ihq $ddlZddlmZddlmZmZmZmZmZddl Z ddl Z ddl m Z mZddlmZddlmZdd lmZmZeGd d eZ dd ed ededde j2fdZde j2de j2fdZGddee Zy)N) dataclass)ListLiteralOptionalTupleUnion) ConfigMixinregister_to_config) BaseOutput) randn_tensor)KarrasDiffusionSchedulersSchedulerMixincXeZdZUdZej ed<dZeej ed<y)DDPMSchedulerOutputaq 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__rrn/home/obispo/Crisostomo_bridge/mision_env/lib/python3.12/site-packages/diffusers/schedulers/scheduling_ddpm.pyrrs' 37(5<<07rrnum_diffusion_timestepsmax_betaalpha_transform_type)cosineexpreturnc $|dk(rd}n|dk(rd}ntd|g}t|D]<}||z }|dz|z }|jtd||||z z |>t j |tj S)aB Create a beta schedule that discretizes the given alpha_t_bar function, which defines the cumulative product of (1-beta) over time from t = [0,1]. Contains a function alpha_bar that takes an argument t and transforms it to the cumulative product of (1-beta) up to that part of the diffusion process. Args: num_diffusion_timesteps (`int`): The number of betas to produce. max_beta (`float`, defaults to `0.999`): The maximum beta to use; use values lower than 1 to avoid numerical instability. alpha_transform_type (`"cosine"` or `"exp"`, defaults to `"cosine"`): The type of noise schedule for `alpha_bar`. Choose from `cosine` or `exp`. Returns: `torch.Tensor`: The betas used by the scheduler to step the model outputs. r"cftj|dzdz tjzdz dzS)NgMb?gT㥛 ?r )mathcospits r alpha_bar_fnz)betas_for_alpha_bar..alpha_bar_fnJs-88QY%/$''9A=>!C Crr#c2tj|dzS)Ng()r'r#r*s rr,z)betas_for_alpha_bar..alpha_bar_fnOs88AI& &rz"Unsupported alpha_transform_type: rdtype) ValueErrorrangeappendminrtensorfloat32)rr r!r,betasit1t2s rbetas_for_alpha_barr:0s0x' D  & '=>R=STUU E * +M ( (!e. . S\"- R0@@@(KLM <<U]] 33rr6c(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)r6alphasalphas_cumprodalphas_bar_sqrtalphas_bar_sqrt_0alphas_bar_sqrt_T alphas_bars rrescale_zero_terminal_snrrJ^s5[F]]6q1N$))+O(*002'+113((O(,=@Q,QRRO!!#J ^j"o -F YY 1Q0 1F JE Lrc eZdZdZeDcgc]}|j c}}ZdZe d.de de de de dd e e ejee fd e d d ed e ddede de de de dde defdZd/dej(de e dej(fdZ d0de e de eej.fde ee fdZ d1d e d!e ej(d e e d dej(fd"Zdej(dej(fd#Z d2d$ej(de dej(d%e ej6d&ede eeff d'Zd(ej(d)ej(dej>dej(fd*Z dej(d)ej(dej>dej(fd+Z!de fd,Z"de de fd-Z#ycc}}w)3 DDPMSchedulera `DDPMScheduler` explores the connections between denoising score matching and Langevin dynamics sampling. 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 `"sigmoid"`, defaults to `"linear"`): The beta schedule, a mapping from a beta range to a sequence of betas for stepping the model. trained_betas (`np.ndarray`, *optional*): An array of betas to pass directly to the constructor without using `beta_start` and `beta_end`. variance_type (`"fixed_small"`, `"fixed_small_log"`, `"fixed_large"`, `"fixed_large_log"`, `"learned"`, or `"learned_range"`, defaults to `"fixed_small"`): Clip the variance when adding noise to the denoised sample. 