o Gi+@sddlmZddlZddlmZddlmZmZddl m Z ddl m Z m Z mZmZmZe eZejjGdd d ZeGd d d eZGd d d eeZdS)) dataclassN) ConfigMixinregister_to_config)logging)CommonSchedulerStateFlaxKarrasDiffusionSchedulersFlaxSchedulerMixinFlaxSchedulerOutputbroadcast_to_shape_from_leftc @sdeZdZUeed<ejed<ejed<ejed<dZeed<e dedejdejdejfddZ dS) EulerDiscreteSchedulerStatecommoninit_noise_sigma timestepssigmasNnum_inference_stepscCs|||||dS)Nrrrr)clsrrrrrrg/home/ubuntu/.local/lib/python3.10/site-packages/diffusers/schedulers/scheduling_euler_discrete_flax.pycreate,s z"EulerDiscreteSchedulerState.create) __name__ __module__ __qualname__r__annotations__jnpndarrayrint classmethodrrrrrr "s     r c@seZdZUeed<dS) FlaxEulerDiscreteSchedulerOutputstateN)rrrr rrrrrr <s r c@s0eZdZUdZddeDZejed<e ddZ e ddd d d d d ej fde dedededejd BdededejfddZd1ded BdefddZdedejde dejfddZ d2ded!e d"edefd#d$Z %d3ded&ejde dejd'edeeBf d(d)Zded*ejd+ejd,ejdejf d-d.Zd/d0Zd S)4FlaxEulerDiscreteSchedulera Euler scheduler (Algorithm 2) from Karras et al. (2022) https://huggingface.co/papers/2206.00364. . Based on the original k-diffusion implementation by Katherine Crowson: https://github.com/crowsonkb/k-diffusion/blob/481677d114f6ea445aa009cf5bd7a9cdee909e47/k_diffusion/sampling.py#L51 [`~ConfigMixin`] takes care of storing all config attributes that are passed in the scheduler's `__init__` function, such as `num_train_timesteps`. They can be accessed via `scheduler.config.num_train_timesteps`. [`SchedulerMixin`] provides general loading and saving functionality via the [`SchedulerMixin.save_pretrained`] and [`~SchedulerMixin.from_pretrained`] functions. Args: num_train_timesteps (`int`): number of diffusion steps used to train the model. beta_start (`float`): the starting `beta` value of inference. beta_end (`float`): the final `beta` value. beta_schedule (`str`): the beta schedule, a mapping from a beta range to a sequence of betas for stepping the model. Choose from `linear` or `scaled_linear`. trained_betas (`jnp.ndarray`, optional): option to pass an array of betas directly to the constructor to bypass `beta_start`, `beta_end` etc. prediction_type (`str`, default `epsilon`, optional): prediction type of the scheduler function, one of `epsilon` (predicting the noise of the diffusion process), `sample` (directly predicting the noisy sample`) or `v_prediction` (see section 2.4 https://huggingface.co/papers/2210.02303) dtype (`jnp.dtype`, *optional*, defaults to `jnp.float32`): the `dtype` used for params and computation. cCsg|]}|jqSr)name).0errr ^sz%FlaxEulerDiscreteScheduler.dtypecCsdS)NTrselfrrr has_statebsz$FlaxEulerDiscreteScheduler.has_stateig-C6?g{Gz?linearNepsilonlinspacenum_train_timesteps beta_startbeta_end beta_schedule trained_betasprediction_typetimestep_spacingc Cstd||_dS)NzFlax classes are deprecated and will be removed in Diffusers v1.0.0. We recommend migrating to PyTorch classes or pinning your version of Diffusers.)loggerwarningr') r)r.r/r0r1r2r3r4r'rrr__init__fs  z#FlaxEulerDiscreteScheduler.