diffusers/pr_10101/en/_app/immutable/nodes/155.bb70ef70.js

import{s as it,o as dt,n as lt}from"../chunks/scheduler.8c3d61f6.js";import{S as at,i as ct,g as i,s as o,r as u,A as pt,h as d,f as s,c as n,j as S,u as m,x as _,k as M,y as t,a as c,v as f,d as h,t as v,w as g}from"../chunks/index.da70eac4.js";import{T as ut}from"../chunks/Tip.1d9b8c37.js";import{D}from"../chunks/Docstring.6b390b9a.js";import{H as Ie,E as mt}from"../chunks/EditOnGithub.1e64e623.js";function ft(ae){let p,O=`The algorithm and model type are decoupled. You can use either DPMSolver or DPMSolver++ for both noise
prediction and data prediction models.`;return{c(){p=i("p"),p.textContent=O},l(b){p=d(b,"P",{"data-svelte-h":!0}),_(p)!=="svelte-95n5s"&&(p.textContent=O)},m(b,X){c(b,p,X)},p:lt,d(b){b&&s(p)}}}function ht(ae){let p,O,b,X,E,ce,N,Be='<code>DPMSolverMultistepInverse</code> is the inverted scheduler from <a href="https://huggingface.co/papers/2206.00927" rel="nofollow">DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps</a> and <a href="https://huggingface.co/papers/2211.01095" rel="nofollow">DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models</a> by Cheng Lu, Yuhao Zhou, Fan Bao, Jianfei Chen, Chongxuan Li, and Jun Zhu.',pe,q,Ye='The implementation is mostly based on the DDIM inversion definition of <a href="https://huggingface.co/papers/2211.09794" rel="nofollow">Null-text Inversion for Editing Real Images using Guided Diffusion Models</a> and notebook implementation of the <code>DiffEdit</code> latent inversion from <a href="https://github.com/Xiang-cd/DiffEdit-stable-diffusion/blob/main/diffedit.ipynb" rel="nofollow">Xiang-cd/DiffEdit-stable-diffusion</a>.',ue,k,me,A,Je=`Dynamic thresholding from <a href="https://huggingface.co/papers/2205.11487" rel="nofollow">Imagen</a> is supported, and for pixel-space
diffusion models, you can set both <code>algorithm_type=&quot;dpmsolver++&quot;</code> and <code>thresholding=True</code> to use the dynamic
thresholding. This thresholding method is unsuitable for latent-space diffusion models such as
Stable Diffusion.`,fe,F,he,l,H,we,Z,Xe='<code>DPMSolverMultistepInverseScheduler</code> is the reverse scheduler of <a href="/docs/diffusers/pr_10101/en/api/schedulers/multistep_dpm_solver#diffusers.DPMSolverMultistepScheduler">DPMSolverMultistepScheduler</a>.',Ce,K,Ze=`This model inherits from <a href="/docs/diffusers/pr_10101/en/api/schedulers/overview#diffusers.SchedulerMixin">SchedulerMixin</a> and <a href="/docs/diffusers/pr_10101/en/api/configuration#diffusers.ConfigMixin">ConfigMixin</a>. Check the superclass documentation for the generic
methods the library implements for all schedulers such as loading and saving.`,Le,x,V,Oe,Q,Ke=`Convert the model output to the corresponding type the DPMSolver/DPMSolver++ algorithm needs. DPM-Solver is
designed to discretize an integral of the noise prediction model, and DPM-Solver++ is designed to discretize an
integral of the data prediction model.`,Ee,y,Ne,T,z,qe,ee,Qe="One step for the first-order DPMSolver (equivalent to DDIM).",ke,P,W,Ae,te,et="One step for the second-order multistep DPMSolver.",Fe,I,j,He,se,tt="One step for the third-order multistep DPMSolver.",Ve,w,G,ze,re,st=`Ensures interchangeability with schedulers that need to scale the denoising model input depending on the
current timestep.`,We,C,U,je,oe,rt="Sets the discrete timesteps used for the diffusion chain (to be run before inference).",Ge,L,R,Ue,ne,ot=`Predict the sample from the previous timestep by reversing the SDE. This function propagates the sample with
