3jw SSKrSSKrSSKJrJr SSKrSSKJr SSKJ r J r SSK J r J r SSKJr SSKJrJr SS KJr SS KJr SS KJrJr SS KJrJrJr SS KJr SSK J!r! SSK"J#r# \"5(a SSK$J%s J&r' Sr(OSr(\RR"\*5r+Sr,Sr-S S\.S-S\/\R`-S-S\1\.S-S\1\2S-4Sjjr3S!S\RhS\RjS-S\/4Sjjr6"SS\\5r7g)"N)AnyCallable)Image)T5EncoderModel T5Tokenizer)MultiPipelineCallbacksPipelineCallback)CogVideoXLoraLoaderMixin)AutoencoderKLCogVideoXCogVideoXTransformer3DModel)get_3d_rotary_pos_embed)DiffusionPipeline)CogVideoXDDIMSchedulerCogVideoXDPMScheduler)is_torch_xla_availableloggingreplace_example_docstring) randn_tensor)VideoProcessor)CogVideoXPipelineOutputTFaX Examples: ```python >>> import torch >>> from diffusers import CogVideoXDPMScheduler, CogVideoXVideoToVideoPipeline >>> from diffusers.utils import export_to_video, load_video >>> # Models: "THUDM/CogVideoX-2b" or "THUDM/CogVideoX-5b" >>> pipe = CogVideoXVideoToVideoPipeline.from_pretrained("THUDM/CogVideoX-5b", torch_dtype=torch.bfloat16) >>> pipe.to("cuda") >>> pipe.scheduler = CogVideoXDPMScheduler.from_config(pipe.scheduler.config) >>> input_video = load_video( ... "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/hiker.mp4" ... ) >>> prompt = ( ... "An astronaut stands triumphantly at the peak of a towering mountain. Panorama of rugged peaks and " ... "valleys. Very futuristic vibe and animated aesthetic. Highlights of purple and golden colors in " ... "the scene. The sky is looks like an animated/cartoonish dream of galaxies, nebulae, stars, planets, " ... "moons, but the remainder of the scene is mostly realistic." ... ) >>> video = pipe( ... video=input_video, prompt=prompt, strength=0.8, guidance_scale=6, num_inference_steps=50 ... ).frames[0] >>> export_to_video(video, "output.mp4", fps=8) ``` cUnUnUupVXV- nXtU- :aUn[[XE- U-55n OUn [[X6- U-55n[[XH- S- 55n [[X9- S- 55n X4X-X-44$)Ng@)intround) src tgt_width tgt_heighttwthhwr resize_height resize_widthcrop_top crop_lefts u/home/wildlama/miniconda3/lib/python3.13/site-packages/diffusers/pipelines/cogvideo/pipeline_cogvideox_video2video.pyget_resize_crop_region_for_gridr)Ms B B DA AG} 5!,-  E"&1*-. 5",345HE2,345I  8#;Y=U"V VVnum_inference_stepsdevice timestepssigmasc 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$) a Calls the scheduler's `set_timesteps` method and retrieves timesteps from the scheduler after the call. Handles custom timesteps. Any kwargs will be supplied to `scheduler.set_timesteps`. Args: scheduler (`SchedulerMixin`): The scheduler to get timesteps from. num_inference_steps (`int`): The number of diffusion steps used when generating samples with a pre-trained model. If used, `timesteps` must be `None`. device (`str` or `torch.device`, *optional*): The device to which the timesteps should be moved to. If `None`, the timesteps are not moved. timesteps (`list[int]`, *optional*): Custom timesteps used to override the timestep spacing strategy of the scheduler. If `timesteps` is passed, `num_inference_steps` and `sigmas` must be `None`. sigmas (`list[float]`, *optional*): Custom sigmas used to override the timestep spacing strategy of the scheduler. If `sigmas` is passed, `num_inference_steps` and `timesteps` must be `None`. Returns: `tuple[torch.Tensor, int]`: A tuple where