+h,LSSKrSSKJr SSKJrJrJrJr SSKrSSK J r J r SSK J r Jr SSKJr SS KJr \R&"\5r\"S S \ 55r"S S \\ 5rg)N) dataclass)ListOptionalTupleUnion) ConfigMixinregister_to_config) BaseOutputlogging) randn_tensor)SchedulerMixinc`\rSrSr%Sr\R \S'Sr\ \R \S'Sr g)EDMEulerSchedulerOutputaM 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. pred_original_sample (`torch.Tensor` of shape `(batch_size, num_channels, height, width)` for images): The predicted denoised sample `(x_{0})` based on the model output from the current timestep. `pred_original_sample` can be used to preview progress or for guidance. prev_sampleNpred_original_sample) __name__ __module__ __qualname____firstlineno____doc__torchTensor__annotations__rr__static_attributes__rc/home/james-whalen/.local/lib/python3.13/site-packages/diffusers/schedulers/scheduling_edm_euler.pyrrs' 37(5<<07rrc*\rSrSrSr/rSr\S6S\S\S\S\ S\ S \ S \S \ 4S jj5r \ S 5r \ S5r\ S5rS7S\ 4SjjrSrSrSrS\R*S\\\R*4S\R*4SjrS8S\ S\\ \R04S\\\R*\\44SjjrS9S\R*4SjjrS9S\R*4SjjrS:S jrS!rS"S"\"S#5S$SS%S4S&\R*S\\\R*4S\R*S'\S(\S)\S*\S+\\R@S,\!S-\\R*S\\"\#44S.jjr$S/\R*S0\R*S1\R*S\R*4S2jr%S3r&S4r'S5r(g);EDMEulerScheduler1a Implements the Euler scheduler in EDM formulation as presented in Karras et al. 2022 [1]. [1] Karras, Tero, et al. "Elucidating the Design Space of Diffusion-Based Generative Models." https://huggingface.co/papers/2206.00364 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: sigma_min (`float`, *optional*, defaults to 0.002): Minimum noise magnitude in the sigma schedule. This was set to 0.002 in the EDM paper [1]; a reasonable range is [0, 10]. sigma_max (`float`, *optional*, defaults to 80.0): Maximum noise magnitude in the sigma schedule. This was set to 80.0 in the EDM paper [1]; a reasonable range is [0.2, 80.0]. sigma_data (`float`, *optional*, defaults to 0.5): The standard deviation of the data distribution. This is set to 0.5 in the EDM paper [1]. sigma_schedule (`str`, *optional*, defaults to `karras`): Sigma schedule to compute the `sigmas`. By default, we the schedule introduced in the EDM paper (https://huggingface.co/papers/2206.00364). Other acceptable value is "exponential". The exponential schedule was incorporated in this model: https://huggingface.co/stabilityai/cosxl. num_train_timesteps (`int`, defaults to 1000): The number of diffusion steps to train the model. prediction_type (`str`, defaults to `epsilon`, *optional*): Prediction type of the scheduler function; can be `epsilon` (predicts the noise of the diffusion process), `sample` (directly predicts the noisy sample`) or `v_prediction` (see section 2.4 of [Imagen Video](https://imagen.research.google/video/paper.pdf) paper). rho (`float`, *optional*, defaults to 7.0): The rho parameter used for calculating the Karras sigma schedule, which is set to 7.0 in the EDM paper [1]. final_sigmas_type (`str`, defaults to `"zero"`): The final `sigma` value for the noise schedule during the sampling process. If `"sigma_min"`, the final sigma is the same as the last sigma in the training schedule. If `zero`, the final sigma is set to 0. r sigma_min sigma_max sigma_datasigma_schedulenum_train_timestepsprediction_typerhofinal_sigmas_typec rUS;a[SU<S35eSUl[RRR 5(a[R O[Rn [R"US-U S9U- n US:XaURU 5n OUS:XaURU 5n U R[R 5n URU 5Ul URRS:XaU S n O?URRS :XaS n O"[S URR35e[R "U [R""S XR$S9/5UlSUlSUlSUlUR&RS5Ulg)N)karras exponentialz-Wrong value for provided for `sigma_schedule=z`.`rdtyper-r.r$zerorC`final_sigmas_type` must be one of 'zero', or 'sigma_min', but got r fill_valuedeviceFcpu) ValueErrornum_inference_stepsrbackendsmps is_availablefloat32float64arange_compute_karras_sigmas_compute_exponential_sigmastoprecondition_noise timestepsconfigr+catfullr7sigmasis_scale_input_called _step_index _begin_index) selfr$r%r&r'r(r)r*r+ sigmas_dtyperI sigma_lasts r __init__EDMEulerScheduler.