the multistep DPMSolver.`,ve,B,ge,$,Y,Re,ie,nt="Base class for the output of a scheduler’s <code>step</code> function.",_e,J,be,le,Se;return E=new Ie({props:{title:"DPMSolverMultistepInverse",local:"dpmsolvermultistepinverse",headingTag:"h1"}}),k=new Ie({props:{title:"Tips",local:"tips",headingTag:"h2"}}),F=new Ie({props:{title:"DPMSolverMultistepInverseScheduler",local:"diffusers.DPMSolverMultistepInverseScheduler",headingTag:"h2"}}),H=new D({props:{name:"class diffusers.DPMSolverMultistepInverseScheduler",anchor:"diffusers.DPMSolverMultistepInverseScheduler",parameters:[{name:"num_train_timesteps",val:": int = 1000"},{name:"beta_start",val:": float = 0.0001"},{name:"beta_end",val:": float = 0.02"},{name:"beta_schedule",val:": str = 'linear'"},{name:"trained_betas",val:": typing.Union[numpy.ndarray, typing.List[float], NoneType] = None"},{name:"solver_order",val:": int = 2"},{name:"prediction_type",val:": str = 'epsilon'"},{name:"thresholding",val:": bool = False"},{name:"dynamic_thresholding_ratio",val:": float = 0.995"},{name:"sample_max_value",val:": float = 1.0"},{name:"algorithm_type",val:": str = 'dpmsolver++'"},{name:"solver_type",val:": str = 'midpoint'"},{name:"lower_order_final",val:": bool = True"},{name:"euler_at_final",val:": bool = False"},{name:"use_karras_sigmas",val:": typing.Optional[bool] = False"},{name:"use_exponential_sigmas",val:": typing.Optional[bool] = False"},{name:"use_beta_sigmas",val:": typing.Optional[bool] = False"},{name:"lambda_min_clipped",val:": float = -inf"},{name:"variance_type",val:": typing.Optional[str] = None"},{name:"timestep_spacing",val:": str = 'linspace'"},{name:"steps_offset",val:": int = 0"}],parametersDescription:[{anchor:"diffusers.DPMSolverMultistepInverseScheduler.num_train_timesteps",description:`<strong>num_train_timesteps</strong> (<code>int</code>, defaults to 1000) &#x2014;
The number of diffusion steps to train the model.`,name:"num_train_timesteps"},{anchor:"diffusers.DPMSolverMultistepInverseScheduler.beta_start",description:`<strong>beta_start</strong> (<code>float</code>, defaults to 0.0001) &#x2014;
The starting <code>beta</code> value of inference.`,name:"beta_start"},{anchor:"diffusers.DPMSolverMultistepInverseScheduler.beta_end",description:`<strong>beta_end</strong> (<code>float</code>, defaults to 0.02) &#x2014;
The final <code>beta</code> value.`,name:"beta_end"},{anchor:"diffusers.DPMSolverMultistepInverseScheduler.beta_schedule",description:`<strong>beta_schedule</strong> (<code>str</code>, defaults to <code>&quot;linear&quot;</code>) &#x2014;
The beta schedule, a mapping from a beta range to a sequence of betas for stepping the model. Choose from
<code>linear</code>, <code>scaled_linear</code>, or <code>squaredcos_cap_v2</code>.`,name:"beta_schedule"},{anchor:"diffusers.DPMSolverMultistepInverseScheduler.trained_betas",description:`<strong>trained_betas</strong> (<code>np.ndarray</code>, <em>optional</em>) &#x2014;
Pass an array of betas directly to the constructor to bypass <code>beta_start</code> and <code>beta_end</code>.`,name:"trained_betas"},{anchor:"diffusers.DPMSolverMultistepInverseScheduler.solver_order",description:`<strong>solver_order</strong> (<code>int</code>, defaults to 2) &#x2014;
The DPMSolver order which can be <code>1</code> or <code>2</code> or <code>3</code>. It is recommended to use <code>solver_order=2</code> for guided
sampling, and <code>solver_order=3</code> for unconditional sampling.`,name:"solver_order"},{anchor:"diffusers.DPMSolverMultistepInverseScheduler.prediction_type",description:`<strong>prediction_type</strong> (<code>str</code>, defaults to <code>epsilon</code>, <em>optional</em>) &#x2014;
Prediction type of the scheduler function; can be <code>epsilon</code> (predicts the noise of the diffusion process),
<code>sample</code> (directly predicts the noisy sample<code>) or </code>v_prediction\` (see section 2.4 of <a href="https://imagen.research.google/video/paper.pdf" rel="nofollow">Imagen
