+h 4SSKrSSKJr SSKJrJrJr SSKrSSKJ r J r SSK J r SSK Jr SS KJrJr \"S S \ 55r"S S \\ 5rg)N) dataclass)OptionalTupleUnion) ConfigMixinregister_to_config) BaseOutput) randn_tensor)SchedulerMixinSchedulerOutputcV\rSrSr%Sr\R \S'\R \S'Srg) SdeVeOutputa Output class for the scheduler's `step` function output. Args: prev_sample (`torch.Tensor` of shape `(batch_size, num_channels, height, width)` for images): Computed sample `(x_{t-1})` of previous timestep. `prev_sample` should be used as next model input in the denoising loop. prev_sample_mean (`torch.Tensor` of shape `(batch_size, num_channels, height, width)` for images): Mean averaged `prev_sample` over previous timesteps. prev_sampleprev_sample_meanN) __name__ __module__ __qualname____firstlineno____doc__torchTensor__annotations____static_attributes__r`/home/james-whalen/.local/lib/python3.13/site-packages/diffusers/schedulers/scheduling_sde_ve.pyrrs ll"rrcX\rSrSrSrSr\S S\S\S\S\S\S \4 S jj5r S!S \ RS \ \S\ R4Sjjr S"S\S\S\\\ R 44SjjrS#S\S\S\S\4SjjrSrS$S\ RS \S \ RS\ \ R(S\S\\\44 SjjrS$S\ RS \ RS\ \ R(S\S\\\44 SjjrS\ RS\ RS\ RS\ R4SjrSrSrg )%ScoreSdeVeScheduler.at `ScoreSdeVeScheduler` is a variance exploding stochastic differential equation (SDE) scheduler. This model inherits from [`SchedulerMixin`] and [`ConfigMixin`]. Check the superclass documentation for the generic methods the library implements for all schedulers such as loading and saving. Args: num_train_timesteps (`int`, defaults to 1000): The number of diffusion steps to train the model. snr (`float`, defaults to 0.15): A coefficient weighting the step from the `model_output` sample (from the network) to the random noise. sigma_min (`float`, defaults to 0.01): The initial noise scale for the sigma sequence in the sampling procedure. The minimum sigma should mirror the distribution of the data. sigma_max (`float`, defaults to 1348.0): The maximum value used for the range of continuous timesteps passed into the model. sampling_eps (`float`, defaults to 1e-5): The end value of sampling where timesteps decrease progressively from 1 to epsilon. correct_steps (`int`, defaults to 1): The number of correction steps performed on a produced sample. r num_train_timestepssnr sigma_min sigma_max sampling_eps correct_stepscBX@lSUlURXXE5 gN)init_noise_sigma timesteps set_sigmas)selfr#r$r%r&r'r(s r__init__ScoreSdeVeScheduler.__init__Gs"!* + PrNsampletimestepreturncU$)aN Ensures interchangeability with schedulers that need to scale the denoising model input depending on the current timestep. Args: sample (`torch.Tensor`): The input sample. timestep (`int`, *optional*): The current timestep in the diffusion chain. Returns: `torch.Tensor`: A scaled input sample. r)r.r1r2s rscale_model_input%ScoreSdeVeScheduler.scale_model_inputYs  rnum_inference_stepsdevicecpUbUOURRn[R"SX!US9Ulg)a Sets the continuous timesteps used for the diffusion chain (to be run before inference). Args: num_inference_steps (`int`): The number of diffusion steps used when generating samples with a pre-trained model. sampling_eps (`float`, *optional*): The final timestep value (overrides value given during scheduler instantiation). device (`str` or `torch.device`, *optional*): The device to which the timesteps should be moved to. If `None`, the timesteps are not moved. Nr r8)configr'rlinspacer,)r.r7r'r8s r set_timesteps!ScoreSdeVeScheduler.set_timestepsjs/(4'?|T[[E]E] > !   