+hirSSKrSSKJrJrJrJrJrJr SSKr SSK r SSK J r J r SSKJrJr SSKJr SSKJrJr SSKJr SS KJrJrJrJr SS KJr SS KJ r S S K!J"r" SSK#J$r$ \"5(a SSK%J&s J'r( Sr)OSr)\RT"\+5r,\"5(aSSK-r-Sr.Sr/Sr0Sr1"SS\"\5r2g)N)AnyCallableDictListOptionalUnion) AutoTokenizerUMT5EncoderModel)MultiPipelineCallbacksPipelineCallback)SkyReelsV2LoraLoaderMixin)AutoencoderKLWanSkyReelsV2Transformer3DModel)UniPCMultistepScheduler)is_ftfy_availableis_torch_xla_availableloggingreplace_example_docstring) randn_tensor)VideoProcessor)DiffusionPipeline)SkyReelsV2PipelineOutputTFas Examples: ```py >>> import torch >>> from diffusers import ( ... SkyReelsV2Pipeline, ... UniPCMultistepScheduler, ... AutoencoderKLWan, ... ) >>> from diffusers.utils import export_to_video >>> # Load the pipeline >>> # Available models: >>> # - Skywork/SkyReels-V2-T2V-14B-540P-Diffusers >>> # - Skywork/SkyReels-V2-T2V-14B-720P-Diffusers >>> vae = AutoencoderKLWan.from_pretrained( ... "Skywork/SkyReels-V2-T2V-14B-720P-Diffusers", ... subfolder="vae", ... torch_dtype=torch.float32, ... ) >>> pipe = SkyReelsV2Pipeline.from_pretrained( ... "Skywork/SkyReels-V2-T2V-14B-720P-Diffusers", ... vae=vae, ... torch_dtype=torch.bfloat16, ... ) >>> flow_shift = 8.0 # 8.0 for T2V, 5.0 for I2V >>> pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config, flow_shift=flow_shift) >>> pipe = pipe.to("cuda") >>> prompt = "A cat and a dog baking a cake together in a kitchen. The cat is carefully measuring flour, while the dog is stirring the batter with a wooden spoon. The kitchen is cozy, with sunlight streaming through the window." >>> output = pipe( ... prompt=prompt, ... num_inference_steps=50, ... height=544, ... width=960, ... guidance_scale=6.0, # 6.0 for T2V, 5.0 for I2V ... num_frames=97, ... ).frames[0] >>> export_to_video(output, "video.mp4", fps=24, quality=8) ``` c[R"U5n[R"[R"U55nUR 5$N)ftfyfix_texthtmlunescapestriptexts n/home/james-whalen/.local/lib/python3.13/site-packages/diffusers/pipelines/skyreels_v2/pipeline_skyreels_v2.py basic_cleanr&Zs3 == D ==t, -D ::<cV[R"SSU5nUR5nU$)Nz\s+ )resubr"r#s r%whitespace_cleanr,`s$ 66&#t $D ::transformer->vae)latents prompt_embedsnegative_prompt_embeds tokenizer text_encoder transformervae schedulercd>[TU]5 URUUUUUS9 [USS5(a"S[ UR R 5-OSUl[USS5(a"S[UR R 5-OSUl [URS9Ul g)N)r8r6r5r7r9r8r)vae_scale_factor) super__init__register_modulesgetattrsumr8temperal_downsamplevae_scale_factor_temporallenvae_scale_factor_spatialrvideo_processor)selfr5r6r7r8r9 __class__s r%r?SkyReelsV2Pipeline.__init__s  %#  T[[_afhlSmSmc$((2N2N.O)Ost&RYZ^`egkRlRlS1M1M-N(Nrs%-t?\?\]r'Nrpromptnum_videos_per_promptmax_sequence_lengthdevicedtypecU=(d URnU=(d URRn[U[5(aU/OUnUVs/sHn[ U5PM nn[ U5nURUSUSSSSS9nURURpU RS5RSS9R5n URU RU5U RU55Rn U RXTS9n [X5VV s/sH upmUSU PM n nn [ R""U Vs/sHJn[ R$"XfR'X6R)S5- UR)S55/5PML snSS9n U R*upnU R-SUS5n U R/Xr-US 5n U $s snfs sn nfs snf) N max_lengthTpt)paddingrQ truncationadd_special_tokensreturn_attention_maskreturn_tensorsrr)dim)rOrN)_execution_devicer6rO isinstancestrr.rEr5 input_idsattention_maskgtrBlongtolast_hidden_stateziptorchstackcat new_zerossizeshaperepeatview)rHrKrLrMrNrOu batch_size text_inputstext_input_idsmaskseq_lensr3v_seq_lens r%_get_t5_prompt_embeds(SkyReelsV2Pipeline._get_t5_prompt_embedss14110**00'44&&+126a,q/62[ nn  *#"&%  +44k6P6P771:>>a>(--/)).*;*;F*CTWWV_Ugg %((u(D +.}+GH+G412A+G H ^k l^kYZUYY;;':VVAY'Fq RS T^k lrs &++ A%,,Q0EqI %**:+MwXZ[ 73"I lsG$G! AG'Tnegative_promptdo_classifier_free_guidancer3r4c 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)rKrLrMrNrOz?