diffusers/v0.22.2/en/_app/immutable/nodes/109.0c1922f6.js

import{s as Tt,o as Pt,n as Mt}from"../chunks/scheduler.182ea377.js";import{S as yt,i as wt,g as i,s,r as m,A as Ct,h as d,f as r,c as o,j as S,u as f,x as c,k as b,y as t,a as p,v as h,d as g,t as _,w as v}from"../chunks/index.abf12888.js";import{T as Ft}from"../chunks/Tip.230e2334.js";import{D as $}from"../chunks/Docstring.93f6f462.js";import{H as Ve}from"../chunks/Heading.16916d63.js";function Lt(ge){let u,I=`The algorithm and model type are decoupled. You can use either DPMSolver or DPMSolver++ for both noise
prediction and data prediction models.`;return{c(){u=i("p"),u.textContent=I},l(x){u=d(x,"P",{"data-svelte-h":!0}),c(u)!=="svelte-95n5s"&&(u.textContent=I)},m(x,te){p(x,u,te)},p:Mt,d(x){x&&r(u)}}}function Ot(ge){let u,I,x,te,E,_e,k,dt='<code>DPMSolverSinglestepScheduler</code> is a single step scheduler from <a href="https://huggingface.co/papers/2206.00927" rel="nofollow">DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps</a> and <a href="https://huggingface.co/papers/2211.01095" rel="nofollow">DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models</a> by Cheng Lu, Yuhao Zhou, Fan Bao, Jianfei Chen, Chongxuan Li, and Jun Zhu.',ve,q,lt=`DPMSolver (and the improved version DPMSolver++) is a fast dedicated high-order solver for diffusion ODEs with convergence order guarantee. Empirically, DPMSolver sampling with only 20 steps can generate high-quality
samples, and it can generate quite good samples even in 10 steps.`,Se,V,at='The original implementation can be found at <a href="https://github.com/LuChengTHU/dpm-solver" rel="nofollow">LuChengTHU/dpm-solver</a>.',be,A,xe,N,pt="It is recommended to set <code>solver_order</code> to 2 for guide sampling, and <code>solver_order=3</code> for unconditional sampling.",$e,z,ct=`Dynamic thresholding from Imagen (<a href="https://huggingface.co/papers/2205.11487" rel="nofollow">https://huggingface.co/papers/2205.11487</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 dynamic
thresholding. This thresholding method is unsuitable for latent-space diffusion models such as
Stable Diffusion.`,De,j,Te,l,U,Ae,re,ut="<code>DPMSolverSinglestepScheduler</code> is a fast dedicated high-order solver for diffusion ODEs.",Ne,se,mt=`This model inherits from <a href="/docs/diffusers/v0.22.2/en/api/schedulers/overview#diffusers.SchedulerMixin">SchedulerMixin</a> and <a href="/docs/diffusers/v0.22.2/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.`,ze,D,W,je,oe,ft=`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.`,Ue,P,We,M,B,Be,ne,ht="One step for the first-order DPMSolver (equivalent to DDIM).",Ge,y,G,Je,ie,gt="Computes the solver order at each time step.",Ye,w,J,Ze,de,_t=`Ensures interchangeability with schedulers that need to scale the denoising model input depending on the
current timestep.`,Ke,C,Y,Re,le,vt="Sets the discrete timesteps used for the diffusion chain (to be run before inference).",Qe,F,Z,Xe,ae,St=`One step for the second-order singlestep DPMSolver that computes the solution at time <code>prev_timestep</code> from the
time <code>timestep_list[-2]</code>.`,et,L,K,tt,pe,bt=`One step for the third-order singlestep DPMSolver that computes the solution at time <code>prev_timestep</code> from the
time <code>timestep_list[-3]</code>.`,rt,O,R,st,ce,xt="One step for the singlestep DPMSolver.",ot,H,Q,nt,ue,$t=`Predict the sample from the previous timestep by reversing the SDE. This function propagates the sample with
