+h=SSKrSSKJr SSKJrJrJr SSKrSSK r SSK J r J r SSK Jr SSKJr SS KJr \"S S \55rSS jr"S S\\ 5rg)N) dataclass)OptionalTupleUnion) ConfigMixinregister_to_config) BaseOutput) randn_tensor)SchedulerMixincV\rSrSr%Sr\R \S'\R \S'Srg)RePaintSchedulerOutputaH 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_samplepred_original_sampleN) __name__ __module__ __qualname____firstlineno____doc__torchTensor__annotations____static_attributes__ra/home/james-whalen/.local/lib/python3.13/site-packages/diffusers/schedulers/scheduling_repaint.pyrrs ,,&rrc &US:XaSnOUS:XaSnO[SU35e/n[U5H<nXP- nUS-U- nUR[SU"U5U"U5- - U55 M> [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_fnHs-88QY%/$''9A=>!C Crexpc4[R"US-5$)Ng()r"r)r%s rr'r(Ms88AI& &rz"Unsupported alpha_transform_type: r dtype) ValueErrorrangeappendminrtensorfloat32)num_diffusion_timestepsmax_betaalpha_transform_typer'betasit1t2s rbetas_for_alpha_barr:/s.x' D  & '=>R=STUU E * +  (!e. . S\"- R0@@@(KL, <<U]] 33rc(\rSrSrSrSr\S$S\S\S\S\ S \S \ \ RS \ 4S jj5rS%S \R S\ \S\R 4SjjrS&S\S\S\S\\ \R&44SjjrSrS'S\R S\S \R S\R S\R S\ \R,S\ S\\\44SjjrS%SjrS\R S\R S \R6S\R 4S!jrS"rS#rg)(RePaintScheduler[a `RePaintScheduler` is a scheduler for DDPM inpainting inside a given mask. This model inherits from [`SchedulerMixin`] and [`ConfigMixin`]. Check the superclass documentation for the generic methods the library implements for all schedulers such as loading and saving. Args: num_train_timesteps (`int`, defaults to 1000): The number of diffusion steps to train the model. beta_start (`float`, defaults to 0.0001): The starting `beta` value of inference. beta_end (`float`, defaults to 0.02): The final `beta` value. beta_schedule (`str`, defaults to `"linear"`): The beta schedule, a mapping from a beta range to a sequence of betas for stepping the model. Choose from `linear`, `scaled_linear`, `squaredcos_cap_v2`, or `sigmoid`. eta (`float`): The weight of noise for added noise in diffusion step. If its value is between 0.0 and 1.0 it corresponds to the DDIM scheduler, and if its value is between -0.0 and 1.0 it corresponds to the DDPM scheduler. trained_betas (`np.ndarray`, *optional*): Pass an array of betas directly to the constructor to bypass `beta_start` and `beta_end`. clip_sample (`bool`, defaults to `True`): Clip the predicted sample between -1 and 1 for numerical stability. r Nnum_train_timesteps beta_startbeta_end beta_scheduleeta trained_betas clip_samplecUb[R"U5UlOUS:Xa*[R"X#U[RS9UlOUS:Xa4[R"US-US-U[RS9S-UlOsUS:Xa[ U5UlO\US:Xa<[R"SS U5n[R "U5X2- -U-UlO[US UR35eS UR- Ul [R"URS S 9Ul [R"S 5Ul [R"S 5UlS UlSUl[R"["R$"S U5SSS2R'55UlXPlg)Nlinearr+ scaled_linear?rsquaredcos_cap_v2sigmoidiz is not implemented for ?r)dim)r from_numpyr6linspacer2r:rJNotImplementedError __class__alphascumprodalphas_cumprodr1onefinal_alpha_cumprodinit_noise_sigmanum_inference_stepsnparangecopy timestepsrB) selfr>r?r@rArBrCrDr6s r__init__RePaintScheduler.__init__xsr  $))-8DJ h & >QY^YfYfgDJ o - C3H[chcpcpquvvDJ 1 1,-@ADJ i 'NN2q*=>Eu-1FG*TDJ%7OPTP^P^O_&`a aDJJ& #mmDKKQ?<<$#(<<#4 !