PIL.Imagerr}torch.nn.functionalnn functionalr transformersr r r loadersr modelsr schedulersrutilsrrrrrutils.torch_utilsrpipeline_utilsrpipeline_outputrr'r watermarkrr;rr=rtorch_xla.core.xla_modelcore xla_modelrr get_loggerrr.rrr r9r7r2s  == HH5*'..-+$!,))MM   H %@a r 13Qa rr9