the first element is the timestep schedule from the scheduler and the second element is the number of inference steps. zYOnly one of `timesteps` or `sigmas` can be passed. Please choose one to set custom valuesr-zThe current scheduler class zx's `set_timesteps` does not support custom timestep schedules. Please check whether you are using the correct scheduler.)r-r,r.zv's `set_timesteps` does not support custom sigmas schedules. Please check whether you are using the correct scheduler.)r.r,r,) ValueErrorsetinspect signature set_timesteps parameterskeys __class__r-len) schedulerr+r,r-r.kwargsaccepts_timesteps accept_sigmass r(retrieve_timestepsr>`s}>!3tuu'3w/@/@AXAX/Y/d/d/i/i/k+ll .y/B/B.CDab  M)MfM'' !)n  ))   C(9(9):Q:Q(R(](](b(b(d$ee .y/B/B.CD_`  GvGG'' !)n  ))  3MFMfM''  ))r*encoder_output generator sample_modec[US5(a!US:XaURRU5$[US5(a US:XaURR5$[US5(a UR$[ S5e)N latent_distsampleargmaxlatentsz3Could not access latents of provided encoder_output)hasattrrCrDmoderFAttributeError)r?r@rAs r(retrieve_latentsrJs}~}--+2I))00;;  / /K84K))..00  + +%%%RSSr*c2^\rSrSrSr/rSr/SQrS\S\ S\ S\ S \ \ -4 U4S jjrSDS\\\-S\S\S\R&S -S\R(S -4 SjjrSES\\\-S\\\-S -S\S\S\R.S -S\R.S -S\S\R&S -S\R(S -4SjjrSFS\R.S -S\S\S\S\S\R(S -S\R&S -S\R2S -S \R.S -S!\R.S -4S"jjrS \R.S#\R.4S$jrS%rS&rSGS'jrSHS(jrSHS)jr S\S\S*\S\R&S#\!\R.\R.44 S+jr"\#S,5r$\#S-5r%\#S.5r&\#S/5r'\#S05r(\RR"5\*"\+5S S S S S S1S S2S3S4S S5S S S S S6SS S S /S 4S\\,RXS\\\-S -S\\\-S -S\S -S\S -S7\S8\\S -S9\-S:\-S;\S\S<\-S\R2\\R2-S -S \R\S -S\R\S -S\R\S -S=\S>\S?\/\\04S -S@\1\\/S 4\2-\3-S -SA\\S\S#\4\!-4.SBjj55r5SCr6U=r7$)ICogVideoXVideoToVideoPipelinea Pipeline for video-to-video generation using CogVideoX. 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.) Args: vae ([`AutoencoderKL`]): Variational Auto-Encoder (VAE) Model to encode and decode videos to and from latent representations. text_encoder ([`T5EncoderModel`]): Frozen text-encoder. CogVideoX uses [T5](https://huggingface.co/docs/transformers/model_doc/t5#transformers.T5EncoderModel); specifically the [t5-v1_1-xxl](https://huggingface.co/PixArt-alpha/PixArt-alpha/tree/main/t5-v1_1-xxl) variant. tokenizer (`T5Tokenizer`): Tokenizer of class [T5Tokenizer](https://huggingface.co/docs/transformers/model_doc/t5#transformers.T5Tokenizer). transformer ([`CogVideoXTransformer3DModel`]): A text conditioned `CogVideoXTransformer3DModel` to denoise the encoded video latents. scheduler ([`SchedulerMixin`]): A scheduler to be used in combination with `transformer` to denoise the encoded video latents. ztext_encoder->transformer->vae)rF prompt_embedsnegative_prompt_embeds tokenizer text_encodervae transformerr:c>[TU]5 URXX4US9 [USS5(a/S[ UR R R5S- -OSUl[USS5(a UR R ROSUl [USS5(a UR R ROSUl [URS9Ulg) N)rPrQrRrSr:rRrgffffff?)vae_scale_factor)super__init__register_modulesgetattrr9rRconfigblock_out_channelsvae_scale_factor_spatialtemporal_compression_ratiovae_scale_factor_temporalscaling_factorvae_scaling_factor_imagervideo_processor)selfrPrQrRrSr:r8s r(rZ&CogVideoXVideoToVideoPipeline.__init__s  hq  CJ$PUW[B\B\A#dhhoo889A= >bc %;B$t:T:TDHHOO 6 6Z[ &KRRVX]_cJdJd(F(Fjm%-t?\?