ic fddlZddlmZddlmZmZmZmZmZddl Z ddl Z ddl m Z mZddlmZmZmZddlmZdd lmZmZerddlZej4eZeGd d eZ dd ed ededde j@fdZ!de j@de j@fdZ"Gddee Z#y)N) dataclass)ListLiteralOptionalTupleUnion) ConfigMixinregister_to_config) BaseOutputis_scipy_availablelogging) randn_tensor)KarrasDiffusionSchedulersSchedulerMixincXeZdZUdZej ed<dZeej ed<y)EulerDiscreteSchedulerOutputaq 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__rrx/home/obispo/Crisostomo_bridge/mision_env/lib/python3.12/site-packages/diffusers/schedulers/scheduling_euler_discrete.pyrr"s' 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_fnPs-88QY%/$''9A=>!C Crr%c2tj|dzS)Ng()r)r%r,s r r.z)betas_for_alpha_bar..alpha_bar_fnUs88AI& &rz"Unsupported alpha_transform_type: rdtype) ValueErrorrangeappendminrtensorfloat32)r!r"r#r.betasit1t2s r betas_for_alpha_barr<6s0x' D  & '=>R=STUU E * +M ( (!e. . S\"- R0@@@(KLM <<U]] 33rr8c(d|z }tj|d}|j}|dj}|dj}||z}||||z z z}|dz}|dd|ddz }tj|dd|g}d|z }|S)a: Rescales betas to have zero terminal SNR Based on https://huggingface.co/papers/2305.08891 (Algorithm 1) Args: betas (`torch.Tensor`): The betas that the scheduler is being initialized with. Returns: `torch.Tensor`: Rescaled betas with zero terminal SNR. ?rdimr rN)rcumprodsqrtclonecat)r8alphasalphas_cumprodalphas_bar_sqrtalphas_bar_sqrt_0alphas_bar_sqrt_T alphas_bars r rescale_zero_terminal_snrrLds5[F]]6q1N$))+O(*002'+113((O(,=@Q,QRRO!!#J ^j"o -F YY 1Q0 1F JE Lrc%eZdZdZeDcgc]}|j c}}ZdZe dGde de de de dd e e ejee fd e d d e d de ede ede ede e de e de dde dde dede df"dZede e ej*ffdZede e fdZede e fdZdHd e ddfd!Zd"ej*d#e e ej*fdej*fd$Z dId%e e d&e e eej8fd'e ee d(e ee ddf d)Zd*ejd+ejdejfd,Zd-ej*d%e dej*fd.Zd-ej*d%e dej*fd/Z dJd-ej*d%e d0e d1e dej*f d2Z! dKd#e e ej*fd3e ej*de fd4Z"d#e e ej*fddfd5Z#d6d6e d7d8dd9fd:ej*d#e e ej*fd"ej*d;e de d?e ejHd@ede e%e&ffdAZ'dBej*dCej*d'ej*dej*fdDZ(d"ej*dCej*d'ej*dej*fdEZ)de fdFZ*ycc}}w)LEulerDiscreteScheduleru" Euler scheduler. 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 (`Literal["linear", "scaled_linear", "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`, *optional*): Pass an array of betas directly to the constructor to bypass `beta_start` and `beta_end`. prediction_type (`Literal["epsilon", "sample", "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). interpolation_type (`Literal["linear", "log_linear"]`, defaults to `"linear"`, *optional*): The interpolation type to compute intermediate sigmas for the scheduler denoising steps. Should be one of `"linear"` or `"log_linear"`. 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. sigma_min (`float`, *optional*): The minimum sigma value for the noise schedule. If not provided, defaults to the last sigma in the schedule. sigma_max (`float`, *optional*): The maximum sigma value for the noise schedule. If not provided, defaults to the first sigma in the schedule. timestep_spacing (`Literal["linspace", "leading", "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. timestep_type (`Literal["discrete", "continuous"]`, defaults to `"discrete"`): The type of timesteps to use. Can be `"discrete"` or `"continuous"`. steps_offset (`int`, defaults to 0): An offset added to the inference steps, as required by some model families. rescale_betas_zero_snr (`bool`, defaults to `False`): Whether to rescale the betas to have zero terminal SNR. This enables the model to generate very bright and dark samples instead of limiting it to samples with