i| ddlZddlmZddlmZmZmZmZmZddl Z ddl Z ddl m Z mZddlmZmZddlmZmZerddlZeGd d eZ dd ed ed edde j4fdZGddee Zy)N) dataclass)ListLiteralOptionalTupleUnion) ConfigMixinregister_to_config) BaseOutputis_scipy_available)KarrasDiffusionSchedulersSchedulerMixincXeZdZUdZej ed<dZeej ed<y)HeunDiscreteSchedulerOutputaq 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__rrw/home/obispo/Crisostomo_bridge/mision_env/lib/python3.12/site-packages/diffusers/schedulers/scheduling_heun_discrete.pyrrs' 37(5<<07rrnum_diffusion_timestepsmax_betaalpha_transform_type)cosineexpreturnc $|dk(rd}n|dk(rd}ntd|g}t|D]<}||z }|dz|z }|jtd||||z z |>t j |tj S)aB Create a beta schedule that discretizes the given alpha_t_bar function, which defines the cumulative product of (1-beta) over time from t = [0,1]. Contains a function alpha_bar that takes an argument t and transforms it to the cumulative product of (1-beta) up to that part of the diffusion process. Args: num_diffusion_timesteps (`int`): The number of betas to produce. max_beta (`float`, defaults to `0.999`): The maximum beta to use; use values lower than 1 to avoid numerical instability. alpha_transform_type (`"cosine"` or `"exp"`, defaults to `"cosine"`): The type of noise schedule for `alpha_bar`. Choose from `cosine` or `exp`. Returns: `torch.Tensor`: The betas used by the scheduler to step the model outputs. r"cftj|dzdz tjzdz dzS)NgMb?gT㥛 ?r )mathcospits r alpha_bar_fnz)betas_for_alpha_bar..alpha_bar_fnMs-88QY%/$''9A=>!C Crr#c2tj|dzS)Ng()r'r#r*s rr,z)betas_for_alpha_bar..alpha_bar_fnRs88AI& &rz"Unsupported alpha_transform_type: rdtype) ValueErrorrangeappendminrtensorfloat32)rr r!r,betasit1t2s rbetas_for_alpha_barr:3s0x' D  & '=>R=STUU E * +M ( (!e. . S\"- R0@@@(KLM <<U]] 33rceZdZdZeDcgc]}|j c}}ZdZe d6de de de de dd e e ejee fd e d d e ed e ede ede ede de dde ddfdZ d7de e ej(fde ej(de fdZedZedZedZd8de ddfdZdej(de e ej(fdej(fdZ d9d e e d!e eej:fde e d"e ee ddf d#Zd$ejd%ejdejfd&Zd'ej(d e dej(fd(Z d'ej(d e dej(fd)Z! d:d'ej(d e d*e d+e dej(f d,Z"ed-Z#de e ej(fddfd.Z$ d;d/e ej(ejfde e ej(fde ej(ejfd0ede e%e&ff d1Z'd2ej(d3ej(d"ej(dej(fd4Z(de fd5Z)ycc}}w)<HeunDiscreteScheduleruE 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 (`"linear"`, `"scaled_linear"`, `"squaredcos_cap_v2"`, or `"exp"`, 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 `exp`. trained_betas (`np.ndarray`, *optional*): Pass an array of betas directly to the constructor to bypass `beta_start` and `beta_end`. prediction_type (`"epsilon"`, `"sample"`, or `"v_prediction"`, 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://huggingface.co/papers/2210.02303) 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 (`"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. r Nnum_train_timesteps beta_startbeta_end beta_schedule)linear scaled_linearsquaredcos_cap_v2r# trained_betasprediction_type)epsilonsample v_predictionuse_karras_sigmasuse_exponential_sigmasuse_beta_sigmas clip_sampleclip_sample_rangetimestep_spacing)linspaceleadingtrailing steps_offsetr$c|jjrts tdt |jj|jj |jj gdkDr td|+tj|tj|_ n|dk(r-tj|||tj|_ n|dk(r6tj|dz|dz|tjdz|_ nJ|d k(rt|d |_ n2|d k(rt|d |_ nt|d |jd|jz |_tj"|j d|_|j'|d|||_d|_d|_|j,j/d|_y)Nz:Make sure to install scipy if you want to use beta sigmas.rznOnly one of `config.use_beta_sigmas`, `config.use_exponential_sigmas`, `config.use_karras_sigmas` can be used.r.rArB?r rCr")r!r#z is not implemented for ?r)dimcpu)configrKr ImportErrorsumrJrIr0rr4r5r6rOr:NotImplementedError __class__alphascumprodalphas_cumprod set_timesteps _step_index _begin_indexsigmasto)selfr=r>r?r@rDrErIrJrKrLrMrNrRs r__init__zHeunDiscreteScheduler.