\]r*Nrpromptnum_videos_per_promptmax_sequence_lengthr,dtypec U=(d URnU=(d URRn[U[5(aU/OUn[ U5nUR USUSSSS9nURnUR USSS9Rn U RSURS:a][R"X5(dBUR RU SS2US- S245n [RS US U 35 URURU55S n U RXTS 9n U Rupn U RSUS5n U R!Xb-U S5n U $) N max_lengthTpt)paddingrm truncationadd_special_tokensreturn_tensorslongest)rorrrzXThe following part of your input was truncated because `max_sequence_length` is set to z tokens: r)rkr,)_execution_devicerQrk isinstancestrr9rP input_idsshapetorchequal batch_decodeloggerwarningtorepeatview)rerhrirjr,rk batch_size text_inputstext_input_idsuntruncated_ids removed_textrN_seq_lens r(_get_t5_prompt_embeds3CogVideoXVideoToVideoPipeline._get_t5_prompt_embedss14110**00'44&&[ nn  *# % %....SW.Xbb   $(<(>66qJ]`aJadfJfGf7ghL NN'( ,A  )).*;*;F*CDQG %((u(D &++ A%,,Q0EqI %**:+MwXZ[ r*Tnegative_promptdo_classifier_free_guidancerNrOc 2U=(d URn[U[5(aU/OUnUb [U5n OURSn UcUR UUUUU S9nU(aUcU=(d Sn[U[5(aX/-OUnUb;[ U5[ U5La$[S[ U5S[ U5S35eU [U5:wa![SUS[U5S USU S 3 5eUR UUUUU S9nXV4$) ab Encodes the prompt into text encoder hidden states. Args: prompt (`str` or `list[str]`, *optional*): prompt to be encoded 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`). do_classifier_free_guidance (`bool`, *optional*, defaults to `True`): Whether to use classifier free guidance or not. num_videos_per_prompt (`int`, *optional*, defaults to 1): Number of videos that should be generated per prompt. torch device to place the resulting embeddings on 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. device: (`torch.device`, *optional*): torch device dtype: (`torch.dtype`, *optional*): torch dtype r)rhrirjr,rkz?`negative_prompt` should be the same type to `prompt`, but got z != .z`negative_prompt`: z has batch size z, but `prompt`: zT. Please make sure that passed `negative_prompt` matches the batch size of `prompt`.) rurvrwr9ryrtype TypeErrorr1) rerhrrrirNrOrjr,rkrs r( encode_prompt+CogVideoXVideoToVideoPipeline.encode_prompt skL1411'44&&  VJ&,,Q/J   66&;$7 7M '+A+I-3O@J?\_@`@`j+<Z+GA#i.AQR&<'gi  SZRaejjma'D,J,JJQNgngsgstugv    33 3 22 2   ?)T**dijtdu du_`$TXX__UX5G5G5J%KY\Zdu  kppjocf 0qAQ1RT] ^jo p 99\q9<G$returncURSSSSS5nSUR- U-nURRU5RnU$)NrrUrrrW)rrcrRdecoderD)rerFframess r(decode_latents,CogVideoXVideoToVideoPipeline.decode_latentssJ//!Q1a0d333g=)00 r*c[[X-5U5n[X- S5nX&URR-SnX!U- 4$)Nr)minrmaxr:order)rer+r-strengthr, init_timestept_starts r( get_timesteps+CogVideoXVideoToVideoPipeline.get_timestepssPC 3 >?ATU )91=(<(<<>? 777r*cnS[[R"URR5R R 55;n0nU(aX$S'S[[R"URR5R R 55;nU(aXS'U$)Netar@)r2r3r4r:stepr6r7)rer@r accepts_etaextra_step_kwargsaccepts_generators r(prepare_extra_step_kwargs7CogVideoXVideoToVideoPipeline.prepare_extra_step_kwargss s7#4#4T^^5H5H#I#T#T#Y#Y#[\\  '*e $(3w/@/@ATAT/U/`/`/e/e/g+hh -6k *  r*c *^US-S:wd US-S:wa[SUSUS35eUS:dUS:a[SU35eUbW[U4SjU55(d=[S TRS UV s/sHoTR;dMU PM sn 35eUbU b[S US U S 35eUcU c [S5eUbA[U[5(d,[U[ 5(d[S[ U535eUbU b[S USU S 35eUbU b[SUSU S 35eU bCU b@U RU R:wa&[SU RSU RS35eUbUb [S5eggs sn f)NrVrz7`height` and `width` have to be divisible by 8 but are z and rrz2The value of strength should in [0.0, 1.0] but is c3@># UHoTR;v M g7fN)_callback_tensor_inputs).0kres r( =CogVideoXVideoToVideoPipeline.