the singlestep DPMSolver.`,Pe,X,Me,T,ee,it,me,Dt="Base class for the output of a scheduler’s <code>step</code> function.",ye,he,we;return E=new Ve({props:{title:"DPMSolverSinglestepScheduler",local:"dpmsolversinglestepscheduler",headingTag:"h1"}}),A=new Ve({props:{title:"Tips",local:"tips",headingTag:"h2"}}),j=new Ve({props:{title:"DPMSolverSinglestepScheduler",local:"diffusers.DPMSolverSinglestepScheduler",headingTag:"h2"}}),U=new $({props:{name:"class diffusers.DPMSolverSinglestepScheduler",anchor:"diffusers.DPMSolverSinglestepScheduler",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.Optional[numpy.ndarray] = 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:"use_karras_sigmas",val:": typing.Optional[bool] = False"},{name:"lambda_min_clipped",val:": float = -inf"},{name:"variance_type",val:": typing.Optional[str] = None"}],parametersDescription:[{anchor:"diffusers.DPMSolverSinglestepScheduler.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.DPMSolverSinglestepScheduler.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.DPMSolverSinglestepScheduler.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.DPMSolverSinglestepScheduler.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.DPMSolverSinglestepScheduler.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.DPMSolverSinglestepScheduler.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.DPMSolverSinglestepScheduler.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.DPMSolverSinglestepScheduler.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.DPMSolverSinglestepScheduler.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.DPMSolverSinglestepScheduler.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.DPMSolverSinglestepScheduler.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.DPMSolverSinglestepScheduler.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.DPMSolverSinglestepScheduler.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.DPMSolverSinglestepScheduler.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.DPMSolverSinglestepScheduler.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.DPMSolverSinglestepScheduler.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"}],source:"https://github.com/huggingface/diffusers/blob/v0.22.2/src/diffusers/schedulers/scheduling_dpmsolver_singlestep.py#L76"}}),W=new $({props:{name:"convert_model_output",anchor:"diffusers.DPMSolverSinglestepScheduler.convert_model_output",parameters:[{name:"model_output",val:": FloatTensor"},{name:"*args",val:""},{name:"sample",val:": FloatTensor = None"},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"diffusers.DPMSolverSinglestepScheduler.convert_model_output.model_output",description:`<strong>model_output</strong> (<code>torch.FloatTensor</code>) &#x2014;
The direct output from the learned diffusion model.`,name:"model_output"},{anchor:"diffusers.DPMSolverSinglestepScheduler.convert_model_output.sample",description:`<strong>sample</strong> (<code>torch.FloatTensor</code>) &#x2014;
A current instance of a sample created by the diffusion process.`,name:"sample"}],source:"https://github.com/huggingface/diffusers/blob/v0.22.2/src/diffusers/schedulers/scheduling_dpmsolver_singlestep.py#L372",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.FloatTensor</code></p>
`}}),P=new Ft({props:{$$slots:{default:[Lt]},$$scope:{ctx:ge}}}),B=new $({props:{name:"dpm_solver_first_order_update",anchor:"diffusers.DPMSolverSinglestepScheduler.dpm_solver_first_order_update",parameters:[{name:"model_output",val:": FloatTensor"},{name:"*args",val:""},{name:"sample",val:": FloatTensor = None"},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"diffusers.DPMSolverSinglestepScheduler.dpm_solver_first_order_update.model_output",description:`<strong>model_output</strong> (<code>torch.FloatTensor</code>) &#x2014;
The direct output from the learned diffusion model.`,name:"model_output"},{anchor:"diffusers.DPMSolverSinglestepScheduler.dpm_solver_first_order_update.timestep",description:`<strong>timestep</strong> (<code>int</code>) &#x2014;
The current discrete timestep in the diffusion chain.`,name:"timestep"},{anchor:"diffusers.DPMSolverSinglestepScheduler.dpm_solver_first_order_update.prev_timestep",description:`<strong>prev_timestep</strong> (<code>int</code>) &#x2014;
