+h [R "U[R S9$)a Create a beta schedule that discretizes the given alpha_t_bar function, which defines the cumulative product of (1-beta) over time from t = [0,1]. Contains a function alpha_bar that takes an argument t and transforms it to the cumulative product of (1-beta) up to that part of the diffusion process. Args: num_diffusion_timesteps (`int`): the number of betas to produce. max_beta (`float`): the maximum beta to use; use values lower than 1 to prevent singularities. alpha_transform_type (`str`, *optional*, default to `cosine`): the type of noise schedule for alpha_bar. Choose from `cosine` or `exp` Returns: betas (`np.ndarray`): the betas used by the scheduler to step the model outputs cosinech[R"US-S- [R-S- 5S-$)NgMb?gT㥛 ?r)mathcospits r alpha_bar_fn)betas_for_alpha_bar..alpha_bar_fnLs-88QY%/$''9A=>!C Crexpc4[R"US-5$)Ng()r$r+r's r r)r*Qs88AI& &rz"Unsupported alpha_transform_type: r dtype) ValueErrorrangeappendminrtensorfloat32)num_diffusion_timestepsmax_betaalpha_transform_typer)betasit1t2s r betas_for_alpha_barr<3s.x' D  & '=>R=STUU E * +  (!e. . S\"- R0@@@(KL, <<U]] 33rc\rSrSrSr\VVs/sHoR PM snnrSr\ S2S\ S\ S\ S\ S \ \\R \\ 4S \ S \ \S \ \S \ \S\ \S\ S\ S\ 4Sjj5rS3Sjr\S5r\S5r\S5rS4S\ 4SjjrS\R6S\\ \R64S\R64SjrS5S\ \ S\\ \R:4S\ \ S\ \\ 4S jjrS!rS"\R6S\R64S#jr S"\R6S\ S\R64S$jr!S6S"\R6S\ S%\ S&\ S\R64 S'jjr"\S(5r#S)r$S7S*\\R6\R 4S\\ \R64S\\R6\R 4S+\S\\%\&44 S,jjr'S-\R6S.\R6S\R6S\R64S/jr(S0r)S1r*gs snnf)8HeunDiscreteScheduler_u Scheduler with Heun steps for discrete beta schedules. 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 (`str`, defaults to `"linear"`): The beta schedule, a mapping from a beta range to a sequence of betas for stepping the model. Choose from `linear` or `scaled_linear`. trained_betas (`np.ndarray`, *optional*): Pass an array of betas directly to the constructor to bypass `beta_start` and `beta_end`. 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). clip_sample (`bool`, defaults to `True`): Clip the predicted sample for numerical stability. clip_sample_range (`float`, defaults to 1.0): The maximum magnitude for sample clipping. Valid only when `clip_sample=True`. 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. timestep_spacing (`str`, 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. rNnum_train_timesteps beta_startbeta_end beta_schedule trained_betasprediction_typeuse_karras_sigmasuse_exponential_sigmasuse_beta_sigmas clip_sampleclip_sample_rangetimestep_spacing steps_offsetcURR(a[5(d [S5e[ URRURR URR /5S:a [S5eUb)[R"U[RS9Ul OUS:Xa*[R"X#U[RS9Ul OUS:Xa4[R"US-US-U[RS9S-Ul OFUS :Xa[US S 9Ul O0US :Xa[US S 9Ul O[US UR35eSUR- Ul[R""UR SS9UlUR'USU5 XplSUlSUlUR,R/S5Ulg)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-linear scaled_linear?rsquaredcos_cap_v2r")r7r+z is not implemented for ?r)dimcpu)configrHr ImportErrorsumrGrFr/rr3r4r8linspacer<NotImplementedError __class__alphascumprodalphas_cumprod set_timesteps _step_index _begin_indexsigmasto)selfr@rArBrCrDrErFrGrHrIrJrKrLs r __init__HeunDiscreteScheduler.