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 and `negative_prompt_embeds`: z'Cannot forward both `negative_prompt`: zu`prompt_embeds` and `negative_prompt_embeds` must have the same shape when passed directly, but got: `prompt_embeds` z != `negative_prompt_embeds` z3Only one of `video` or `latents` should be provided)r1allrrvrwrrry) rerhrrrr"callback_on_step_end_tensor_inputsrrFrNrOrs ` r( check_inputs*CogVideoXVideoToVideoPipeline.check_inputssn A:?eai1nVW]V^^cdicjjklm m a<8a<QRZQ[\] ] - 9#F 7YF C C DTEaEaDbbn|^pH|^vwkokGkGbGpq|^pHoIJ   -";08N}o^00 ^ 5w  FC)@)@TZ\`IaIaQRVW]R^Q_`a a  "8"D09*++]_   &+A+M9/9JK*++]_   $)?)K""&<&B&BB --:-@-@,AB.445Q8  !4RS S"5 EpHs 4F FcFSUlURR5 g)zEnables fused QKV projections.TN)fusing_transformerrSfuse_qkv_projectionsres r(r2CogVideoXVideoToVideoPipeline.fuse_qkv_projectionss"& --/r*cUR(d[RS5 gURR 5 SUlg)z)Disable QKV projection fusion if enabled.zKThe Transformer was not initially fused for QKV projections. Doing nothing.FN)rr}r~rSunfuse_qkv_projectionsrs r(r4CogVideoXVideoToVideoPipeline.unfuse_qkv_projectionss2&& NNh i    3 3 5&+D #r*rc XRURRR--nX RURRR--nURRRnURRRnURRR U-n URRR U-n Uc>[XV4X5n [URRRU XV4UUS9upX4$X8-S- U-n[URRRSXV4USX4US9upX4$)N) embed_dim crops_coords grid_size temporal_sizer,rslice)rrrr grid_typemax_sizer,) r_rSr] patch_size patch_size_t sample_width sample_heightr)rattention_head_dim)rerrrr, grid_height grid_widthpp_tbase_size_widthbase_size_heightgrid_crops_coords freqs_cos freqs_sinbase_num_framess r(%_prepare_rotary_positional_embeddingsCCogVideoXVideoToVideoPipeline._prepare_rotary_positional_embeddingssd!>!>AQAQAXAXAcAc!cd <>!C++22@@AE ; ?)?! $;**11DD.&3( $ I*## */!3;O#:**11DD!&3-!*<$ I##r*cUR$r)_guidance_scalers r(guidance_scale,CogVideoXVideoToVideoPipeline.guidance_scale+s###r*cUR$r)_num_timestepsrs r( num_timesteps+CogVideoXVideoToVideoPipeline.num_timesteps/s"""r*cUR$r)_attention_kwargsrs r(attention_kwargs.CogVideoXVideoToVideoPipeline.attention_kwargs3%%%r*cUR$r)_current_timesteprs r(current_timestep.CogVideoXVideoToVideoPipeline.current_timestep7rr*cUR$r) _interruptrs r( interrupt'CogVideoXVideoToVideoPipeline.interrupt;s r*2g?Fgpilr+r-rruse_dynamic_cfgr output_type return_dictrcallback_on_step_endrc : [U[[45(a URnU=(d- URR R UR-nU=(d- URR RUR-nUc [U5OURS5nSn URUUUUUUUUUUS9 Xl UUl SUlSUlUb[U[ 5(aSnO3Ub![U["5(a [U5nOUR$SnUR&nU S:nUR)UUUU UUUUS9unnU(a[*R,"UU/SS9n[.(aS nOUnR2UUU5upvUR5XgUU5upvUSSR7UU -5n[U5UlUS- UR:-S-nURR R<nUbUU-S:wa[?S U<S U<S 35eUc4UR@RCXUS 9nUREUURFS9nURR RHnURKUUU -UUUURFUU UU5 nURMX5n URR RN(a"URQXEURS5U5OSn![S[U5X`R2RT-- S5n"URWUS9n#Sn$[YU5GHun%n&URZ(aMU&UlU(a[*R,"U/S-5OUn'UR2R]U'U&5n'U&R_U'R$S5n(URRaS5 UR U'UU(U!USS9Sn)SSS5 W)Rc5n)U (aOSU S[dRf"[dRhUU&Rk5- U- S--5- S- --Ul U(a)U)RmS5un*n+U*URnU+U*- --n)[UR2[p5(d'UR2Rr"U)U&U40U DSS0D6SnO6UR2Rr"U)U$U&U%S:aUU%S- OSU40U DSS0D6unn$UREURF5nUb\0n,UHn-[u5U-U,U-'M U"UU%U&U,5n.U.RwSU5nU.RwSU5nU.RwSU5nU%[U5S- :Xd)U%S-U":a0U%S-UR2RT-S:XaU#Ry5 [.(dGM[zR|"5 GM SSS5 SUlUS:Xd,URU5nUR@RUUS9nOUnUR5 U(dU4$[US9$!,(df  GNt=f!,(df  N~=f)a Function invoked when calling the pipeline for generation. Args: video (`list[PIL.Image.Image]`): The input video to condition the generation on. Must be a list of images/frames of the video. 