3j SSKrSSKJr SSKrSSKrSSKJrJr SSK J r J r SSK J r JrJr \ "5(aSSKrSS\S \S \S S \R(4S jjr"SS\\5rg)N)Literal) ConfigMixinregister_to_config) deprecateis_scipy_available)KarrasDiffusionSchedulersSchedulerMixinSchedulerOutputnum_diffusion_timestepsmax_betaalpha_transform_type)cosineexplaplacereturnc :US:XaSnO"US:XaSnOUS:XaSnO[SU35e/n[U5H<nXP- nUS-U- nUR[SU"U5U"U5- - U55 M> [R "U[R S 9$) a Create a beta schedule that discretizes the given alpha_t_bar function, which defines the cumulative product of (1-beta) over time from t = [0,1]. Contains a function alpha_bar that takes an argument t and transforms it to the cumulative product of (1-beta) up to that part of the diffusion process. Args: num_diffusion_timesteps (`int`): The number of betas to produce. max_beta (`float`, defaults to `0.999`): The maximum beta to use; use values lower than 1 to avoid numerical instability. alpha_transform_type (`str`, defaults to `"cosine"`): The type of noise schedule for `alpha_bar`. Choose from `cosine`, `exp`, or `laplace`. Returns: `torch.Tensor`: The betas used by the scheduler to step the model outputs. rch[R"US-S- [R-S- 5S-$)NgMb?gT㥛 ?r)mathcospits h/home/wildlama/miniconda3/lib/python3.13/site-packages/diffusers/schedulers/scheduling_deis_multistep.py alpha_bar_fn)betas_for_alpha_bar..alpha_bar_fn<s-88QY%/$''9A=>!C Crc S[R"SSU- 5-[R"SS[R"SU- 5-- S-5-n[R"U5n[R "USU-- 5$)Ngr ?rgư>)rcopysignlogfabsrsqrt)rlmbsnrs rrrAsmq#'22TXXa!diiPSVWPWFXBX>X[_>_5``C((3-C99SAG_- -rrc4[R"US-5$)Ng()rrrs rrrHs88AI& &rz"Unsupported alpha_transform_type: r dtype) ValueErrorrangeappendmintorchtensorfloat32)r rrrbetasit1t2s rbetas_for_alpha_barr5"s0x' D  * .  & '=>R=STUU E * +  (!e. . S\"- R0@@@(KL, <<U]] 33rc0\rSrSrSr\VVs/sHoR PM snnrSr\ SKS\ S \ S \ S \ S S \ R\\ -S-S\ S\ SS\S\ S\ S\ SS\ SS\S\S\S\S\S\ S\ SS\ S\S \ SS!S4.S"jj5r\S!\ 4S#j5r\S!\ 4S$j5rSLS%\ S!S4S&jjrSMS'\ S(\\R0-S)\ S-4S*jjrS+\R4S!\R44S,jrS-\ RS.\ RS!\ R4S/jrS-\R4S!\\R4\R444S0jrS1\R4S'\ S!\R44S2jrS1\R4S'\ S!\R44S3jr SNS1\R4S'\ S4\ S5\ S!\R44 S6jjr!SS7.S8\R4S+\R4S!\R44S9jjr"SS7.S8\R4S+\R4S!\R44S:jjr#SS7.S;\\R4S+\R4S!\R44S<jjr$SS7.S;\\R4S+\R4S!\R44S=jjr%SOS>\ \R4-S?\R4S-S!\ 4S@jjr&S>\ \R4-S!S4SAjr'SPS8\R4S>\ \R4-S+\R4SB\S!\(\-4 SCjjr)S+\R4S!\R44SDjr*SE\R4SF\R4SG\RVS!\R44SHjr,S!\ 4SIjr-SJr.gs snnf)QDEISMultistepSchedulerVu( `DEISMultistepScheduler` is a fast high order solver for diffusion ordinary differential equations (ODEs). 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. beta_start (`float`, defaults to `0.0001`): The starting `beta` value of inference. beta_end (`float`, defaults to `0.02`): The final `beta` value. beta_schedule (`"linear"`, `"scaled_linear"`, or `"squaredcos_cap_v2"`, defaults to `"linear"`): The beta schedule, a mapping from a beta range to a sequence of betas for stepping the model. Choose from `linear`, `scaled_linear`, or `squaredcos_cap_v2`. trained_betas (`np.ndarray` or `list[float]`, *optional*): Pass an array of betas directly to the constructor to bypass `beta_start` and `beta_end`. solver_order (`int`, defaults to `2`): The DEIS order which can be `1` or `2` or `3`. It is recommended to use `solver_order=2` for guided sampling, and `solver_order=3` for unconditional sampling. prediction_type (`"epsilon"`, `"sample"`, `"v_prediction"`, or `"flow_prediction"`, defaults to `"epsilon"`): Prediction type of the scheduler function; can be `epsilon` (predicts the noise of the diffusion process), `sample` (directly predicts the noisy sample`), `v_prediction` (see section 2.4 of [Imagen Video](https://huggingface.co/papers/2210.02303) paper), or `flow_prediction`. thresholding (`bool`, defaults to `False`): Whether to use the "dynamic thresholding" method. This is unsuitable for latent-space diffusion models such as Stable Diffusion. dynamic_thresholding_ratio (`float`, defaults to `0.995`): The ratio for the dynamic thresholding method. Valid only when `thresholding=True`. sample_max_value (`float`, defaults to `1.0`): The threshold value for dynamic thresholding. Valid only when `thresholding=True`. algorithm_type (`"deis"`, defaults to `"deis"`): The algorithm type for the solver. solver_type (`"logrho"`, defaults to `"logrho"`): Solver type for DEIS. lower_order_final (`bool`, defaults to `True`): Whether to use lower-order solvers in the final steps. Only valid for < 15 inference steps. use_karras_sigmas (`bool`, *optional*, defaults to `False`): Whether to use Karras sigmas for step sizes in the noise schedule during the sampling process. If `True`, the sigmas are determined according to a sequence of noise levels {σi}. use_exponential_sigmas (`bool`, *optional*, defaults to `False`): Whether to use exponential sigmas for step sizes in the noise schedule during the sampling process. use_beta_sigmas (`bool`, *optional*, defaults to `False`): Whether to use beta sigmas for step sizes in the noise schedule during the sampling process. Refer to [Beta Sampling is All You Need](https://huggingface.co/papers/2407.12173) for more information. use_flow_sigmas (`bool`, *optional*, defaults to `False`): Whether to use flow sigmas for step sizes in the noise schedule during the sampling process. flow_shift (`float`, *optional*, defaults to `1.0`): The flow shift parameter for flow-based models. timestep_spacing (`"linspace"`, `"leading"`, or `"trailing"`, defaults to `"linspace"`): The way the timesteps should be scaled. Refer to Table 2 of the [Common Diffusion Noise Schedules and Sample Steps are Flawed](https://huggingface.co/papers/2305.08891) for more information. steps_offset (`int`, defaults to `0`): An offset added to the inference steps, as required by some model families. use_dynamic_shifting (`bool`, defaults to `False`): Whether to use dynamic shifting for the noise schedule. time_shift_type (`"exponential"`, defaults to `"exponential"`): The type of time shifting to apply. r Ndeislogrho exponentialnum_train_timesteps beta_startbeta_end beta_schedule)linear scaled_linearsquaredcos_cap_v2 trained_betas solver_orderprediction_type)epsilonsample v_predictionflow_prediction thresholdingdynamic_thresholding_ratiosample_max_valuealgorithm_type solver_typelower_order_finaluse_karras_sigmasuse_exponential_sigmasuse_beta_sigmasuse_flow_sigmas flow_shifttimestep_spacing)linspaceleadingtrailing steps_offsetuse_dynamic_shiftingtime_shift_typercURR(a[5(d [S5e[ URRURR URR /5S:a [S5eUb)[R"U[RS9Ul OUS:Xa*[R"X#U[RS9Ul OkUS:Xa4[R"US-US-U[RS9S-Ul O1US :Xa[U5Ul O[US UR35eS UR- Ul[R""UR S S 9Ul[R&"UR$5Ul[R&"SUR$- 5Ul[R,"UR(5[R,"UR*5- UlSUR$- UR$- S-UlS UlU