__init__s" ;; & &/A/C/CZ[ [  ++T[[-O-OQUQ\Q\QnQno pst tA   $m5==IDJ h & >QY^YfYfgDJ o - C3H[chcpcpquvvDJ 1 1,-@W_`DJ e #,-@W\]DJ%7OPTP^P^O_&`a aDJJ& #mmDKKQ? .6IJ!2 kknnU+ rcUc URnX!:HR5n[U5S:aSOSnX4R5$)Nr r) timestepsnonzerolenitem)rctimestepschedule_timestepsindicesposs r index_for_timestep(HeunDiscreteScheduler.index_for_timestepsH  %!% %1::< w[R"S US - U[RS9SSS 2R5nGOR9S5Ulgs snfs snfs snf)ay 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. num_train_timesteps (`int`, *optional*): The number of diffusion steps used when training the model. If `None`, the default `num_train_timesteps` attribute is used. timesteps (`List[int]`, *optional*): Custom timesteps used to support arbitrary spacing between timesteps. If `None`, timesteps will be generated based on the `timestep_spacing` attribute. If `timesteps` is passed, `num_inference_steps` must be `None`, and `timestep_spacing` attribute will be ignored. NzEMust pass exactly one of `num_inference_steps` or `custom_timesteps`.zACan only pass one of `num_inference_steps` or `custom_timesteps`.z=Cannot use `timesteps` with `config.use_karras_sigmas = True`zCCannot set `timesteps` with `config.use_exponential_sigmas = True`.z+BDW_a_i_ijkomokopuuw --:04L4LL  YYq*=>KRRTUYWYUYZ__ahhikisist [[555 --;03K3KK  YY':A {KRRTYY[bbcecmcmn Q  {{3345NOA 3 33t7J7JJsRSVVF^ 9bii3v;&?H ;; ( (,,vSkSk,lFSY!ZSY%"2"25"ESY!Z[I [[ / /11F1lFSY!ZSY%"2"25"ESY!Z[I [[ ( (**V*eFSY!ZSY%"2"25"ESY!Z[I#077 C!!&),,F,;iiVAb\-K-KA-NPVWYWZP[ \] $$Y/ IIy!}im.M.Ma.PQR "V5==I $ kknnU+ /"["["[sU-:U2U7c[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 $)Ng|=r)axisr)rsr ) rrmaximumnewaxiscumsumargmaxclipshapereshape) rcrr log_sigmadistslow_idxhigh_idxlowhighwr(s r r!HeunDiscreteScheduler._sigma_to_tdsFF2::eU34 q"**}55))UaZq188a8@EE*JZJZ[\J]`aJaEbQ;!#_ , GGAq! Ug  , IIekk "rrc[URS5(aURRnOSn[URS5(aURRnOSnUbUOUSR 5nUbUOUSR 5nSn[ R "SSU5nUSU- -nUSU- -nXXx- --U-n U $)z6Constructs the noise schedule of Karras et al. (2022). sigma_minN sigma_maxrrg@r )hasattrrUrrrjrrX) rcrrrrrhoramp min_inv_rho max_inv_rhoras r r(HeunDiscreteScheduler._convert_to_karras|s 4;; , , --II 4;; , , --II!*!6IIbMTUCUZ]B]3]#^q.1,-$ [[ ( (H 4#/ +DKK,G,G+HHtu  ;; " "#7#=#=... 0M0M$   $ $ 79DJ'B$. G K!7:EJ..;q@JB[[F$(D DGDKB.  A$  +{nnroriginal_samplesnoisecURRURURS9nURRS:Xav[ R "U5(a[URRUR[ RS9nURUR[ RS9nO@URRUR5nURUR5nURc!UVs/sHo`RXe5PM nnOHURbUR/URS-nOUR/URS-nXGR5n[UR5[UR5:a?URS5n[UR5[UR5:aM?XU--n U $s snf)Nrmpsr-rr)rarbrr.typeris_floating_pointrgr4r|rorxrflattenri unsqueeze) rcrrrgrarlr( step_indicesr noisy_sampless r add_noiseHeunDiscreteScheduler.add_noise@s'7'>'>FVF\F\]  " " ' '5 0U5L5LY5W5W!%!2!23C3J3JRWR_R_!2!` ! %5%<%r>_sU'R%>>$=qFF$=>L E$(#%BF(,116*/&+#& *., .,., .,  .,  bjj$u+&= >? .,.,$D>.,!).,"$.,d^.,!.,.,.,.,b #33  !!(3( u||+,  8.2+/-1)- Z,%c]Z,c5<<'(Z,&c] Z, DI& Z,z0ELLRWR^R^4TW\a\h\h.dg1! eoELL"**45eou||+,eoellBJJ./ eo  eo *E1 2 eoP,,||<<   B/q?sHr>)g+?r")r$ dataclassesrtypingrrrrnumpyrrconfiguration_utilsr r utilsr r scheduling_utilsrr scipy.statsrrr<r>rrr rsi !// A2G 8*8 8(!)4XC/NKC/r