2 Ay#8dnn|>["\\ $yy8KTXXV_M`bu)vwllVZVdVd#eVdQR1F10L$LVd#ef #esD#c[R"US:H[R"URUR55UR US- RUR55$)Nrr )rwhere zeros_liketor8rD)r.r,rFs rget_adjacent_sigma&ScoreSdeVeScheduler.get_adjacent_sigmasZ{{ N   QTT)"2"23 4  Q / 2 293C3C D  r model_output generator return_dictcURc [S5eU[R"URSUR S9-nU[ UR5S- -R5nURURR 5nURURUR 5nURXb5RUR 5n[R"U5n US-US-- S-n U R5n [ U R5[ UR5:a?U RS5n [ U R5[ UR5:aM?XS-U-- n [URURXCR UR S9n X9- n XU --n U(dX4$[#XS 9$) a Predict the sample from the previous timestep by reversing the SDE. This function propagates the diffusion process from the learned model outputs (most often the predicted noise). Args: model_output (`torch.Tensor`): The direct output from learned diffusion model. timestep (`int`): The current discrete timestep in the diffusion chain. sample (`torch.Tensor`): A current instance of a sample created by the diffusion process. generator (`torch.Generator`, *optional*): A random number generator. return_dict (`bool`, *optional*, defaults to `True`): Whether or not to return a [`~schedulers.scheduling_sde_ve.SdeVeOutput`] or `tuple`. Returns: [`~schedulers.scheduling_sde_ve.SdeVeOutput`] or `tuple`: If return_dict is `True`, [`~schedulers.scheduling_sde_ve.SdeVeOutput`] is returned, otherwise a tuple is returned where the first element is the sample tensor. Y`self.timesteps` is not set, you need to run 'set_timesteps' after creating the schedulerrr:r r?)layoutrOr8dtype)rr)r, ValueErrorronesshaper8lenlongrKrDrLrJflatten unsqueezer rUrVr)r.rNr2r1rOrPr,sigmaadjacent_sigmadrift diffusionnoiserrs r step_predScoreSdeVeScheduler.step_preds< >> !k ejj LLOFMM  T^^!4q!89??A LL!5!5!&U):: 2 2{VVrcURc [S5e[URURUS9R UR 5n[R"URURSS5SS9R5n[R"URURSS5SS9R5nURRU-U- S-S-nU[R"URS5R UR 5-nUR5n[UR5[UR5:a?UR!S5n[UR5[UR5:aM?X(U--n XS-S-U--n U(dU 4$[#U S9$) aI Correct the predicted sample based on the `model_output` of the network. This is often run repeatedly after making the prediction for the previous timestep. Args: model_output (`torch.Tensor`): The direct output from learned diffusion model. sample (`torch.Tensor`): A current instance of a sample created by the diffusion process. generator (`torch.Generator`, *optional*): A random number generator. return_dict (`bool`, *optional*, defaults to `True`): Whether or not to return a [`~schedulers.scheduling_sde_ve.SdeVeOutput`] or `tuple`. Returns: [`~schedulers.scheduling_sde_ve.SdeVeOutput`] or `tuple`: If return_dict is `True`, [`~schedulers.scheduling_sde_ve.SdeVeOutput`] is returned, otherwise a tuple is returned where the first element is the sample tensor. rR)rUrOrrT)dimrrS)r)r,rWr rYrUrKr8rnormreshapemeanr;r$rXr\rZr]r) r.rNr1rOrPrb grad_norm noise_norm step_sizerrs r step_correct ScoreSdeVeScheduler.step_corrects6 >> !k  V\\&--9UXXY_YfYfgJJ|33L4F4Fq4I2NTVW\\^ ZZ ekk!nb ArJOOQ [[__z1I=!CaG  6<<? ; > >v}} MM %%' )//"S%66!++B/I)//"S%66! $<<&q=S*@E)II > !;77roriginal_samplesrbr,cURUR5nURRUR5UnUb X$SS2SSS4-O![R"U5USS2SSS4-nX!-nU$r*)rKr8rDr randn_like)r.rorbr,r@ noisy_sampless r add_noiseScoreSdeVeScheduler.add_noisesLL!1!8!89 %%(()9)@)@A)L  1dD$./ /!!"23fQdD=P6QQ  0 rc.URR$r*)r;r#)r.s r__len__ScoreSdeVeScheduler.__len__,s{{...r)rDr+r@r,)ig333333?g{Gz?g@gh㈵>r r*)NN)NNN)NT)rrrrrorderr intfloatr/rrrr5rstrr8r=r-rL Generatorboolrrrcrrmrsrvrrrrr!r!.s, E$(!"Q QQ Q  Q  QQQ"  Y^YeYe$hl]#&]6;]LQRUW\WcWcRcLd](qug#&g38gLQghmg8 04 BWllBWBW BW EOO, BW  BW {E! "BWP04 58ll58 58EOO, 58  58 % & 58n,,||<<   "/rr!)rB dataclassesrtypingrrrrconfiguration_utilsrr utilsr utils.torch_utilsr scheduling_utilsr rrr!rrrrsM" !)) A,=  #* #  # /.+/r