medium brightness. Loosely related to [`--offset_noise`](https://github.com/huggingface/diffusers/blob/74fd735eb073eb1d774b1ab4154a0876eb82f055/examples/dreambooth/train_dreambooth.py#L506). final_sigmas_type (`Literal["zero", "sigma_min"]`, defaults to `"zero"`): The final `sigma` value for the noise schedule during the sampling process. If `"sigma_min"`, the final sigma is the same as the last sigma in the training schedule. If `"zero"`, the final sigma is set to 0. rNnum_train_timesteps beta_startbeta_end beta_schedule)linear scaled_linearsquaredcos_cap_v2 trained_betasprediction_type)epsilonsample v_predictioninterpolation_type)rS log_linearuse_karras_sigmasuse_exponential_sigmasuse_beta_sigmas sigma_min sigma_maxtimestep_spacing)linspaceleadingtrailing timestep_type)discrete continuous steps_offsetrescale_betas_zero_snrfinal_sigmas_type)zeror`cN|jjrts tdt |jj|jj |jj gdkDr td|+tj|tj|_ n|dk(r-tj|||tj|_ nk|dk(r6tj|dz|dz|tjdz|_ n0|d k(rt||_ nt|d |j|rt!|j|_ d |jz |_tj$|j"d |_|rd|j&d<d|j&z |j&z dzj)d }t+jd |dz |t,dddj/}tj0|j3tj}d|_|dk(r?|dk(r:tj6|Dcgc]}d|j9zc}|_n||_tj<|tj>d|j@g|_!d|_"||_| |_| |_d|_#d|_$|jBj3d|_!ycc}w)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.r0rSrT?r rUz is not implemented for r>rr?gp>rArhrZ?deviceFcpu)%configr_r ImportErrorsumr^r]r2rr6r7r8rcr<NotImplementedError __class__rLrFrBrGflipnpfloatcopy from_numpytonum_inference_stepsrlog timestepsrEzerosrqsigmasis_scale_input_called _step_index _begin_index)selfrOrPrQrRrVrWr[r]r^r_r`rarbrfrirjrkrrsigmas r __init__zEulerDiscreteScheduler.__init__s* ;; & &/A/CZ[ [  ++T[[-O-OQUQ\Q\QnQno pst tA   $m5==IDJ h & H>QY^YfYfgDJ o - C3H[chcpcpquvvDJ 1 1,-@ADJ%7OPTP^P^O_&`a a !24::>DJDJJ& #mmDKKQ? !'-D   #+++t/B/BBsJPPQRSKK#6#:dk(r&d |jdz |jdz d z}n>|jj>dk(rd}n"td|jj>tj@||ggjtj}t3jB|jEt2j|}|jj dk(rf|jj d k(rMt3jF|dd Dcgc]}d|jzc}jE||_$nGt3jB|jtjjE||_$d|_%d|_&|jEd|_'ycc}wcc}wcc}wcc}wcc}w)a Sets the discrete timesteps used for the diffusion chain (to be run before inference). Args: num_inference_steps (`int`, *optional*): The number of diffusion steps used when generating samples with a pre-trained model. If `None`, `timesteps` or `sigmas` must be provided. device (`str` or `torch.device`, *optional*): The device to which the timesteps should be moved to. If `None`, the timesteps are not moved. timesteps (`List[int]`, *optional*): Custom timesteps used to support arbitrary timesteps schedule. If `None`, timesteps will be generated based on the `timestep_spacing` attribute. If `timesteps` is passed, `num_inference_steps` and `sigmas` must be `None`, and `timestep_spacing` attribute will be ignored. sigmas (`List[float]`, *optional*): Custom sigmas used to support arbitrary timesteps schedule. If `None`, timesteps and sigmas will be generated based on the relevant scheduler attributes. If `sigmas` is passed, `num_inference_steps` and `timesteps` must be `None`, and the timesteps will be generated based on the custom sigmas schedule. Nz2Only one of `timesteps` or `sigmas` should be set.zIMust pass exactly one of `num_inference_steps` or `timesteps` or `sigmas.zFCan only pass one of `num_inference_steps` or `timesteps` or `sigmas`.z>Cannot set `timesteps` with `config.use_karras_sigmas = True`.zCCannot set `timesteps` with `config.use_exponential_sigmas = True`.z.