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`. prediction_type (`"epsilon"`, `"sample"`, or `"v_prediction"`, defaults to `"epsilon"`): 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). thresholding (`bool`, defaults to `False`): Whether to use the "dynamic thresholding" method. This is unsuitable for latent-space diffusion models such as Stable Diffusion. dynamic_thresholding_ratio (`float`, defaults to `0.995`): The ratio for the dynamic thresholding method. Valid only when `thresholding=True`. sample_max_value (`float`, defaults to `1.0`): The threshold value for dynamic thresholding. Valid only when `thresholding=True`. timestep_spacing (`"linspace"`, `"leading"`, or `"trailing"`, defaults to `"leading"`): 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_v2sigmoid trained_betas variance_type) fixed_smallfixed_small_log fixed_largefixed_large_loglearned learned_range clip_sampleprediction_type)epsilonsample v_prediction thresholdingdynamic_thresholding_ratioclip_sample_rangesample_max_valuetimestep_spacing)linspaceleadingtrailing steps_offsetrescale_betas_zero_snrc|+tj|tj|_n|dk(r-tj|||tj|_n|dk(r6tj|dz|dz|tjdz|_np|dk(rt ||_nZ|dk(r;tjdd |}tj |||z z|z|_nt|d |j|rt|j|_d |jz |_ tj|jd |_ tjd |_ d |_d|_d|_tj"t%j&d |dddj)|_||_y)Nr.rQrR?r rSrTiz is not implemented for r<rr=Fr?)rr4r5r6rgr:rTNotImplementedError __class__rJrDr@rEoneinit_noise_sigmacustom_timestepsnum_inference_steps from_numpynparangecopy timestepsrV)selfrMrNrOrPrUrVr]r^rbrcrdrerfrjrkr6s r__init__zDDPMScheduler.__init__s*  $m5==IDJ h & H>QY^YfYfgDJ o - C3H[chcpcpquvvDJ 1 1,-@ADJ i 'NN2q*=>Eu-J1FG*TDJ%7OPTP^P^O_&`a a "24::>DJDJJ& #mmDKKQ?<<$!$!&#' ))"))A7J*KDbD*Q*V*V*XY*rr`timestepr$c|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)rzr`r|s rscale_model_inputzDDPMScheduler.scale_model_inputs  rrtdeviceryc l| | td|tdt|D]}||||dz k\std|d|jjk\r#td|jjdt j |t j}d |_nZ||jjkDr=td |d |jjd |jjd ||_ d|_|jjdk(rot jd|jjdz |jdddjjt j}nn|jjdk(r|jj|jz}t jd||zjdddjjt j}||jj z }n|jjdk(r|jj|jz }t jt j|jjd| jt j}|dz}n"t|jjdt#j$|j'||_y)a, Sets the discrete timesteps used for the diffusion chain (to be run before inference). Args: num_inference_steps (`int`): The number of diffusion steps used when generating samples with a pre-trained model. If used, `timesteps` must be `None`. device (`str` or `torch.device`, *optional*): The device to which the timesteps should be moved to. If `None`, the timesteps are not moved. timesteps (`List[int]`, *optional*): Custom timesteps used to support arbitrary spacing between timesteps. If `None`, then the default timestep spacing strategy of equal spacing between timesteps is used. If `timesteps` is passed, `num_inference_steps` must be `None`. NzACan only pass one of `num_inference_steps` or `custom_timesteps`.rz/`custom_timesteps` must be in descending order.rz=`timesteps` must start before `self.config.train_timesteps`: .r.Tz`num_inference_steps`: z6 cannot be larger than `self.config.train_timesteps`: zG as the unet model trained with this scheduler can only handle maximal z timesteps.Frgr?rhrizY is not supported. Please make sure to choose one of 'linspace', 'leading' or 'trailing'.)r0r1lenconfigrMrvarrayint64rsrtrfrgroundrxastyperwrjrrutory)rzrtrryr7 step_ratios r set_timestepszDDPMScheduler.set_timestepss*  *y/D`a a  1c)n- XQ<9QU#33$%VWW X|t{{>>> STXT_T_TsTsSttuv"((;I$(D !"T[[%D%DD -.A-BC 7789 $ ? ?@ M (;D $$)D !{{++z9KK4;;#B#BQ#FH[\UWTrT#TVVBHH%  --:![[<<@X@XX  YYq*=>KRRTUYWYUYZ__ahhikiqiqr T[[555 --;![[<?.P;;xU3   KK55M M )H$!