S;a0U S;aUR5SS9 O[U S UR35eU S;a1U S;aUR5SS9 O[SU S UR35eSUl"S US- U[8RS9SSS2R;5n[R<"U5UlS/U-Ul S Ul!SUl"SUl#UR0RIS5Ulg)Nz:Make sure to install scipy if you want to use beta sigmas.r znOnly one of `config.use_beta_sigmas`, `config.use_exponential_sigmas`, `config.use_karras_sigmas` can be used.r(r@rAr rrBz is not implemented for ?rdim)r9) dpmsolverz dpmsolver++r9)rM)r:)midpointheunbh1bh2r:)rNz solver type cpu)%configrRr ImportErrorsumrQrPr*r.r/r0r1rVr5NotImplementedError __class__alphascumprodalphas_cumprodr$alpha_tsigma_tr"lambda_tsigmasinit_noise_sigmarnum_inference_stepsnpcopy from_numpy timesteps model_outputslower_order_nums _step_index _begin_indexto)selfr<r=r>r?rCrDrErJrKrLrMrNrOrPrQrRrSrTrUrYrZr[rxs r__init__DEISMultistepScheduler.__init__s4 ;; & &/A/C/CZ[ [ KK//KK66KK11  A   $m5==IDJ h & >QY^YfYfgDJ o -OcM'--    J1 1,-@ADJ%7OPTP^P^O_&`a aDJJ& #mmDKKQ?zz$"5"56 zz!d&9&9"9:  $,,/%))DLL2II D///43F3FF3N !$  )!==''v'>)^,<;;33 8S8SWd8d dd%'VVBZDKK " ;; ' ': 5 At{{>>BDWZ[D[\2"$!  [[ ) )Y 688=PST=TUJ1&9A&=>KRRTUYWYUYZ[^\^_ddfmmnpnvnvwI 11 1I [[ ) )Z 788;NNJ $++"A"A1zkRXXZ__ahhikiqiqrI NI;;//01JK A 3 33t7J7JJsRSVVF^ ;; ( (WWV_))+F,,v,gFSY!ZSY%"2"25"ESY!Z[aacI^^VBC[$9:AA"**MF [[ / /WWV_))+F11F1lFSY!ZSY%"2"25"ESY!Z[I^^VBC[$9:AA"**MF [[ ( (WWV_))+F**V*eFSY!ZSY%"2"25"ESY!Z[I^^VBC[$9:AA"**MF [[ ( ([[A (G(G$GI\_`I`aF6\FWWT[[33f<T[[E[E[^_E_ciDi@ijklomopuuwF++"A"AAGGII^^VBC[$9:AA"**MFYYy"))As6{*CVLFt221559L9LQ9OOTWWJ^^V\$:;BB2::NF&&v. )))477vU[[7Y#&y>   KK $ $%!"  kknnU+ I"[ "[ "[s \?]] rGcXURnURtp4nU[R[R4;aUR 5nUR X4[R"U5-5nUR5n[R"X`RRSS9n[R"USURRS9nURS5n[R"X*U5U- nUR "X4/UQ76nUR!U5nU$)a  Apply dynamic thresholding to the predicted sample. "Dynamic thresholding: At each sampling step we set s to a certain percentile absolute pixel value in xt0 (the prediction of x_0 at timestep t), and if s > 1, then we threshold xt0 to the range [-s, s] and then divide by s. Dynamic thresholding pushes saturated pixels (those near -1 and 1) inwards, thereby actively preventing pixels from saturation at each step. We find that dynamic thresholding results in significantly better photorealism as well as better image-text alignment, especially when using very large guidance weights." https://huggingface.co/papers/2205.11487 Args: sample (`torch.Tensor`): The predicted sample to be thresholded. Returns: `torch.Tensor`: The thresholded sample. r r^)r-max)r)shaper.r0float64floatreshaperuprodabsquantilergrKclamprL unsqueezer})r~rGr) batch_sizechannelsremaining_dims abs_sampless r_threshold_sample(DEISMultistepScheduler._threshold_samplees( 06 - ~  6 6\\^F rww~7N,NOZZ\ NN:{{'M'MST U KK 1$++66  KKNVR+a/ F~F5! rrrc[R"[R"US55nX2SS2[R4- n[R"US:SS9R SS9R URSS- S9nUS-nX%nX&nXs- Xx- - n [R "U SS5n SU - U-X--n U RUR5n U $)at Convert sigma values to corresponding timestep values through interpolation. Args: sigma (`np.ndarray`): The sigma value(s) to convert to timestep(s). log_sigmas (`np.ndarray`): The logarithm of the sigma schedule used for interpolation. Returns: `np.ndarray`: The interpolated timestep value(s) corresponding to the input sigma(s). g|=Nr)axisr)rr ) rur"maximumnewaxiscumsumargmaxcliprr) r~rr log_sigmadistslow_idxhigh_idxlowhighwrs rr"DEISMultistepScheduler._sigma_to_tsFF2::eU34 q"**}55))UaZq188a8@EE*JZJZ[\J]`aJaEbQ;!