Video</a> paper).`,name:"prediction_type"},{anchor:"diffusers.DPMSolverMultistepInverseScheduler.thresholding",description:`<strong>thresholding</strong> (<code>bool</code>, defaults to <code>False</code>) &#x2014;
Whether to use the &#x201C;dynamic thresholding&#x201D; method. This is unsuitable for latent-space diffusion models such
as Stable Diffusion.`,name:"thresholding"},{anchor:"diffusers.DPMSolverMultistepInverseScheduler.dynamic_thresholding_ratio",description:`<strong>dynamic_thresholding_ratio</strong> (<code>float</code>, defaults to 0.995) &#x2014;
The ratio for the dynamic thresholding method. Valid only when <code>thresholding=True</code>.`,name:"dynamic_thresholding_ratio"},{anchor:"diffusers.DPMSolverMultistepInverseScheduler.sample_max_value",description:`<strong>sample_max_value</strong> (<code>float</code>, defaults to 1.0) &#x2014;
The threshold value for dynamic thresholding. Valid only when <code>thresholding=True</code> and
<code>algorithm_type=&quot;dpmsolver++&quot;</code>.`,name:"sample_max_value"},{anchor:"diffusers.DPMSolverMultistepInverseScheduler.algorithm_type",description:`<strong>algorithm_type</strong> (<code>str</code>, defaults to <code>dpmsolver++</code>) &#x2014;
Algorithm type for the solver; can be <code>dpmsolver</code>, <code>dpmsolver++</code>, <code>sde-dpmsolver</code> or <code>sde-dpmsolver++</code>. The
<code>dpmsolver</code> type implements the algorithms in the <a href="https://huggingface.co/papers/2206.00927" rel="nofollow">DPMSolver</a>
paper, and the <code>dpmsolver++</code> type implements the algorithms in the
<a href="https://huggingface.co/papers/2211.01095" rel="nofollow">DPMSolver++</a> paper. It is recommended to use <code>dpmsolver++</code> or
<code>sde-dpmsolver++</code> with <code>solver_order=2</code> for guided sampling like in Stable Diffusion.`,name:"algorithm_type"},{anchor:"diffusers.DPMSolverMultistepInverseScheduler.solver_type",description:`<strong>solver_type</strong> (<code>str</code>, defaults to <code>midpoint</code>) &#x2014;
Solver type for the second-order solver; can be <code>midpoint</code> or <code>heun</code>. The solver type slightly affects the
sample quality, especially for a small number of steps. It is recommended to use <code>midpoint</code> solvers.`,name:"solver_type"},{anchor:"diffusers.DPMSolverMultistepInverseScheduler.lower_order_final",description:`<strong>lower_order_final</strong> (<code>bool</code>, defaults to <code>True</code>) &#x2014;
Whether to use lower-order solvers in the final steps. Only valid for &lt; 15 inference steps. This can
stabilize the sampling of DPMSolver for steps &lt; 15, especially for steps &lt;= 10.`,name:"lower_order_final"},{anchor:"diffusers.DPMSolverMultistepInverseScheduler.euler_at_final",description:`<strong>euler_at_final</strong> (<code>bool</code>, defaults to <code>False</code>) &#x2014;
Whether to use Euler&#x2019;s method in the final step. It is a trade-off between numerical stability and detail
richness. This can stabilize the sampling of the SDE variant of DPMSolver for small number of inference
steps, but sometimes may result in blurring.`,name:"euler_at_final"},{anchor:"diffusers.DPMSolverMultistepInverseScheduler.use_karras_sigmas",description:`<strong>use_karras_sigmas</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>False</code>) &#x2014;
Whether to use Karras sigmas for step sizes in the noise schedule during the sampling process. If <code>True</code>,
the sigmas are determined according to a sequence of noise levels {&#x3C3;i}.`,name:"use_karras_sigmas"},{anchor:"diffusers.DPMSolverMultistepInverseScheduler.use_exponential_sigmas",description:`<strong>use_exponential_sigmas</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>False</code>) &#x2014;