`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`.) rZr[r\rErirutype TypeError ValueError) rHrKrwrxrLr3r4rMrNrOrms r% encode_prompt SkyReelsV2Pipeline.encode_promptskL1411'44&&  VJ&,,Q/J   66&;$7 7M '+A+I-3O@J?\_@`@`j+<# UHoTR;v M g7fr)_callback_tensor_inputs).0krHs r% 2SkyReelsV2Pipeline.check_inputs..#sF 7Y!-- -7Ysz2`callback_on_step_end_tensor_inputs` has to be in z , but found zCannot forward both `prompt`: z and `prompt_embeds`: z2. Please make sure to only forward one of the two.z'Cannot forward both `negative_prompt`: z and `negative_prompt_embeds`: zeProvide either `prompt` or `prompt_embeds`. Cannot leave both `prompt` and `prompt_embeds` undefined.z2`prompt` has to be of type `str` or `list` but is z;`negative_prompt` has to be of type `str` or `list` but is )r~allrr[r\listr|) rHrKrwheightwidthr3r4"callback_on_step_end_tensor_inputsrs ` r% check_inputsSkyReelsV2Pipeline.check_inputss B;! urzQWX^W__dejdkklmn n - 9#F 7YF C C DTEaEaDbbn|^pH|^vwkokGkGbGpq|^pHoIJ   -";08N}o^00  (-C-O9/9JJikAjBB00 ^ 5w  FC)@)@TZ\`IaIaQRVW]R^Q_`a a  (?C00OUY9Z9ZZ[_`o[pZqrs s:[0)'pHs E 1E rmnum_channels_latentsrr num_frames generatorr2returnc LU bU RXvS9$US- UR-S-n UUU [U5UR-[U5UR-4n [ U[ 5(a*[ U5U:wa[S[ U5SUS35e[XXvS9n U $)N)rNrOrz/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.)rrNrO) rarDintrFr[rrEr~r) rHrmrrrrrOrNrr2num_latent_framesris r%prepare_latents"SkyReelsV2Pipeline.prepare_latents@s  ::V:9 9'!^0N0NNQRR   K488 8 J$77 7   i & &3y>Z+GA#i.AQR&<'gi  u&Vr'cUR$r_guidance_scalerHs r%guidance_scale!SkyReelsV2Pipeline.guidance_scale`s###r'c URS:$)N?rrs r%rx.SkyReelsV2Pipeline.do_classifier_free_guidanceds##c))r'cUR$r)_num_timestepsrs r% num_timesteps SkyReelsV2Pipeline.num_timestepshs"""r'cUR$r)_current_timesteprs r%current_timestep#SkyReelsV2Pipeline.current_timestepl%%%r'cUR$r) _interruptrs r% interruptSkyReelsV2Pipeline.interruptps r'cUR$r)_attention_kwargsrs r%attention_kwargs#SkyReelsV2Pipeline.attention_kwargstrr'i ia2g@npinum_inference_stepsr output_type return_dictrcallback_on_step_endrc  [U[[45(a URnUR UUUUU U U5 XPR -S:waA[ RSUR S35 XPR -UR -S-n[US5nXpl Xl SUl SUl URnUb[U[5(aSnO3Ub![U[5(a [!U5nOU R"SnUR%UUUR&UU U UUS9upUR(R*nU R-U5n U bU R-U5n UR.R1UUS9 UR.R2nUR(R4R6nUR9UU-UUUU[:R<UU U 5 n [!U5X`R.R>-- n[!U5Ul URCUS 9n[EU5GHunnURF(aMUUl U R-U5nURIU R"S5nUR)UUU USS 9SnUR&(a!UR)UUU USS 9SnUUUU- --nUR.RKUUU SS 9Sn Ub\0n UHn![M5U!U U!'M U"UUUU 5n"U"ROS U 5n U"ROS U 5n U"ROSU 5n U[!U5S- :Xd)US-U:a0US-UR.R>-S:XaURQ5 [R(dGMo[TRV"5 GM SSS5 SUl U S:XGdzU R-URXR*5n [:RZ"URXR4R\5R_SURXR4R`SSS5R-U RbU R*5n#S[:RZ"URXR4Rd5R_SURXR4R`SSS5R-U RbU R*5- n$U U$- U#-n URXRgU SS 9Sn%URhRkU%U S9n%OU n%URm5 U(dU%4$[oU%S9$!,(df  GN=f)a The call function to 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`, defaults to `544`): The height in pixels of the generated image. width (`int`, defaults to `960`): The width in pixels of the generated image. num_frames (`int`, defaults to `97`): The number of frames in the generated video. num_inference_steps (`int`, defaults to `50`): The number of denoising steps. More denoising steps usually lead to a higher quality image at the expense of slower inference. guidance_scale (`float`, defaults to `6.0`): Guidance scale as defined in [Classifier-Free Diffusion Guidance](https://arxiv.org/abs/2207.12598). `guidance_scale` is defined as `w` of equation 2. of [Imagen Paper](https://arxiv.org/pdf/2205.11487.pdf). 