#_ , GGAq! Ug  , IIekk "rcvURR(a SU- nUnX#4$SUS-S-S-- nX-nX#4$)z Convert sigma values to alpha_t and sigma_t values. Args: sigma (`torch.Tensor`): The sigma value(s) to convert. Returns: `tuple[torch.Tensor, torch.Tensor]`: A tuple containing (alpha_t, sigma_t) values. r rr )rgrS)r~rrorps r_sigma_to_alpha_sigma_t.DEISMultistepScheduler._sigma_to_alpha_sigma_tsS ;; & &%iGG E1HqLS01GoGrrc[URS5(aURRnOSn[URS5(aURRnOSnUbUOUSR 5nUbUOUSR 5nSn[ R "SSU5nUSU- -nUSU- -nXXx- --U-n U $)a Construct the noise schedule as proposed in [Elucidating the Design Space of Diffusion-Based Generative Models](https://huggingface.co/papers/2206.00364). Args: in_sigmas (`torch.Tensor`): The input sigma values to be converted. num_inference_steps (`int`): The number of inference steps to generate the noise schedule for. Returns: `torch.Tensor`: The converted sigma values following the Karras noise schedule. sigma_minN sigma_maxrerg@r )hasattrrgrritemrurV) r~rrtrrrhoramp min_inv_rho max_inv_rhorrs rr)DEISMultistepScheduler._convert_to_karrass$ 4;; , , --II 4;; , , --II!*!6IIbM4y1}a !RSS   Z   DOO,77> ;; & &) 3, 66'AG [[ ( (H 4"G [[ ( (N :&)??G [[ ( (,= =kk$//2G55G+DKK,G,G+HIWW  ;; # #,,W5G ;; % % /w..'9 9%&OP Prc,[U5S:aUSOURSS5n[U5S:aUSOURSS5nUc [U5S:aUSnO [S5eUb [SS S 5 Ub [SS S 5 URUR S-URUR pUR U5upUR U5up[R"U 5[R"U5- n [R"U 5[R"U5- n X- n URRS :Xa)X- U-U[R"U 5S - -U-- nU$[S5e)a One step for the first-order DEIS (equivalent to DDIM). Args: model_output (`torch.Tensor`): The direct output from the learned diffusion model. timestep (`int`): The current discrete timestep in the diffusion chain. prev_timestep (`int`): The previous discrete timestep in the diffusion chain. sample (`torch.Tensor`): A current instance of a sample created by the diffusion process. Returns: `torch.Tensor`: The sample tensor at the previous timestep. rrNr prev_timesteprrrxrrPassing `prev_timestep` is deprecated and has no effect as model output conversion is now handled via an internal counter `self.step_index`r9r]r) rrr*rrrrrr.r"rgrMrrj)r~rrGrrrrrpsigma_sroalpha_srqlambda_shx_ts rdeis_first_order_update.DEISMultistepScheduler.deis_first_order_updates0"$i!m47J1M#&t9q=QfjjRV6W >4y1}a !RSS   Z   $ ^  KK!+ , KK ( 77@77@99W% '(::99W% '(::   ;; % % /$.'UYYq\C=O2PT`1``C &&OP Prmodel_output_listc*[U5S:aUSOURSS5n[U5S:aUSOURSS5nUc [U5S:aUSnO [S5eUb [SSS 5 Ub [SSS 5 URUR S-URUR URUR S- pnUR U5upUR U5upUR U 5upUS US pXz- X- X- nnnURRS :XaBSnU"UUU5U"UUU5- nU"UUU5U"UUU5- nXU - UU --UU---nU$[S5e)au One step for the second-order multistep DEIS. Args: model_output_list (`list[torch.Tensor]`): The direct outputs from learned diffusion model at current and latter timesteps. sample (`torch.Tensor`): A current instance of a sample created by the diffusion process. Returns: `torch.Tensor`: The sample tensor at the previous timestep. r timestep_listNr rrrrPassing `timestep_list` is deprecated and has no effect as model output conversion is now handled via an internal counter `self.step_index`rrer9cU[R"U5*[R"U5-S- -[R"U5[R"U5- - $)Nr rur")rbcs rind_fnIDEISMultistepScheduler.multistep_deis_second_order_update..ind_fnsCRVVAYJ2Q67266!9rvvay;PQQrr rrr*rrrrrrgrMrj)r~rrGrrrrrpsigma_s0sigma_s1roalpha_s0alpha_s1m0m1rho_trho_s0rho_s1rcoef1coef2rs r"multistep_deis_second_order_update9DEISMultistepScheduler.multistep_deis_second_order_updates($'t9q=QfjjRV6W #&t9q=QfjjRV6W >4y1}a !RSS  $ ^   $ ^  KK!