Whether to use exponential sigmas for step sizes in the noise schedule during the sampling process.`,name:"use_exponential_sigmas"},{anchor:"diffusers.DPMSolverMultistepInverseScheduler.use_beta_sigmas",description:`<strong>use_beta_sigmas</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>False</code>) &#x2014;
Whether to use beta sigmas for step sizes in the noise schedule during the sampling process. Refer to <a href="https://huggingface.co/papers/2407.12173" rel="nofollow">Beta
Sampling is All You Need</a> for more information.`,name:"use_beta_sigmas"},{anchor:"diffusers.DPMSolverMultistepInverseScheduler.lambda_min_clipped",description:`<strong>lambda_min_clipped</strong> (<code>float</code>, defaults to <code>-inf</code>) &#x2014;
Clipping threshold for the minimum value of <code>lambda(t)</code> for numerical stability. This is critical for the
cosine (<code>squaredcos_cap_v2</code>) noise schedule.`,name:"lambda_min_clipped"},{anchor:"diffusers.DPMSolverMultistepInverseScheduler.variance_type",description:`<strong>variance_type</strong> (<code>str</code>, <em>optional</em>) &#x2014;
Set to &#x201C;learned&#x201D; or &#x201C;learned_range&#x201D; for diffusion models that predict variance. If set, the model&#x2019;s output
contains the predicted Gaussian variance.`,name:"variance_type"},{anchor:"diffusers.DPMSolverMultistepInverseScheduler.timestep_spacing",description:`<strong>timestep_spacing</strong> (<code>str</code>, defaults to <code>&quot;linspace&quot;</code>) &#x2014;
The way the timesteps should be scaled. Refer to Table 2 of the <a href="https://huggingface.co/papers/2305.08891" rel="nofollow">Common Diffusion Noise Schedules and
Sample Steps are Flawed</a> for more information.`,name:"timestep_spacing"},{anchor:"diffusers.DPMSolverMultistepInverseScheduler.steps_offset",description:`<strong>steps_offset</strong> (<code>int</code>, defaults to 0) &#x2014;
An offset added to the inference steps, as required by some model families.`,name:"steps_offset"}],source:"https://github.com/huggingface/diffusers/blob/vr_10101/src/diffusers/schedulers/scheduling_dpmsolver_multistep_inverse.py#L78"}}),V=new D({props:{name:"convert_model_output",anchor:"diffusers.DPMSolverMultistepInverseScheduler.convert_model_output",parameters:[{name:"model_output",val:": Tensor"},{name:"*args",val:""},{name:"sample",val:": Tensor = None"},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"diffusers.DPMSolverMultistepInverseScheduler.convert_model_output.model_output",description:`<strong>model_output</strong> (<code>torch.Tensor</code>) &#x2014;
The direct output from the learned diffusion model.`,name:"model_output"},{anchor:"diffusers.DPMSolverMultistepInverseScheduler.convert_model_output.sample",description:`<strong>sample</strong> (<code>torch.Tensor</code>) &#x2014;
A current instance of a sample created by the diffusion process.`,name:"sample"}],source:"https://github.com/huggingface/diffusers/blob/vr_10101/src/diffusers/schedulers/scheduling_dpmsolver_multistep_inverse.py#L468",returnDescription:`<script context="module">export const metadata = 'undefined';<\/script>


<p>The converted model output.</p>
`,returnType:`<script context="module">export const metadata = 'undefined';<\/script>


<p><code>torch.Tensor</code></p>
`}}),y=new ut({props:{$$slots:{default:[ft]},$$scope:{ctx:ae}}}),z=new D({props:{name:"dpm_solver_first_order_update",anchor:"diffusers.DPMSolverMultistepInverseScheduler.dpm_solver_first_order_update",parameters:[{name:"model_output",val:": Tensor"},{name:"*args",val:""},{name:"sample",val:": Tensor = None"},{name:"noise",val:": typing.Optional[torch.Tensor] = None"},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"diffusers.DPMSolverMultistepInverseScheduler.dpm_solver_first_order_update.model_output",description:`<strong>model_output</strong> (<code>torch.Tensor</code>) &#x2014;
