iq ddlZddlZddlmZddlmZmZmZmZm Z ddl Z ddl Z ddlZddl mZddlmZmZddlmZdd lmZmZeGd d eZ dd ed ededdej6fdZGddeeZy)N) dataclass)ListLiteralOptionalTupleUnion) integrate) ConfigMixinregister_to_config) BaseOutput)KarrasDiffusionSchedulersSchedulerMixincXeZdZUdZej ed<dZeej ed<y)LMSDiscreteSchedulerOutputaq 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____doc__torchTensor__annotations__rrv/home/obispo/Crisostomo_bridge/mision_env/lib/python3.12/site-packages/diffusers/schedulers/scheduling_lms_discrete.pyrrs' 37(5<<07rrnum_diffusion_timestepsmax_betaalpha_transform_type)cosineexpreturnc $|dk(rd}n|dk(rd}ntd|g}t|D]<}||z }|dz|z }|jtd||||z z |>t j |tj S)aB Create a beta schedule that discretizes the given alpha_t_bar function, which defines the cumulative product of (1-beta) over time from t = [0,1]. Contains a function alpha_bar that takes an argument t and transforms it to the cumulative product of (1-beta) up to that part of the diffusion process. Args: num_diffusion_timesteps (`int`): The number of betas to produce. max_beta (`float`, defaults to `0.999`): The maximum beta to use; use values lower than 1 to avoid numerical instability. alpha_transform_type (`"cosine"` or `"exp"`, defaults to `"cosine"`): The type of noise schedule for `alpha_bar`. Choose from `cosine` or `exp`. Returns: `torch.Tensor`: The betas used by the scheduler to step the model outputs. r"cftj|dzdz tjzdz dzS)NgMb?gT㥛 ?r )mathcospits r alpha_bar_fnz)betas_for_alpha_bar..alpha_bar_fnKs-88QY%/$''9A=>!C Crr#c2tj|dzS)Ng()r'r#r*s rr,z)betas_for_alpha_bar..alpha_bar_fnPs88AI& &rz"Unsupported alpha_transform_type: rdtype) ValueErrorrangeappendminrtensorfloat32)rr r!r,betasit1t2s rbetas_for_alpha_barr:1s0x' D  & '=>R=STUU E * +M ( (!e. . S\"- R0@@@(KLM <<U]] 33rceZdZdZeDcgc]}|j c}}ZdZe d7de de de de dd e e ejee fd e ed e ed e ed e dde dde fdZede e ej*ffdZede e fdZede e fdZd8de ddfdZdej*de e ej*fdej*fdZde de de de fdZd9d e d!e e eej:fddfd"Z d9de e ej*fd#e ej*de fd$Zde e ej*fddfd%Z d&ejd'ejdejfd(Z!d)ej*dej*fd*Z"d)ej*d e dej*fd+Z# d:d)ej*d e d,e d-e dej*f d.Z$ d;d/ej*de e ej*fdej*de d0ede e%e&ff d1Z'd2ej*d3ej*d4ej*dej*fd5Z(de fd6Z)ycc}}w)<LMSDiscreteScheduleru A linear multistep scheduler 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 (`"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. trained_betas (`np.ndarray`, *optional*): Pass an array of betas directly to the constructor to bypass `beta_start` and `beta_end`. 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. prediction_type (`"epsilon"`, `"sample"`, or `"v_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`) or `v_prediction` (see section 2.4 of [Imagen Video](https://huggingface.co/papers/2210.02303) paper). 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. rNnum_train_timesteps beta_startbeta_end beta_schedule)linear scaled_linearsquaredcos_cap_v2 trained_betasuse_karras_sigmasuse_exponential_sigmasuse_beta_sigmasprediction_type)epsilonsample v_predictiontimestep_spacing)linspaceleadingtrailing steps_offsetc t|jj|jj|jjgdkDr t d|+t j|t j|_ n|dk(r-t j|||t j|_ nk|dk(r6t j|dz|dz|t jdz|_ n0|dk(rt||_ nt|d |jd |jz |_t j|jd |_t#j$d|j z |j z dz} t#j&| ddd dggj)t"j} t j*| |_d|_||_|j1|dg|_d|_d|_d|_|j,j;d|_y)NrznOnly one of `config.use_beta_sigmas`, `config.use_exponential_sigmas`, `config.use_karras_sigmas` can be used.r.rArB?r rCz is not implemented for ?r)dimFcpu)sumconfigrGrFrEr0rr4r5r6rMr:NotImplementedError __class__alphascumprodalphas_cumprodnparray concatenateastype from_numpysigmasnum_inference_steps set_timesteps derivativesis_scale_input_called _step_index _begin_indexto) selfr=r>r?r@rDrErFrGrHrLrPrds r__init__zLMSDiscreteScheduler.__init__s  ++T[[-O-OQUQ\Q\QnQno pst tA   $m5==IDJ h & H>QY^YfYfgDJ o - C3H[chcpcpquvvDJ 1 1,-@ADJ%7OPTP^P^O_&`a aDJJ& #mmDKKQ?A 3 33t7J7JJsRS"u 56==bjjI&&v. $( !2 .5%*" kknnU+ rr$c|jjdvr|jjS|jjdzdzdzS)a0 The standard deviation of the initial noise distribution. Returns: `float` or `torch.Tensor`: The standard deviation of the initial noise distribution, computed based on the maximum sigma value and the timestep spacing configuration. )rMrOr rrR)rYrLrdmaxrls rinit_noise_sigmaz%LMSDiscreteScheduler.init_noise_sigmasH ;; ' '+C C;;??