+ , KK ( KK!+ ,$  77@!99(C!99(C"2&(9"(=B      v ;; % % / R5&&1F6664RRE5&&1F6664RREh.;ebjHICJ%&OP Prc[U5S:aUSOURSS5n[U5S:aUSOURSS5nUc [U5S:aUSnO [S5eUb [SSS 5 Ub [SSS 5 URUR S-URUR URUR S- URUR S- 4upxpUR U5upUR U5upUR U 5upUR U 5upUS US US nnnX{- X- X- X- 4unnnnURRS:XacSnU"UUUU5U"UUUU5- nU"UUUU5U"UUUU5- nU"UUUU5U"UUUU5- nXU - UU--UU--UU---nU$[S5e)ap One step for the third-order multistep DEIS. Args: model_output_list (`list[torch.Tensor]`): The direct outputs from learned diffusion model at current and latter timesteps. sample (`torch.Tensor`): A current instance of a sample created by diffusion process. Returns: `torch.Tensor`: The sample tensor at the previous timestep. rrNr rrrrrrrerr9cLU[R"U5[R"U5[R"U5- S--[R"U5[R"U5-- [R"U5-[R"U5S--S[R"U5-- S--n[R"U5[R"U5- [R"U5[R"U5- -nXE- $)Nr rr)rrrd numerator denominators rrHDEISMultistepScheduler.multistep_deis_third_order_update..ind_fnHsFF1IRVVAY!6!:;ffQi"&&)+,ffQi ffQi1n%"&&)m $    "vvay266!94RVVAY9NO  ..rrr)r~rrGrrrrrprrsigma_s2rorralpha_s2rrm2rrrrho_s2rrr coef3rs r!multistep_deis_third_order_update8DEISMultistepScheduler.multistep_deis_third_order_updatesP*$'t9q=QfjjRV6W #&t9q=QfjjRV6W >4y1}a !RSS  $ ^   $ ^  KK!+ , KK ( KK!+ , KK!+ , 1 -8 77@!99(C!99(C!99(C&r*,=b,ACTUWCXB         ) %vvv ;; % % / /5&&&9F66SY[a !;77rcU$)z Ensures interchangeability with schedulers that need to scale the denoising model input depending on the current timestep. Args: sample (`torch.Tensor`): The input sample. Returns: `torch.Tensor`: A scaled input sample. )r~rGrrs rscale_model_input(DEISMultistepScheduler.scale_model_inputs  roriginal_samplesnoiserxc*URRURURS9nURRS:Xav[ R "U5(a[URRUR[ RS9nURUR[ RS9nO@URRUR5nURUR5nURc!UVs/sHo`RXe5PM nnOHURbUR/URS-nOUR/URS-nXGR5n[UR5[UR5:a?URS5n[UR5[UR5:aM?UR!U5upX-X--n U $s snf)a Add noise to the original samples according to the noise schedule at the specified timesteps. Args: original_samples (`torch.Tensor`): The original samples without noise. noise (`torch.Tensor`): The noise to add to the samples. timesteps (`torch.IntTensor`): The timesteps at which to add noise to the samples. Returns: `torch.Tensor`: The noisy samples. rmpsr(rre)rrr}rr)typer.is_floating_pointrxr0rrrrflattenrrr) r~r0r1rxrrrr step_indicesrrorp noisy_sampless r add_noise DEISMultistepScheduler.add_noises,'7'>'>FVF\F\]  " " ' '5 0U5L5LY5W5W!%!2!23C3J3JRWR_R_!2!` ! %5%<%2W_D _sHc.URR$N)rgr<rs r__len__DEISMultistepScheduler.__len__s{{...r)r|r{rorlrnr1rsrqrzryrtrprrrx)ig-C6?g{Gz?r@NrrFFgףp= ?r]r9r:TFFFFr]rVrFr;)r)NN)333333?r?r<)T)/__name__ __module__ __qualname____firstlineno____doc__r name _compatiblesorderrintrrrundarraylistboolrpropertyrrrstrr.rrr"rrtuplerrrrrrr rrr#r r*r. IntTensorr9r=__static_attributes__).0es00rr7r7Vs;z%>>$=qFF$=>L E$("QY9=[d",1"%*0)1"&"'', % %GQ%*2?/], ],], ], MN ], zzDK/$6 ],],!!WX],],%*], ], ],X&], ], ], !%!],"#],$%],&'],(""CD)],*+],,#-],.!//],0 1],],~ C  !S!!(3(t(R,R,cELL>PR,]bei]iR,j) ))X""" "J U\\ eELLRWR^R^D^>_ ,$ELL$s$W\WcWc$NTW\a\h\hFdg..8ll>8 $>8 >8  >8 5 >8@  %,,  /,,/||/?? /  /b//E?sL>r7)g+?r)rtypingrnumpyrur.configuration_utilsrrutilsrrscheduling_utilsr r r scipy.statsrrHrr"r5r7r-rrrYsy$  A1XX @H14 1414""<=14 \\ 14hA/^[A/r