i[ LddlZddlmZddlmZmZmZmZmZddl Z ddl Z ddl m Z mZddlmZmZddlmZdd lmZmZej.eZeGd d eZ dd ed ededde j:fdZde j:de j:fdZGddee Z y)N) dataclass)ListLiteralOptionalTupleUnion) ConfigMixinregister_to_config) BaseOutputlogging) randn_tensor)KarrasDiffusionSchedulersSchedulerMixincXeZdZUdZej ed<dZeej ed<y)%EulerAncestralDiscreteSchedulerOutputaq 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__rr/home/obispo/Crisostomo_bridge/mision_env/lib/python3.12/site-packages/diffusers/schedulers/scheduling_euler_ancestral_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)r r!r"r-betasit1t2s rbetas_for_alpha_barr;3s0x' D  & '=>R=STUU E * +M ( (!e. . S\"- R0@@@(KLM <<U]] 33rr7c(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)r7alphasalphas_cumprodalphas_bar_sqrtalphas_bar_sqrt_0alphas_bar_sqrt_T alphas_bars rrescale_zero_terminal_snrrKas5[F]]6q1N$))+O(*002'+113((O(,=@Q,QRRO!!#J ^j"o -F YY 1Q0 1F JE LrcleZdZdZeDcgc]}|j c}}ZdZe d)de de de de dd e e ejee fd e d d e d de deddfdZedej*fdZede e fdZede e fdZd*de ddfdZdej*de e ej*fdej*fdZd+de de e eej8fddfdZ d+de e ej*fde ej*de fdZde e ej*fddfdZ d,d ej*de e ej*fdej*d!e ej@d"ede e!e"ff d#Z#d$ej*d%ej*d&ej*dej*fd'Z$de fd(Z%ycc}}w)-EulerAncestralDiscreteSchedulera Ancestral sampling with Euler method steps. 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. 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 (`"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). 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. 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). rNnum_train_timesteps beta_startbeta_end beta_schedule)linear scaled_linearsquaredcos_cap_v2 trained_betasprediction_type)epsilonsample v_predictiontimestep_spacing)linspaceleadingtrailing steps_offsetrescale_betas_zero_snrr%c |+tj|tj|_n|dk(r-tj|||tj|_nk|dk(r6tj|dz|dz|tjdz|_n0|dk(rt ||_nt |d|j| rt|j|_d|jz |_ tj|jd |_ | rd |jd <tjd |jz |jz dz} tj| ddd dggjtj} tj | |_d|_tjd |d z |t&ddd j)} tj | |_d|_d|_d|_|j"j3d|_y)Nr/rRrS?r rTz is not implemented for r=rr>gp>r@rFcpu)rr5r6r7r[r;NotImplementedError __class__rKrErArFnparray concatenateastype from_numpysigmasnum_inference_stepsfloatcopy timestepsis_scale_input_called _step_index _begin_indexto) selfrNrOrPrQrUrVrZr^r_rkros r__init__z(EulerAncestralDiscreteScheduler.__init__s  $m5==IDJ h & H>QY^YfYfgDJ o - C3H[chcpcpquvvDJ 1 1,-@ADJ%7OPTP^P^O_&`a a !24::>DJDJJ& #mmDKKQ? !'-D   #A 3 33t7J7JJsRS"u 56==bjjI&&v. $( KK#6#:?*a-OTWWkHaK/C7 33u< % zB. $$\//|7I7IRXdmn!EH$44 "nn\%7%78  A$  5#:N  roriginal_samplesrroc|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. )rr0mpsr/rr@)rkrsrr0typeris_floating_pointror6rrr|rflattenr unsqueeze) rtrrrorkrr, step_indicesr noisy_sampless r add_noisez)EulerAncestralDiscreteScheduler.add_noises,'7'>'>FVF\F\]  " " ' '5 0U5L5LY5W!%!2!23C3J3JRWR_R_!2!` ! %5%<%>qAFF>L E$("QYBFHQGQ',0, 0,0, 0, MN 0,  bjj$u+&= >? 0,!!DE0,""CD0,0,!%0, 0,0,d3%,,33 HSM  !Xc]!!(3(t( eU\\FY@Z_d_k_k0*,*,huSRWR^R^M^G_>`*,lp*,\bf#eU\\12#HPQVQ]Q]H^# #> 1uell/B)C 1 1(04 d lld u||+,d  d EOO, d  d  4e; <d N.,,.||.<< .  .`//C ?sF0rM)g+?r#)!r( dataclassesrtypingrrrrrnumpyrfrconfiguration_utilsr r utilsr r utils.torch_utilsrscheduling_utilsrr get_loggerrrrrrmrr;rKrMrrrrs !88 A',G   H % 8J8 8(5=*4 *4*4"/2*4 \\ *4\!U\\!ell!HD/nkD/r