$ $ !Q&*s22rc|jS)z The index counter for current timestep. It will increase by 1 after each scheduler step. Returns: `int` or `None`: The current step index, or `None` if not initialized. )rirps r step_indexzLMSDiscreteScheduler.step_indexsrc|jS)z The index for the first timestep. It should be set from pipeline with `set_begin_index` method. Returns: `int` or `None`: The begin index for the scheduler, or `None` if not set. rjrps r begin_indexz LMSDiscreteScheduler.begin_indexs   rrvc||_y)z Sets the begin index for the scheduler. This function should be run from pipeline before the inference. Args: begin_index (`int`, defaults to `0`): The begin index for the scheduler. Nru)rlrvs rset_begin_indexz$LMSDiscreteScheduler.set_begin_indexs (rrJtimestepc|j|j||j|j}||dzdzdzz }d|_|S)a Ensures interchangeability with schedulers that need to scale the denoising model input depending on the current timestep. Args: sample (`torch.Tensor`): The input sample. timestep (`float` or `torch.Tensor`): The current timestep in the diffusion chain. Returns: `torch.Tensor`: A scaled input sample. r rrRT)rs_init_step_indexrdrh)rlrJrysigmas rscale_model_inputz&LMSDiscreteScheduler.scale_model_inputsR ?? "  ! !( + DOO,E1HqLS01%)" rorderr+ current_ordercfd}tj|jjdzdd}|S)a Compute the linear multistep coefficient. Args: order (`int`): The order of the linear multistep method. t (`int`): The current timestep index. current_order (`int`): The current order for which to compute the coefficient. Returns: `float`: The computed linear multistep coefficient. cd}tD]F}|k(r ||j|z z jz j|z z z z}H|S)NrS)r1rd)tauprodkrr~rlr+s rlms_derivativez@LMSDiscreteScheduler.get_lms_coefficient..lms_derivativesvD5\ k A%t{{1q511dkk!mBS6TW[WbWbcdghchWi6ijj kKrr-C6?)epsrelr)r quadrd)rlr~r+rrintegrated_coeffs```` rget_lms_coefficientz(LMSDiscreteScheduler.get_lms_coefficientsD" %>>.$++a.$++VWZ[V[J\eijklmrredevicec ||_|jjdk(rTtjd|jj dz |tj dddj}nw|jjdk(r|jj |jz}tjd||zjdddjjtj }||jjz }n|jjdk(r|jj |jz }tj|jj d| jjjtj }|dz}n"t|jjd tjd|jz |jz d z}tj|}tj |tjdt#||}|jj$rF|j'| }tj|Dcgc]}|j)||c}}n|jj*rG|j-|| }tj|Dcgc]}|j)||c}}n\|jj.rF|j1|| }tj|Dcgc]}|j)||c}}tj2|d ggjtj }t5j6|j9||_t5j6|j9|t4j |_d|_d|_ |j:j9d|_g|_!ycc}wcc}wcc}w)a 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. rMrrr.NrUrNrOzY is not supported. Please make sure to choose one of 'linspace', 'leading' or 'trailing'.rR) in_sigmas)rrerV)rrr/rW)"rerYrLr_rMr=r5copyarangeroundrbrPr0r`r^loginterplenrE_convert_to_karras _sigma_to_trF_convert_to_exponentialrG_convert_to_betararrcrkrd timestepsrirjrg)rlrerr step_ratiord log_sigmasr|s rrfz"LMSDiscreteScheduler.set_timestepssh$7  ;; ' ': 5 At{{'F'F'JL_gigqgqr"df [[ ) )Y 688DFSY!Z%$"2"25*"E!Z[I [[ / /11FXk1lFSY!Z%$"2"25*"E!Z[I [[ ( (**VQd*eFSY!Z%$"2"25*"E!Z[I#077 C&&v.111@ )))477vU]]7[ kknnU+ !"["["[s"Q ?QQschedule_timestepsc| |j}||k(j}t|dkDrdnd}||jS)ak Find the index of a given timestep in the timestep schedule. Args: timestep (`float` or `torch.Tensor`): The timestep value to find in the schedule. schedule_timesteps (`torch.Tensor`, *optional*): The timestep schedule to search in. If `None`, uses `self.timesteps`. Returns: `int`: The index of the timestep in the schedule. For the very first step, returns the second index if multiple matches exist to avoid skipping a sigma when starting mid-schedule (e.g., for image-to-image). rr)rnonzeroritem)rlryrindicesposs rindex_for_timestepz'LMSDiscreteScheduler.index_for_timestepYsN"  %!% %1::< wz,LMSDiscreteScheduler.step..Xs# #45*EJ # s)rr)rhwarningswarnrsr{rdrYrHr0rgr2rpopr3r1rrXzipreversedrir) rlrryrJr~rr|rr curr_order lms_coeffsrs rstepzLMSDiscreteScheduler.steps<)) MME  ?? "  ! !( + DOO, ;; & &) 3#)EL,@#@ [[ ( (N :#/E6UAX\c'>FVF\F\]  " " ' '5 0U5L5LY5W!%!2!23C3J3JRWR_R_!2!` ! %5%<%>qAFF>L E$("QYBF,116*/HQGQ/, /,/, /, MN /,  bjj$u+&= >? /,$D>/,!)/,"$/,!!DE/,""CD/,/,/,b 3%u||(;"< 3 3 HSM  !Xc]!!(3(t( eU\\FY@Z_d_k_k0   S U :88huSRWR^R^M^G_>`8lp8xbf#eU\\12#HPQVQ]Q]H^# #> 1uell/B)C 1 1 """ "HELLU\\2TW\a\h\hFdg..rs !88 AG 88 8(5=*4 *4*4"/2*4 \\ *4Z{/>;{/r