The direct output from the learned diffusion model.`,name:"model_output"},{anchor:"diffusers.DPMSolverMultistepInverseScheduler.dpm_solver_first_order_update.sample",description:`<strong>sample</strong> (<code>torch.Tensor</code>) &#x2014;
A current instance of a sample created by the diffusion process.`,name:"sample"}],source:"https://github.com/huggingface/diffusers/blob/vr_10101/src/diffusers/schedulers/scheduling_dpmsolver_multistep_inverse.py#L568",returnDescription:`<script context="module">export const metadata = 'undefined';<\/script>


<p>The sample tensor at the previous timestep.</p>
`,returnType:`<script context="module">export const metadata = 'undefined';<\/script>


<p><code>torch.Tensor</code></p>
`}}),W=new D({props:{name:"multistep_dpm_solver_second_order_update",anchor:"diffusers.DPMSolverMultistepInverseScheduler.multistep_dpm_solver_second_order_update",parameters:[{name:"model_output_list",val:": typing.List[torch.Tensor]"},{name:"*args",val:""},{name:"sample",val:": Tensor = None"},{name:"noise",val:": typing.Optional[torch.Tensor] = None"},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"diffusers.DPMSolverMultistepInverseScheduler.multistep_dpm_solver_second_order_update.model_output_list",description:`<strong>model_output_list</strong> (<code>List[torch.Tensor]</code>) &#x2014;
The direct outputs from learned diffusion model at current and latter timesteps.`,name:"model_output_list"},{anchor:"diffusers.DPMSolverMultistepInverseScheduler.multistep_dpm_solver_second_order_update.sample",description:`<strong>sample</strong> (<code>torch.Tensor</code>) &#x2014;
A current instance of a sample created by the diffusion process.`,name:"sample"}],source:"https://github.com/huggingface/diffusers/blob/vr_10101/src/diffusers/schedulers/scheduling_dpmsolver_multistep_inverse.py#L638",returnDescription:`<script context="module">export const metadata = 'undefined';<\/script>


<p>The sample tensor at the previous timestep.</p>
`,returnType:`<script context="module">export const metadata = 'undefined';<\/script>


<p><code>torch.Tensor</code></p>
`}}),j=new D({props:{name:"multistep_dpm_solver_third_order_update",anchor:"diffusers.DPMSolverMultistepInverseScheduler.multistep_dpm_solver_third_order_update",parameters:[{name:"model_output_list",val:": typing.List[torch.Tensor]"},{name:"*args",val:""},{name:"sample",val:": Tensor = None"},{name:"noise",val:": typing.Optional[torch.Tensor] = None"},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"diffusers.DPMSolverMultistepInverseScheduler.multistep_dpm_solver_third_order_update.model_output_list",description:`<strong>model_output_list</strong> (<code>List[torch.Tensor]</code>) &#x2014;
The direct outputs from learned diffusion model at current and latter timesteps.`,name:"model_output_list"},{anchor:"diffusers.DPMSolverMultistepInverseScheduler.multistep_dpm_solver_third_order_update.sample",description:`<strong>sample</strong> (<code>torch.Tensor</code>) &#x2014;
A current instance of a sample created by diffusion process.`,name:"sample"}],source:"https://github.com/huggingface/diffusers/blob/vr_10101/src/diffusers/schedulers/scheduling_dpmsolver_multistep_inverse.py#L762",returnDescription:`<script context="module">export const metadata = 'undefined';<\/script>


<p>The sample tensor at the previous timestep.</p>
`,returnType:`<script context="module">export const metadata = 'undefined';<\/script>


<p><code>torch.Tensor</code></p>