/ /yy*Hyyx0Hm +%H/ /yy0Hi '% % o -ii)Gii/G&*a/Dg~TW(< 1, then we threshold xt0 to the range [-s, s] and then divide by s. Dynamic thresholding pushes saturated pixels (those near -1 and 1) inwards, thereby actively preventing pixels from saturation at each step. We find that dynamic thresholding results in significantly better photorealism as well as better image-text alignment, especially when using very large guidance weights." https://huggingface.co/papers/2205.11487 Args: sample (`torch.Tensor`): The predicted sample to be thresholded. Returns: `torch.Tensor`: The thresholded sample. rr=)r3max)r/shaperr5float64floatreshapervprodabsquantilerrcrre unsqueezer)rzr`r/ batch_sizechannelsremaining_dims abs_sampless r_threshold_samplezDDPMScheduler._threshold_samples( 06 - H~  6 6\\^F Hrww~7N,NOZZ\ NN:t{{'M'MST U KK 1$++66  KKNVaR+a/ HF~F5! r model_output generator return_dictcX|}|j|}|jd|jddzk(r7|jdvr)tj||jdd\}}nd}|j |} |dk\r|j |n |j } d| z } d| z } | | z } d| z }|jjdk(r|| dz|zz | dzz }nj|jjd k(r|}nN|jjd k(r| dz|z| dz|zz }n#td |jjd |jjr|j|}nQ|jjr;|j|jj |jj}| dz|z| z }| dz| z| z }||z||zz}d}|dkDr|j}t!|j|||j" }|jdk(r|j%|||z}nW|jdk(r/|j%||}tj&d|z|z}n|j%||dz|z}||z}|s||fSt)||S)aI 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 learned diffusion model. timestep (`int`): The current discrete 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`, defaults to `True`): Whether or not to return a [`~schedulers.scheduling_ddpm.DDPMSchedulerOutput`] or `tuple`. Returns: [`~schedulers.scheduling_ddpm.DDPMSchedulerOutput`] or `tuple`: If return_dict is `True`, [`~schedulers.scheduling_ddpm.DDPMSchedulerOutput`] is returned, otherwise a tuple is returned where the first element is the sample tensor. rr )r[r\r=Nrr_rmr`razprediction_type given as zM must be one of `epsilon`, `sample` or `v_prediction` for the DDPMScheduler.)rrr/rX)rr\)rr)rrrVrsplitrErqrr^r0rbrr]rrdrr r/rr#r)rzrr|r`rrr+rrrr beta_prod_tbeta_prod_t_prevcurrent_alpha_trrpred_original_sample_coeffcurrent_sample_coeffpred_prev_samplerrvariance_noises rstepzDDPMScheduler.steps: ''*   a FLLOa$7 7D&QU`%`".37:JJ[X68LLOcflOll q5!((F)""ilN`N`N!!%66--aDV-WZhh##6--aDV-W 99S8^4~E ..qEW.X\__cqq+h6 $  #/?Vjkkroriginal_samplesnoisec|jj|j|_|jj|j}|j|j}||dz}|j }t |j t |j kr=|jd}t |j t |j kr=d||z dz}|j }t |j t |j kr=|jd}t |j t |j kr=||z||zz}|S)a2 Add noise to the original samples according to the noise magnitude at each timestep (this is the forward diffusion process). Args: original_samples (`torch.Tensor`): The original samples to which noise will be added. noise (`torch.Tensor`): The noise to add to the samples. timesteps (`torch.IntTensor`): The timesteps indicating the noise level for each sample. Returns: `torch.Tensor`: The noisy samples. rr.rmr?rrErrr/flattenrrr)rzrrryrEsqrt_alpha_prodsqrt_one_minus_alpha_prod noisy_sampless r add_noisezDDPMScheduler.add_noisesa2#1144>qAFF>L E$("\dBF  HQ",1#&"%GP',%5+ 5+5+ 5+ XY 5+  bjj$u+&= >? 5+ j 5+5+!!DE5+5+%*5+!5+ 5+ ""CD!5+"#5+$!%%5+5+n  Y^YeYe&.2+/)- H@%c]H@c5<<'(H@DI& H@Z6:  > >%U\\2> r s > >@) ))`04 dllldldl dl EOO, dl  dl "E) *dlL(,,(||(?? (  (T 5<<  QVQ`Q` ejeqeq D//##m ?sF=rL)g+?r")r' dataclassesrtypingrrrrrnumpyrvrconfiguration_utilsr r utilsr utils.torch_utilsr scheduling_utilsrrrrrrr:rJrLrrrrs" !88 A,G 8*8 8&5=*4 *4*4"/2*4 \\ *4\!U\\!ell!HxNKxr