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, one has to pass `negative_prompt_embeds` instead. Ignored when not using guidance (i.e., ignored if `guidance_scale` is less than `1`). height (`int`, *optional*, defaults to self.transformer.config.sample_height * self.vae_scale_factor_spatial): The height in pixels of the generated image. This is set to 480 by default for the best results. width (`int`, *optional*, defaults to self.transformer.config.sample_height * self.vae_scale_factor_spatial): The width in pixels of the generated image. This is set to 720 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. timesteps (`list[int]`, *optional*): Custom timesteps to use for the denoising process with schedulers which support a `timesteps` argument in their `set_timesteps` method. If not defined, the default behavior when `num_inference_steps` is passed will be used. Must be in descending order. strength (`float`, *optional*, defaults to 0.8): Higher strength leads to more differences between original video and generated video. guidance_scale (`float`, *optional*, defaults to 7.0): 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. num_videos_per_prompt (`int`, *optional*, defaults to 1): The number of videos 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.FloatTensor`, *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.FloatTensor`, *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.FloatTensor`, *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_xl.StableDiffusionXLPipelineOutput`] 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. max_sequence_length (`int`, defaults to `226`): Maximum sequence length in encoded prompt. Must be consistent with `self.transformer.config.max_text_seq_length` otherwise may lead to poor results. Examples: Returns: [`~pipelines.cogvideo.pipeline_output.CogVideoXPipelineOutput`] or `tuple`: [`~pipelines.cogvideo.pipeline_output.CogVideoXPipelineOutput`] if `return_dict` is True, otherwise a `tuple`. When returning a tuple, the first element is a list with the generated images. Nr) rhrrrrrrrFrNrOFrg?)rirNrOrjr,rcpuz?The number of latent frames must be divisible by `patch_size_t=z-` but the given video contains latent_frames=z, which is not divisible.)rr)r,rk)totalrU cond_uncond) hidden_statesencoder_hidden_statesrimage_rotary_embrr g@r rFrNrOlatent)rr )r)Crvr r tensor_inputsrSr]rr_rr9rrrrrrrwrryrurrzr XLA_AVAILABLEr>r:rrrrarr1rdpreprocess_videorrk in_channelsrr use_rotary_positional_embeddingsrrr progress_bar enumeraterscale_model_inputexpand cache_contextfloatmathcospiitemchunkrrrlocalspopupdatexm mark_steprpostprocess_videomaybe_free_model_hooksr)/rerrhrrrr+r-rrrrirr@rFrNrOr r rr rrjrrr,rtimestep_devicelatent_timestep latent_framesrlatent_channelsrrnum_warmup_stepsrold_pred_original_samplertlatent_model_inputr noise_prednoise_pred_uncondnoise_pred_textcallback_kwargsrcallback_outputss/ r(__call__&CogVideoXVideoToVideoPipeline.__call__?sT *-=?U,V W W1E1S1S .`4++22@@4C`C``]))00==@]@]]#*?SZ Q ! +/Q'#9   .!1!%  *VS"9"9J  Jvt$<$<VJ&,,Q/J'' '5s&:#150B0B   '"7'#9 31C 1 - - '!II'=}&MSTUM =#O$O); NN/)* & *.););>)*&A\UYYy1}%=bi"%)^^%E%EFXZ[%\"88$6$<$r}rKr)rrwr,rrr>rFrGrJrLr0r*r(r`s  4A/I89GOO--4))MM   H %>W*'+(,"&!% 8*t8* %,,  %8*Cy4 8* K$  8*z`h TLL T-2__t-C TY\ T 5$57O 5r*