`}}),G=new D({props:{name:"scale_model_input",anchor:"diffusers.DPMSolverMultistepInverseScheduler.scale_model_input",parameters:[{name:"sample",val:": Tensor"},{name:"*args",val:""},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"diffusers.DPMSolverMultistepInverseScheduler.scale_model_input.sample",description:`<strong>sample</strong> (<code>torch.Tensor</code>) &#x2014;
The input sample.`,name:"sample"}],source:"https://github.com/huggingface/diffusers/blob/vr_10101/src/diffusers/schedulers/scheduling_dpmsolver_multistep_inverse.py#L959",returnDescription:`<script context="module">export const metadata = 'undefined';<\/script>


<p>A scaled input sample.</p>
`,returnType:`<script context="module">export const metadata = 'undefined';<\/script>


<p><code>torch.Tensor</code></p>
`}}),U=new D({props:{name:"set_timesteps",anchor:"diffusers.DPMSolverMultistepInverseScheduler.set_timesteps",parameters:[{name:"num_inference_steps",val:": int = None"},{name:"device",val:": typing.Union[str, torch.device] = None"}],parametersDescription:[{anchor:"diffusers.DPMSolverMultistepInverseScheduler.set_timesteps.num_inference_steps",description:`<strong>num_inference_steps</strong> (<code>int</code>) &#x2014;
The number of diffusion steps used when generating samples with a pre-trained model.`,name:"num_inference_steps"},{anchor:"diffusers.DPMSolverMultistepInverseScheduler.set_timesteps.device",description:`<strong>device</strong> (<code>str</code> or <code>torch.device</code>, <em>optional</em>) &#x2014;
The device to which the timesteps should be moved to. If <code>None</code>, the timesteps are not moved.`,name:"device"}],source:"https://github.com/huggingface/diffusers/blob/vr_10101/src/diffusers/schedulers/scheduling_dpmsolver_multistep_inverse.py#L243"}}),R=new D({props:{name:"step",anchor:"diffusers.DPMSolverMultistepInverseScheduler.step",parameters:[{name:"model_output",val:": Tensor"},{name:"timestep",val:": typing.Union[int, torch.Tensor]"},{name:"sample",val:": Tensor"},{name:"generator",val:" = None"},{name:"variance_noise",val:": typing.Optional[torch.Tensor] = None"},{name:"return_dict",val:": bool = True"}],parametersDescription:[{anchor:"diffusers.DPMSolverMultistepInverseScheduler.step.model_output",description:`<strong>model_output</strong> (<code>torch.Tensor</code>) &#x2014;
The direct output from learned diffusion model.`,name:"model_output"},{anchor:"diffusers.DPMSolverMultistepInverseScheduler.step.timestep",description:`<strong>timestep</strong> (<code>int</code>) &#x2014;
The current discrete timestep in the diffusion chain.`,name:"timestep"},{anchor:"diffusers.DPMSolverMultistepInverseScheduler.step.sample",description:`<strong>sample</strong> (<code>torch.Tensor</code>) &#x2014;
A current instance of a sample created by the diffusion process.`,name:"sample"},{anchor:"diffusers.DPMSolverMultistepInverseScheduler.step.generator",description:`<strong>generator</strong> (<code>torch.Generator</code>, <em>optional</em>) &#x2014;
A random number generator.`,name:"generator"},{anchor:"diffusers.DPMSolverMultistepInverseScheduler.step.variance_noise",description:`<strong>variance_noise</strong> (<code>torch.Tensor</code>) &#x2014;
Alternative to generating noise with <code>generator</code> by directly providing the noise for the variance
itself. Useful for methods such as <code>CycleDiffusion</code>.`,name:"variance_noise"},{anchor:"diffusers.DPMSolverMultistepInverseScheduler.step.return_dict",description:`<strong>return_dict</strong> (<code>bool</code>) &#x2014;
Whether or not to return a <a href="/docs/diffusers/pr_10101/en/api/schedulers/multistep_dpm_solver#diffusers.schedulers.scheduling_utils.SchedulerOutput">SchedulerOutput</a> or <code>tuple</code>.`,name:"return_dict"}],source:"https://github.com/huggingface/diffusers/blob/vr_10101/src/diffusers/schedulers/scheduling_dpmsolver_multistep_inverse.py#L876",returnDescription:`<script context="module">export const metadata = 'undefined';<\/script>