__init__Xso !: :Mn=NcRS S$( (-(:(:(G(G(I(Iu}}u}} 1A5\JM`` X %008F } ,55f=F5==)008 ;; ( (K 7J [[ * *f 4JUVZVaVaVsVsUtu iiDZXeXe)f gh %*" kknnU+ rc@URRS-S-S-$)Nrr?)rFr%rMs r init_noise_sigma"EDMEulerScheduler.init_noise_sigmas# %%q(1,44rcUR$)zW The index counter for current timestep. It will increase 1 after each scheduler step. )rKrTs r step_indexEDMEulerScheduler.step_indexs rcUR$)za The index for the first timestep. It should be set from pipeline with `set_begin_index` method. rLrTs r begin_indexEDMEulerScheduler.begin_indexs    rr\cXlg)z Sets the begin index for the scheduler. This function should be run from pipeline before the inference. Args: begin_index (`int`): The begin index for the scheduler. Nr[)rMr\s r set_begin_index!EDMEulerScheduler.set_begin_indexs (rc0URU5nX-nU$N)_get_conditioning_c_in)rMsamplesigmac_in scaled_samples r precondition_inputs%EDMEulerScheduler.precondition_inputss**51 rc[U[R5(d[R"U/5nS[R"U5-nU$)Ng?) isinstancerrtensorlog)rMrec_noises r rD$EDMEulerScheduler.precondition_noises;%..LL%)E5))rchURRnUS-US-US--- nURRS:XaX4-US-US--S-- nOSURRS:XaU*U-US-US--S-- nO#[SURRS35eXQ-Xb--nU$)NrepsilonrS v_predictionzPrediction type z is not supported.)rFr&r)r9)rMrd model_outputrer&c_skipc_outdenoiseds r precondition_outputs&EDMEulerScheduler.precondition_outputss[[++ Q%(Z]":; ;; & &) 3&%(Z]*Bs)JJE [[ ( (N :FZ'5!8j!m+C*KKE/ 0K0K/LL^_` `?U%99rrdtimestepreturncURcURU5 URURnURX5nSUlU$)a Ensures interchangeability with schedulers that need to scale the denoising model input depending on the current timestep. Scales the denoising model input by `(sigma**2 + 1) ** 0.5` to match the Euler algorithm. Args: sample (`torch.Tensor`): The input sample. timestep (`int`, *optional*): The current timestep in the diffusion chain. Returns: `torch.Tensor`: A scaled input sample. T)rX_init_step_indexrIrhrJ)rMrdryres r scale_model_input#EDMEulerScheduler.scale_model_inputsK ?? "  ! !( + DOO,))&8%)" rNr:r7rIc Xl[RRR 5(a[R O[R nUc"[R"SSURUS9nO;[U[5(a[R"X4S9nOURU5nURRS:XaURU5nO+URRS:XaURU5nUR[R US9nUR!U5UlURR$S:XaUS nO?URR$S :XaSnO"['S URR$35e[R("U[R*"S XSR,S 9/5UlSUlSUlUR.RS5Ulg)aJ Sets the discrete timesteps used for the diffusion chain (to be run before inference). Args: num_inference_steps (`int`): The number of diffusion steps used when generating samples with a pre-trained model. device (`str` or `torch.device`, *optional*): The device to which the timesteps should be moved to. If `None`, the timesteps are not moved. sigmas (`Union[torch.Tensor, List[float]]`, *optional*): Custom sigmas to use for the denoising process. If not defined, the default behavior when `num_inference_steps` is passed will be used. Nrrr/r-r.)r0r7r$r1r2r3r4r5r8)r:rr;r<r=r>r?linspacerkfloatrlrCrFr'rArBrDrEr+r9rGrHr7rIrKrL)rMr:r7rIrNrOs r set_timestepsEDMEulerScheduler.set_timestepss$$7 (-(:(:(G(G(I(Iu}}u}} >^^Aq$*B*B,WF  & &\\&=FYY|,F ;; % % 1008F [[ ' '= 855f=Fv>008 ;; ( (K 7J [[ * *f 4JUVZVaVaVsVsUtu iiDZXeXe)f gh  kknnU+ rcU=(d URRnU=(d URRnURRnUSU- -nUSU- -nXaXV- --U-nU$)z6Constructs the noise schedule of Karras et al. (2022).r)rFr$r%r*)rMrampr$r%r* min_inv_rho max_inv_rhorIs r rA(EDMEulerScheduler._compute_karras_sigmas sm6!6!6 6!6!6 kkooAG, AG,  (A BBsJ rcNU=(d URRnU=(d URRn[R"[ R "U5[ R "U5[U55R5RS5nU$)zImplementation closely follows k-diffusion. https://github.com/crowsonkb/k-diffusion/blob/6ab5146d4a5ef63901326489f31f1d8e7dd36b48/k_diffusion/sampling.py#L26 r) rFr$r%rrmathrmlenexpflip)rMrr$r%rIs r rB-EDMEulerScheduler._compute_exponential_sigmassn 6!6!6 6!6!6  3TXXi5H#d)TXXZ__`ab rcUc URnX!:HR5n[U5S:aSOSnX4R5$)Nrr)rEnonzeroritem)rMryschedule_timestepsindicesposs r index_for_timestep$EDMEulerScheduler.index_for_timestepsH  %!% %1::< wrIminrr shaper0r7rwrKr)rMrsryrdrrrrrrrregamma sigma_hatnoiseeps derivativedtrs r stepEDMEulerScheduler.step6sP heoou7G7G H I IG )) NNE  ?? "  ! !( +5==) DOO,EKE^X^E^Gs4;;/!34jAdgQY' 19 "",*<*<\EXEXdmE/CY\E1H%<$DDDF '#'#<#r\rrXrflattenr unsqueeze) rMrrrErIrt step_indicesre noisy_sampless r add_noiseEDMEulerScheduler.add_noises'7'>'>FVF\F\]  " " ' '5 0U5L5LY5W5W!%!2!23C3J3JRWR_R_!2!` ! %5%<%rs_ !// A',,   H % 8j8 8"O/ O/r