>rzz.JKNNV\N]DN ii& ["`\&_&_&_"+Xs _-_2_7<_< `rrctjtj|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 )rr) ryrmaximumnewaxiscumsumargmaxclipshapereshape) rrr log_sigmadistslow_idxhigh_idxlowhighwr-s r rz"EulerDiscreteScheduler._sigma_to_tsFF2::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. r`NrarArg@r)hasattrrsr`raitemryrc) rrr~r`rarhoramp min_inv_rho max_inv_rhors r rz)EulerDiscreteScheduler._convert_to_karrass$ 4;; , --II 4;; , --II!*!6IIbMT model_outputs_churns_tmins_tmaxs_noise generator return_dictc t|ttjtjfr t d|j stjd|j|j||jtj}|j|j} || cxkr|kr(nn%t|t|jdz z dnd} | | dzz} | dkDrFt!|j"|j$|j&|} | |z}||| dz| dzz d zzz}|j(j*d k(s|j(j*d k(r|}n}|j(j*d k(r || |zz }n[|j(j*d k(r|| | dzdzd zz z|| dzdzz z}n#t d|j(j*d||z | z }|j|jdz| z }|||zz}|j|j$}|xj,dz c_| s||fSt/||S)a Predict the sample from the previous timestep by reversing the SDE. This function propagates the diffusion process from the learned model outputs (most often the predicted noise). Args: model_output (`torch.Tensor`): The direct output from the learned diffusion model. timestep (`float` or `torch.Tensor`): The current discrete timestep in the diffusion chain. sample (`torch.Tensor`): A current instance of a sample created by the diffusion process. s_churn (`float`, *optional*, defaults to `0.0`): Stochasticity parameter that controls the amount of noise added during sampling. Higher values increase randomness. s_tmin (`float`, *optional*, defaults to `0.0`): Minimum timestep threshold for applying stochasticity. Only timesteps above this value will have noise added. s_tmax (`float`, *optional*, defaults to `inf`): Maximum timestep threshold for applying stochasticity. Only timesteps below this value will have noise added. s_noise (`float`, *optional*, defaults to `1.0`): Scaling factor for noise added to the sample. generator (`torch.Generator`, *optional*): A random number generator for reproducible sampling. return_dict (`bool`, *optional*, defaults to `True`): Whether or not to return a [`~schedulers.scheduling_euler_discrete.EulerDiscreteSchedulerOutput`] or tuple. Returns: [`~schedulers.scheduling_euler_discrete.EulerDiscreteSchedulerOutput`] or `tuple`: If `return_dict` is `True`, [`~schedulers.scheduling_euler_discrete.EulerDiscreteSchedulerOutput`] is returned, otherwise a tuple is returned where the first element is the sample tensor and the second element is the predicted original sample. zPassing integer indices (e.g. from `enumerate(timesteps)`) as timesteps to `EulerDiscreteScheduler.step()` is not supported. Make sure to pass one of the `scheduler.timesteps` as a timestep.zThe `scale_model_input` function should be called before `step` to ensure correct denoising. See `StableDiffusionPipeline` for a usage example.rg4y?rr)r1rqrr rnoriginal_samplerYrXrZzprediction_type given as z, must be one of `epsilon`, or `v_prediction`)rr)rintr IntTensor LongTensorr2rloggerwarningrrr}r7rr5rrrr1rqrsrWrr)rrrrYrrrrrrrgamma sigma_hatnoiseepsr derivativedtrs r stepzEulerDiscreteScheduler.stepsk^ heoou7G7G H IG )) NNE  ?? "  ! !( +5==) DOO,EKuE^X^E^Gs4;;/!34jAdgUQY' 19 "",*<*<\EXEXdmE'/CcY\E1H%<$DDDF ;; & &*; ;t{{?Z?Z^f?f#/ [[ ( (I 5#)I ,D#D [[ ( (N :#/E6UAX\c'>FVF\F\]  " " ' '5 0U5L5LY5W!%!2!23C3J3JRWR_R_!2!` ! %5%<%>qAFF>L E$("QYBFHQ>F,116*/%)%)GQ;E',:@%H, H,H, H, MN H,  bjj$u+&= >? H,!!DEH,$$:;H,$D>H,!)H,"$H,E?H,E?H,""CDH,78H, !H,"!%#H,$##67%H,H,T )%u||(;"< ) ) HSM  !Xc]!!(3(t( eU\\FY@Z_d_k_k4.259)-(, C'%c]C'sELL012C'DI& C' e% C'  C'J""" "J$ELL$s$W\WcWc$NTW\a\h\hDdg..rs !88 A;;,G   H % 8:8 8(5=*4 *4*4"/2*4 \\ *4\!U\\!ell!H{ /^[{ /r