<p>If return_dict is <code>True</code>, <a
  href="/docs/diffusers/pr_10101/en/api/schedulers/multistep_dpm_solver#diffusers.schedulers.scheduling_utils.SchedulerOutput"
>SchedulerOutput</a> is returned, otherwise a
tuple is returned where the first element is the sample tensor.</p>
`,returnType:`<script context="module">export const metadata = 'undefined';<\/script>


<p><a
  href="/docs/diffusers/pr_10101/en/api/schedulers/multistep_dpm_solver#diffusers.schedulers.scheduling_utils.SchedulerOutput"
>SchedulerOutput</a> or <code>tuple</code></p>
`}}),B=new Ie({props:{title:"SchedulerOutput",local:"diffusers.schedulers.scheduling_utils.SchedulerOutput",headingTag:"h2"}}),Y=new D({props:{name:"class diffusers.schedulers.scheduling_utils.SchedulerOutput",anchor:"diffusers.schedulers.scheduling_utils.SchedulerOutput",parameters:[{name:"prev_sample",val:": Tensor"}],parametersDescription:[{anchor:"diffusers.schedulers.scheduling_utils.SchedulerOutput.prev_sample",description:`<strong>prev_sample</strong> (<code>torch.Tensor</code> of shape <code>(batch_size, num_channels, height, width)</code> for images) &#x2014;
Computed sample <code>(x_{t-1})</code> of previous timestep. <code>prev_sample</code> should be used as next model input in the
denoising loop.`,name:"prev_sample"}],source:"https://github.com/huggingface/diffusers/blob/vr_10101/src/diffusers/schedulers/scheduling_utils.py#L60"}}),J=new mt({props:{source:"https://github.com/huggingface/diffusers/blob/main/docs/source/en/api/schedulers/multistep_dpm_solver_inverse.md"}}),{c(){p=i("meta"),O=o(),b=i("p"),X=o(),u(E.$$.fragment),ce=o(),N=i("p"),N.innerHTML=Be,pe=o(),q=i("p"),q.innerHTML=Ye,ue=o(),u(k.$$.fragment),me=o(),A=i("p"),A.innerHTML=Je,fe=o(),u(F.$$.fragment),he=o(),l=i("div"),u(H.$$.fragment),we=o(),Z=i("p"),Z.innerHTML=Xe,Ce=o(),K=i("p"),K.innerHTML=Ze,Le=o(),x=i("div"),u(V.$$.fragment),Oe=o(),Q=i("p"),Q.textContent=Ke,Ee=o(),u(y.$$.fragment),Ne=o(),T=i("div"),u(z.$$.fragment),qe=o(),ee=i("p"),ee.textContent=Qe,ke=o(),P=i("div"),u(W.$$.fragment),Ae=o(),te=i("p"),te.textContent=et,Fe=o(),I=i("div"),u(j.$$.fragment),He=o(),se=i("p"),se.textContent=tt,Ve=o(),w=i("div"),u(G.$$.fragment),ze=o(),re=i("p"),re.textContent=st,We=o(),C=i("div"),u(U.$$.fragment),je=o(),oe=i("p"),oe.textContent=rt,Ge=o(),L=i("div"),u(R.$$.fragment),Ue=o(),ne=i("p"),ne.textContent=ot,ve=o(),u(B.$$.fragment),ge=o(),$=i("div"),u(Y.$$.fragment),Re=o(),ie=i("p"),ie.innerHTML=nt,_e=o(),u(J.$$.fragment),be=o(),le=i("p"),this.h()},l(e){const r=pt("svelte-u9bgzb",document.head);p=d(r,"META",{name:!0,content:!0}),r.forEach(s),O=n(e),b=d(e,"P",{}),S(b).forEach(s),X=n(e),m(E.$$.fragment,e),ce=n(e),N=d(e,"P",{"data-svelte-h":!0}),_(N)!=="svelte-9vmlu9"&&(N.innerHTML=Be),pe=n(e),q=d(e,"P",{"data-svelte-h":!0}),_(q)!=="svelte-jb4p1n"&&(q.innerHTML=Ye),ue=n(e),m(k.$$.fragment,e),me=n(e),A=d(e,"P",{"data-svelte-h":!0}),_(A)!=="svelte-1ng0gyl"&&(A.innerHTML=Je),fe=n(e),m(F.$$.fragment,e),he=n(e),l=d(e,"DIV",{class:!0});var a=S(l);m(H.$$.fragment,a),we=n(a),Z=d(a,"P",{"data-svelte-h":!0}),_(Z)!=="svelte-oogjnc"&&(Z.innerHTML=Xe),Ce=n(a),K=d(a,"P",{"data-svelte-h":!0}),_(K)!=="svelte-kgurhv"&&(K.innerHTML=Ze),Le=n(a),x=d(a,"DIV",{class:!0});var de=S(x);m(V.$$.fragment,de),Oe=n(de),Q=d(de,"P",{"data-svelte-h":!0}),_(Q)!=="svelte-1st02i8"&&(Q.textContent=Ke),Ee=n(de),m(y.$$.fragment,de),de.forEach(s),Ne=n(a),T=d(a,"DIV",{class:!0});var Me=S(T);m(z.$$.fragment,Me),qe=n(Me),ee=d(Me,"P",{"data-svelte-h":!0}),_(ee)!=="svelte-4nw43d"&&(ee.textContent=Qe),Me.forEach(s),ke=n(a),P=d(a,"DIV",{class:!0});var xe=S(P);m(W.