__init__s" ;; & &/A/CZ[ [  ++T[[-O-OQUQ\Q\QnQno pst tA   $m5==IDJ h & H>QY^YfYfgDJ o - C3H[chcpcpquvvDJ 1 1,-@W_`DJ e #,-@W\]DJ%7OPTP^P^O_&`a aDJJ& #mmDKKQ? .6IJ!2 kknnU+ rtimestepschedule_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) timestepsnonzerolenitem)rergrhindicesposs rindex_for_timestepz(HeunDiscreteScheduler.index_for_timestepsN"  %!% %1::< wj9d|_ycc}wcc}wcc}w)aC Sets the discrete timesteps used for the diffusion chain (to be run before inference). Args: num_inference_steps (`int`, *optional*, defaults to `None`): The number of diffusion steps used when generating samples with a pre-trained model. device (`str`, `torch.device`, *optional*, defaults to `None`): The device to which the timesteps should be moved to. If `None`, the timesteps are not moved. num_train_timesteps (`int`, *optional*, defaults to `None`): The number of diffusion steps used when training the model. If `None`, the default `num_train_timesteps` attribute is used. timesteps (`List[int]`, *optional*, defaults to `None`): 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 --:0D4L4LL  YYq*=>KRRTUYWYUYZ__ahhikisist T[[555 --;043K3KK  YY':A {KRRTYY[bbcecmcmn Q  {{3345NOA 3 33t7J7JJsRSVVF^ 9bii3v;&?H ;; ( (,,vSWSkSk,lFSY!Z%$"2"25*"E!Z[I [[ / /11FXk1lFSY!Z%$"2"25*"E!Z[I [[ ( (**VQd*eFSY!Z%$"2"25*"E!Z[I#077 C!!&),,F,;iiVAb\-K-KA-NPVWYWZP[ \] $$Y/ IIy!}im.M.Ma.PQR "V5==I $ kknnU+ /"["["[s6UU0U r~rctjtj|d}||ddtjfz }tj|dk\dj dj |jddz }|dz}||}||}||z ||z z } tj | dd} d| z |z| |zz} | j|j} | S)a 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 )rrr) rrmaximumnewaxiscumsumargmaxclipshapereshape) rer~r log_sigmadistslow_idxhigh_idxlowhighwr+s rrz!HeunDiscreteScheduler._sigma_to_tusFF2::eU34 Jq"**}55))UaZq188a8@EE*JZJZ[\J]`aJaEbQ;!(#9_t , GGAq! Ug H , IIekk "rrct|jdr|jj}nd}t|jdr|jj}nd}||n|dj }||n|dj }d}t j dd|}|d|z z}|d|z z}||||z zz|z} | S)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_maxrrg@r)hasattrrXrrrmrrO) rerrrrrhoramp min_inv_rho max_inv_rhorcs rrz(HeunDiscreteScheduler._convert_to_karrass$ 4;; , --II 4;; , --II!*!6IIbMTUCUZ]B]3]#^+q.1,-$ [[ ( (H 4#/ +DKK,G,G+HHtu  ;; " "#7#=#=... 0M0M$   $ $ #779DJi'B$.D DG DK!#77:EJ..;q@JB[[F$(D DGDKzB.  A$  +{Ymnnroriginal_samplesnoisec|jj|j|j}|jjdk(rvt j |ra|jj|jt j}|j|jt j}n@|jj|j}|j|j}|j |Dcgc]}|j||}}nG|j|jg|jdz}n|jg|jdz}||j}t|jt|jkr=|jd}t|jt|jkr=|||zz} | Scc}w)am Add noise to the original samples according to the noise schedule at the specified timesteps. Args: original_samples (`torch.Tensor`): The original samples to which noise will be added. noise (`torch.Tensor`): The noise tensor to add to the original samples. timesteps (`torch.Tensor`): The timesteps at which to add noise, determining the noise level from the schedule. Returns: `torch.Tensor`: The noisy samples with added noise scaled according to the timestep schedule. rmpsr.rr)rcrdrr/typeris_floating_pointrjr5ryrprvrflattenrl unsqueeze) rerrrjrcrhr+ step_indicesr~ noisy_sampless r add_noisezHeunDiscreteScheduler.add_noises,'7'>'>FVF\F\]  " " ' '5 0U5L5LY5W!%!2!23C3J3JRWR_R_!2!` ! %5%<%>qAFF>L E$(#X`BFHQ,116*/&+#&GQ., .,., ., TU .,  bjj$u+&= >? .,!!DE.,$D>.,!).,"$.,d^.,!.,""CD.,., .,.,dbf#eU\\12#HPQVQ]Q]H^# #<33  !!(3(t( u||+,  8.2+/-1)- Z,%c]Z,c5<<'(Z,&c] Z, DI& Z,  Z,z""" "J$ELL$s$W\WcWc$NTW\a\h\hFdg..rs !88 A2G 8*8 8(5=*4 *4*4"/2*4 \\ *4Z` /NK` /r