$$( ))"))A7J*KDbD*Q*V*V*XYrsampletimestepreturncU$)aN Ensures interchangeability with schedulers that need to scale the denoising model input depending on the current timestep. Args: sample (`torch.Tensor`): The input sample. timestep (`int`, *optional*): The current timestep in the diffusion chain. Returns: `torch.Tensor`: A scaled input sample. r)r^rarbs rscale_model_input"RePaintScheduler.scale_model_inputs  rrY jump_length jump_n_sampledevicec4[URRU5nXl/n0n[ SX- U5H nUS- Xg'M UnUS:aeUS- nUR U5 UR US5S:a1XhS- Xh'[ U5Hn US-nUR U5 M US:aMe[R"U5URRUR--n[R"U5RU5Ul g)u7 Sets the discrete timesteps used for the diffusion chain (to be run before inference). Args: num_inference_steps (`int`): The number of diffusion steps used when generating samples with a pre-trained model. If used, `timesteps` must be `None`. jump_length (`int`, defaults to 10): The number of steps taken forward in time before going backward in time for a single jump (“j” in RePaint paper). Take a look at Figure 9 and 10 in the paper. jump_n_sample (`int`, defaults to 10): The number of times to make a forward time jump for a given chosen time sample. Take a look at Figure 9 and 10 in the paper. device (`str` or `torch.device`, *optional*): The device to which the timesteps should be moved to. If `None`, the timesteps are not moved. rr N) r0configr>rYr.r/getrZarrayrrOtor]) r^rYrgrhrir]jumpsjr&_s r set_timestepsRePaintScheduler.set_timestepss 0"$++"A"ACVW#6  q-;[IA$q(EHJ 1fAA   Q yyA" 8a<{+AAA$$Q', 1fHHY'4;;+J+JdNfNf+fg )))477?rcXRRUR-- nURUnUS:aURUO URnSU- nSU- nXe- SX4- - -nU$)Nrr )rkr>rYrUrW)r^r& prev_timestep alpha_prod_talpha_prod_t_prev beta_prod_tbeta_prod_t_prevvariances r _get_varianceRePaintScheduler._get_variancesKK;;t?W?WWW **1- BOSTBTD// >Z^ZrZr,& 00%2q<;[7[\r model_outputoriginal_imagemask generator return_dictcUnX RRUR-- n URUn U S:aURU O URn SU - n XrYrUrWrDrclamprir shaper,rBr{r)r^r}rbrar~rrrr&rurvrwrxrrinoise std_dev_trzpred_sample_directionprev_unknown_partprev_known_partpred_prev_samples rstepRePaintScheduler.stepsH  ;;#B#BdF^F^#^^ **1- BOSTBTD// >Z^ZrZr,& !'c)9L)H HLZ]L]] ;; " "#(;;/CR#K $$\//9[g[m[mnHHt11(;sBB  q5TXX\ 5(H"#%6!6A!E# MP\ \.s25IILaadll-c1^CL]H]beGeinFnn /1S4ZCT4TT $  &2BYmnnrcURRUR-n[U5HnURX%-nUR R S:Xa;[URURUS9nURUR 5nO)[URX1R URS9nSU- S-U-US-U--nM U$)Nmps)r,rrr rH) rkr>rYr.r6rityper rr,rn)r^rarbrnr7betars r undo_stepRePaintScheduler.undo_stepSs KK + +t/G/G GqA::hl+D}}!!U*$V\\QZ[/$V\\Y}}djdpdpq$h3&/$)e2CCF roriginal_samplesrr]c[S5e)NzCUse `DDPMScheduler.add_noise()` to train for sampling with RePaint.)rQ)r^rrr]s r add_noiseRePaintScheduler.add_noiseds ""ghhrc.URR$N)rkr>)r^s r__len__RePaintScheduler.__len__ls{{...r) rSrUr6rBrWrXrYrVr])ig-C6?g{Gz?rFgNTr) rN)NT)rrrrrorderr intfloatstrrrZndarrayboolr_rrrerrirrr{ Generatorrrrr IntTensorrrrrrrr<r<[s4 E$("%.2 ( (( (  (  (  +(((T  Y^YeYe(+/ -@ -@-@ -@ c5<<'( -@^404 [oll[o[o [o  [o ll [oEOO,[o[o %u, -[oz"i,,i||i?? i  i/rr<)g+?r )r" dataclassesrtypingrrrnumpyrZrconfiguration_utilsrr utilsr utils.torch_utilsr scheduling_utilsr rr:r<rrrrs^ !)) A,, 'Z' '(!)4XR/~{R/r