$$.fragment,xe),Ae=n(xe),te=d(xe,"P",{"data-svelte-h":!0}),_(te)!=="svelte-1d6o6zu"&&(te.textContent=et),xe.forEach(s),Fe=n(a),I=d(a,"DIV",{class:!0});var $e=S(I);m(j.$$.fragment,$e),He=n($e),se=d($e,"P",{"data-svelte-h":!0}),_(se)!=="svelte-17nne8p"&&(se.textContent=tt),$e.forEach(s),Ve=n(a),w=d(a,"DIV",{class:!0});var De=S(w);m(G.$$.fragment,De),ze=n(De),re=d(De,"P",{"data-svelte-h":!0}),_(re)!=="svelte-1rkfgpx"&&(re.textContent=st),De.forEach(s),We=n(a),C=d(a,"DIV",{class:!0});var ye=S(C);m(U.$$.fragment,ye),je=n(ye),oe=d(ye,"P",{"data-svelte-h":!0}),_(oe)!=="svelte-1vzm9q"&&(oe.textContent=rt),ye.forEach(s),Ge=n(a),L=d(a,"DIV",{class:!0});var Te=S(L);m(R.$$.fragment,Te),Ue=n(Te),ne=d(Te,"P",{"data-svelte-h":!0}),_(ne)!=="svelte-7jbjgx"&&(ne.textContent=ot),Te.forEach(s),a.forEach(s),ve=n(e),m(B.$$.fragment,e),ge=n(e),$=d(e,"DIV",{class:!0});var Pe=S($);m(Y.$$.fragment,Pe),Re=n(Pe),ie=d(Pe,"P",{"data-svelte-h":!0}),_(ie)!=="svelte-6ojmkw"&&(ie.innerHTML=nt),Pe.forEach(s),_e=n(e),m(J.$$.fragment,e),be=n(e),le=d(e,"P",{}),S(le).forEach(s),this.h()},h(){M(p,"name","hf:doc:metadata"),M(p,"content",vt),M(x,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),M(T,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),M(P,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),M(I,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),M(w,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),M(C,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),M(L,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),M(l,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),M($,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8")},m(e,r){t(document.head,p),c(e,O,r),c(e,b,r),c(e,X,r),f(E,e,r),c(e,ce,r),c(e,N,r),c(e,pe,r),c(e,q,r),c(e,ue,r),f(k,e,r),c(e,me,r),c(e,A,r),c(e,fe,r),f(F,e,r),c(e,he,r),c(e,l,r),f(H,l,null),t(l,we),t(l,Z),t(l,Ce),t(l,K),t(l,Le),t(l,x),f(V,x,null),t(x,Oe),t(x,Q),t(x,Ee),f(y,x,null),t(l,Ne),t(l,T),f(z,T,null),t(T,qe),t(T,ee),t(l,ke),t(l,P),f(W,P,null),t(P,Ae),t(P,te),t(l,Fe),t(l,I),f(j,I,null),t(I,He),t(I,se),t(l,Ve),t(l,w),f(G,w,null),t(w,ze),t(w,re),t(l,We),t(l,C),f(U,C,null),t(C,je),t(C,oe),t(l,Ge),t(l,L),f(R,L,null),t(L,Ue),t(L,ne),c(e,ve,r),f(B,e,r),c(e,ge,r),c(e,$,r),f(Y,$,null),t($,Re),t($,ie),c(e,_e,r),f(J,e,r),c(e,be,r),c(e,le,r),Se=!0},p(e,[r]){const a={};r&2&&(a.$$scope={dirty:r,ctx:e}),y.$set(a)},i(e){Se||(h(E.$$.fragment,e),h(k.$$.fragment,e),h(F.$$.fragment,e),h(H.$$.fragment,e),h(V.$$.fragment,e),h(y.$$.fragment,e),h(z.$$.fragment,e),h(W.$$.fragment,e),h(j.$$.fragment,e),h(G.$$.fragment,e),h(U.$$.fragment,e),h(R.$$.fragment,e),h(B.$$.fragment,e),h(Y.$$.fragment,e),h(J.$$.fragment,e),Se=!0)},o(e){v(E.$$.fragment,e),v(k.$$.fragment,e),v(F.$$.fragment,e),v(H.$$.fragment,e),v(V.$$.fragment,e),v(y.$$.fragment,e),v(z.$$.fragment,e),v(W.$$.fragment,e),v(j.$$.fragment,e),v(G.$$.fragment,e),v(U.$$.fragment,e),v(R.$$.fragment,e),v(B.$$.fragment,e),v(Y.$$.fragment,e),v(J.$$.fragment,e),Se=!1},d(e){e&&(s(O),s(b),s(X),s(ce),s(N),s(pe),s(q),s(ue),s(me),s(A),s(fe),s(he),s(l),s(ve),s(ge),s($),s(_e),s(be),s(le)),s(p),g(E,e),g(k,e),g(F,e),g(H),g(V),g(y),g(z),g(W),g(j),g(G),g(U),g(R),g(B,e),g(Y),g(J,e)}}}const vt='{"title":"DPMSolverMultistepInverse","local":"dpmsolvermultistepinverse","sections":[{"title":"Tips","local":"tips","sections":[],"depth":2},{"title":"DPMSolverMultistepInverseScheduler","local":"diffusers.DPMSolverMultistepInverseScheduler","sections":[],"depth":2},{"title":"SchedulerOutput","local":"diffusers.schedulers.scheduling_utils.SchedulerOutput","sections":[],"depth":2}],"depth":1}';function gt(ae){return dt(()=>{new URLSearchParams(window.location.search).get("fw")}),[]}class $t extends at{constructor(p){super(),ct(this,p,gt,ht,it,{})}}export{$t as component};