__init__rreturncCs|dur t|}td|jjddd}d|j|jd}t|tdt ||}t |tj dg|j dg}|jj dvrH|}n |ddd}tj||||d S) Nrr?r'r-trailingrr)rrrarangeconfigr.roundalphas_cumprodinterplen concatenatearrayr'r4maxr )r)rrrrrrr create_statexs   z'FlaxEulerDiscreteScheduler.create_stater!sampletimestepcCs@tj|j|kdd\}|d}|j|}||ddd}|S)a  Scales the denoising model input by `(sigma**2 + 1) ** 0.5` to match the Euler algorithm. Args: state (`EulerDiscreteSchedulerState`): the `FlaxEulerDiscreteScheduler` state data class instance. sample (`jnp.ndarray`): current instance of sample being created by diffusion process. timestep (`int`): current discrete timestep in the diffusion chain. Returns: `jnp.ndarray`: scaled input sample rsizerrr:)rwhererr)r)r!rIrJ step_indexsigmarrrscale_model_inputs  z,FlaxEulerDiscreteScheduler.scale_model_inputrrshapecCs|jjdkrtj|jjdd||jd}n.|jjdkr:|jj|}td||ddd t }|d7}n t d|jjd|j j |j j d }t|tdt||}t|tjd g|jdg}|jjd vru|}n |d dd }|j||||d S)a Sets the timesteps used for the diffusion chain. Supporting function to be run before inference. Args: state (`EulerDiscreteSchedulerState`): the `FlaxEulerDiscreteScheduler` state data class instance. num_inference_steps (`int`): the number of diffusion steps used when generating samples with a pre-trained model. r-rrr<leadingNr9z=timestep_spacing must be one of ['linspace', 'leading'], got r:r;r=r)rrrr)r@r4rr-r.r'r?rAcopyastypefloat ValueErrorrrBrCrDrErFrGreplace)r)r!rrQr step_ratiorrrrr set_timestepss4    (    z(FlaxEulerDiscreteScheduler.set_timestepsT model_output return_dictc Cs|jdur tdtj|j|kdd\}|d}|j|}|jjdkr*|||}n&|jjdkrF|| |ddd ||dd}n td |jjd |||} |j|d|} || | } |sk| |fSt| |d S) a Predict the sample at the previous timestep by reversing the SDE. Core function to propagate the diffusion process from the learned model outputs (most often the predicted noise). Args: state (`EulerDiscreteSchedulerState`): the `FlaxEulerDiscreteScheduler` state data class instance. model_output (`jnp.ndarray`): direct output from learned diffusion model. timestep (`int`): current discrete timestep in the diffusion chain. sample (`jnp.ndarray`): current instance of sample being created by diffusion process. order: coefficient for multi-step inference. return_dict (`bool`): option for returning tuple rather than FlaxEulerDiscreteScheduler class Returns: [`FlaxEulerDiscreteScheduler`] or `tuple`: [`FlaxEulerDiscreteScheduler`] if `return_dict` is True, otherwise a `tuple`. When returning a tuple, the first element is the sample tensor. NzaNumber of inference steps is 'None', you need to run 'set_timesteps' after creating the schedulerrrKrr, v_predictionrr:zprediction_type given as z, must be one of `epsilon`, or `v_prediction`) prev_sampler!) rrVrrMrrr@r3r ) r)r!rZrJrIr[rNrOpred_original_sample derivativedtr]rrrsteps(    ,   zFlaxEulerDiscreteScheduler.steporiginal_samplesnoisercCs*|j|}t||j}|||}|SN)rflattenr rQ)r)r!rbrcrrO noisy_samplesrrr add_noises  z$FlaxEulerDiscreteScheduler.add_noisecCs|jjSrd)r@r.r(rrr__len__ sz"FlaxEulerDiscreteScheduler.__len__rd)r)T)rrr__doc__r _compatiblesrr'rpropertyr*rfloat32rrUstrrr7rr rHrPtuplerYboolr rargrhrrrrr"As     7 = r") dataclassesrflax jax.numpynumpyrconfiguration_utilsrrutilsrscheduling_utils_flaxrr r r r get_loggerrr5structr r r"rrrrs