o pi@sddlZddlmZddlmZmZmZddlZddlm Z m Z ddl m Z ddl mZdd lmZ dd d ZeGddde ZGdddee ZdS)N) dataclass)OptionalTupleUnion) ConfigMixinregister_to_config) BaseOutput) randn_tensor)SchedulerMixin+?cosinecCs|dkr dd}n|dkrdd}ntd|g}t|D]}||}|d|}|td|||||qtj|tjdS) 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 rcSs t|ddtjddS)NgMb?gT㥛 ?r)mathcospitrq/home/ubuntu/SoloSpeech/.venv/lib/python3.10/site-packages/diffusers/schedulers/scheduling_consistency_decoder.py alpha_bar_fn's z)betas_for_alpha_bar..alpha_bar_fnexpcSst|dS)Ng()rrrrrrr,sz"Unsupported alpha_transform_type: r )dtype) ValueErrorrangeappendmintorchtensorfloat32)num_diffusion_timestepsmax_betaalpha_transform_typerbetasit1t2rrrbetas_for_alpha_bars    "r'c@seZdZUdZejed<dS)!ConsistencyDecoderSchedulerOutputa> Output class for the scheduler's `step` function. 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. prev_sampleN)__name__ __module__ __qualname____doc__rTensor__annotations__rrrrr(:s  r(c@seZdZdZe  ddedefddZ  dd eed e e e j ffd d Z ed dZdde jdeede jfddZ  dde jde ee jfde jdee jdede eeff ddZdS)ConsistencyDecoderSchedulerr ?num_train_timesteps sigma_datacCst|}d|}tj|dd}t||_td||_td|d}td|}||d|d|d|_|||d|dd|_||d|dd|_dS)Ng?r)dimr rr2) r'rcumprodsqrtsqrt_alphas_cumprodsqrt_one_minus_alphas_cumprodc_skipc_outc_in)selfr3r4r#alphasalphas_cumprodsigmassqrt_recip_alphas_cumprodrrr__init__Ks z$ConsistencyDecoderScheduler.__init__Nnum_inference_stepsdevicecCsr|dkrtdtjddgtj|d|_|j||_|j||_|j||_|j ||_ |j ||_ dS)Nrz8Currently more than 2 inference steps are not supported.ii)rrD) rrrlong timestepsr8tor9r:r;r<)r=rCrDrrr set_timestepsasz)ConsistencyDecoderScheduler.set_timestepscCs|j|jdS)Nr)r9rF)r=rrrinit_noise_sigmapsz,ConsistencyDecoderScheduler.init_noise_sigmasampletimestepreturncCs||j|S)a Ensures interchangeability with schedulers that need to scale the denoising model input depending on the current timestep. Args: sample (`torch.Tensor`): The input sample. timestep (`int`, *optional*): The current timestep in the diffusion chain. Returns: `torch.Tensor`: A scaled input sample. )r<)r=rJrKrrrscale_model_inputtsz-ConsistencyDecoderScheduler.scale_model_inputT model_output generator return_dictc Cs|j|||j||}t|j|kd}|t|jdkr$|}n+t|j||j|j d} |j |j|d |j||j |j|d |j| }|sT|fSt |dS)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`): The current timestep in the diffusion chain. sample (`torch.Tensor`): A current instance of a sample created by the diffusion process. generator (`torch.Generator`, *optional*): A random number generator. return_dict (`bool`, *optional*, defaults to `True`): Whether or not to return a [`~schedulers.scheduling_consistency_models.ConsistencyDecoderSchedulerOutput`] or `tuple`. Returns: [`~schedulers.scheduling_consistency_models.ConsistencyDecoderSchedulerOutput`] or `tuple`: If return_dict is `True`, [`~schedulers.scheduling_consistency_models.ConsistencyDecoderSchedulerOutput`] is returned, otherwise a tuple is returned where the first element is the sample tensor. rr )rOrrD)r))r;r:rwhererFlenr shaperrDr8rGr9r() r=rNrKrJrOrPx_0 timestep_idxr)noiserrrsteps z ConsistencyDecoderScheduler.step)r1r2)NN)N)NT)r*r+r,orderrintfloatrBrrstrrrDrHpropertyrIr.rM Generatorboolr(rrWrrrrr0HsF       r0)r r)r dataclassesrtypingrrrrconfiguration_utilsrrutilsr utils.torch_utilsr scheduling_utilsr r'r(r0rrrrs     ,