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 images to generate per prompt. generator (`torch.Generator` or `List[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`. prompt_embeds (`torch.Tensor`, *optional*): Pre-generated text embeddings. Can be used to easily tweak text inputs (prompt weighting). If not provided, text embeddings are generated from the `prompt` input argument. output_type (`str`, *optional*, defaults to `"np"`): 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 [`SkyReelsV2PipelineOutput`] 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`, `PipelineCallback`, `MultiPipelineCallbacks`, *optional*): A function or a subclass of `PipelineCallback` or `MultiPipelineCallbacks` that is called at the end of each denoising step during the inference. 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`, *optional*, defaults to `512`): The maximum sequence length for the text encoder. Examples: Returns: [`~SkyReelsV2PipelineOutput`] or `tuple`: If `return_dict` is `True`, [`SkyReelsV2PipelineOutput`] is returned, otherwise a `tuple` is returned where the first element is a list with the generated images and the second element is a list of `bool`s indicating whether the corresponding generated image contains "not-safe-for-work" (nsfw) content. rz(`num_frames - 1` has to be divisible by z!. Rounding to the nearest number.NFr)rKrwrxrLr3r4rMrN)rN)total) hidden_statestimestepencoder_hidden_statesrr)rr2r3r4latentr)r)frames)8r[r r tensor_inputsrrDloggerwarningmaxrrrrrZr\rrErirrxr7rOrar9 set_timesteps timestepsconfig in_channelsrrdfloat32orderr progress_bar enumeraterexpandsteplocalspopupdate XLA_AVAILABLExm mark_stepr8tensor latents_meanrkz_dimrN latents_stddecoderGpostprocess_videomaybe_free_model_hooksr)&rHrKrwrrrrrrLrr2r3r4rrrrrrMrNrmtransformer_dtyperrnum_warmup_stepsritlatent_model_inputr noise_pred noise_uncondcallback_kwargsrcallback_outputsrrvideos& r%__call__SkyReelsV2Pipeline.__call__xsZp *-=?U,V W W1E1S1S .       " .  66 6! ; NN:4;Y;Y:ZZ{| $'E'EEHfHffijjJQ' -!1!%''  *VS"9"9J  Jvt$<$<VJ&,,Q/J150B0B+(,(H(H"7'#9 31C 1 - !,,22%(():; ! -%;%>%>?P%Q " $$%8$HNN,,  $//66BB&& . .    MM     y>,?..BVBV,VV!)n   %8  9\!),1>>)*&%,ZZ0A%B"88GMM!$45!--"4%*7%5 % .   33#'#3#3&8!).D)9$) $4$  $L".*|B[0\!\J..--j!WRW-XYZ['3&(O?-3Xa[*@';D!Q'X$.229gFG$4$8$8-$XM-=-A-ABZ\r-s*I**A9I/IqSTuX\XfXfXlXlNlpqNq '') =LLNY-:^"&h&jj0G TXX__99:a..1a8GNNGMM2   TXX__-H-H I N NqRVRZRZRaRaRgRgijlmop q t t !K +l:GHHOOGO?BE((::5k:ZEE ##%8O'u55O: 9s,E6U6'U66 V)rrrrrrFrDrG)NrNN)NTrNNrNN)NNN)rii@QNNNN)/__name__ __module__ __qualname____firstlineno____doc__model_cpu_offload_seqrr r rrrr?rr\rrrrdrNrOruboolTensorrr Generatorrpropertyrrxrrrrno_gradrEXAMPLE_DOC_STRINGfloatrrrr r r__static_attributes__ __classcell__)rIs@r%r0r0ks*=T^ ^'^2 ^  ^ + ^2)-%&#&)-'+ 'c49n%' #'! ' & '  $ 'Z<@,0%&049=#&)-'+O5c49n%O5"%T#Y"78O5&* O5 # O5   - O5!) 6O5!O5&O5 $O5n#+/'tZ%''+)-MQ*."      $&E%//43H"HIJ%,,' @$$**##&&&& ]]_12)-15#% #/0MQ*.049=%) 59 9B #&+h6c49n%h6sDI~.h6 h6  h6  h6!h6h6 (}h6E%//43H"HIJh6%,,'h6  -h6!) 6h6c]h6h6 #4S>2!h6"' (Cd+T124DF\\ ] #h6(-1I)h6*!+h63h6r'r0)3r typingrrrrrrregexr*rd transformersr r callbacksr r loadersrmodelsrr schedulersrutilsrrrrutils.torch_utilsrrGrpipeline_utilsrpipeline_outputrtorch_xla.core.xla_modelcore xla_modelrr get_loggerrrrrr&r,r.r0r'r%r s == 8A0D1bb--.5))MM   H %)X   w6*,Ew6r'