The previous discrete timestep in the diffusion chain.`,name:"prev_timestep"},{anchor:"diffusers.DPMSolverSinglestepScheduler.dpm_solver_first_order_update.sample",description:`<strong>sample</strong> (<code>torch.FloatTensor</code>) &#x2014;
A current instance of a sample created by the diffusion process.`,name:"sample"}],source:"https://github.com/huggingface/diffusers/blob/v0.22.2/src/diffusers/schedulers/scheduling_dpmsolver_singlestep.py#L461",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.FloatTensor</code></p>
`}}),G=new $({props:{name:"get_order_list",anchor:"diffusers.DPMSolverSinglestepScheduler.get_order_list",parameters:[{name:"num_inference_steps",val:": int"}],parametersDescription:[{anchor:"diffusers.DPMSolverSinglestepScheduler.get_order_list.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"}],source:"https://github.com/huggingface/diffusers/blob/v0.22.2/src/diffusers/schedulers/scheduling_dpmsolver_singlestep.py#L202"}}),J=new $({props:{name:"scale_model_input",anchor:"diffusers.DPMSolverSinglestepScheduler.scale_model_input",parameters:[{name:"sample",val:": FloatTensor"},{name:"*args",val:""},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"diffusers.DPMSolverSinglestepScheduler.scale_model_input.sample",description:`<strong>sample</strong> (<code>torch.FloatTensor</code>) &#x2014;
The input sample.`,name:"sample"}],source:"https://github.com/huggingface/diffusers/blob/v0.22.2/src/diffusers/schedulers/scheduling_dpmsolver_singlestep.py#L857",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.FloatTensor</code></p>
`}}),Y=new $({props:{name:"set_timesteps",anchor:"diffusers.DPMSolverSinglestepScheduler.set_timesteps",parameters:[{name:"num_inference_steps",val:": int"},{name:"device",val:": typing.Union[str, torch.device] = None"}],parametersDescription:[{anchor:"diffusers.DPMSolverSinglestepScheduler.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.DPMSolverSinglestepScheduler.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/v0.22.2/src/diffusers/schedulers/scheduling_dpmsolver_singlestep.py#L243"}}),Z=new $({props:{name:"singlestep_dpm_solver_second_order_update",anchor:"diffusers.DPMSolverSinglestepScheduler.singlestep_dpm_solver_second_order_update",parameters:[{name:"model_output_list",val:": typing.List[torch.FloatTensor]"},{name:"*args",val:""},{name:"sample",val:": FloatTensor = None"},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"diffusers.DPMSolverSinglestepScheduler.singlestep_dpm_solver_second_order_update.model_output_list",description:`<strong>model_output_list</strong> (<code>List[torch.FloatTensor]</code>) &#x2014;
The direct outputs from learned diffusion model at current and latter timesteps.`,name:"model_output_list"},{anchor:"diffusers.DPMSolverSinglestepScheduler.singlestep_dpm_solver_second_order_update.timestep",description:`<strong>timestep</strong> (<code>int</code>) &#x2014;
The current and latter discrete timestep in the diffusion chain.`,name:"timestep"},{anchor:"diffusers.DPMSolverSinglestepScheduler.singlestep_dpm_solver_second_order_update.prev_timestep",description:`<strong>prev_timestep</strong> (<code>int</code>) &#x2014;
The previous discrete timestep in the diffusion chain.`,name:"prev_timestep"},{anchor:"diffusers.DPMSolverSinglestepScheduler.singlestep_dpm_solver_second_order_update.sample",description:`<strong>sample</strong> (<code>torch.FloatTensor</code>) &#x2014;
A current instance of a sample created by the diffusion process.`,name:"sample"}],source:"https://github.com/huggingface/diffusers/blob/v0.22.2/src/diffusers/schedulers/scheduling_dpmsolver_singlestep.py#L517",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.FloatTensor</code></p>
`}}),K=new $({props:{name:"singlestep_dpm_solver_third_order_update",anchor:"diffusers.DPMSolverSinglestepScheduler.singlestep_dpm_solver_third_order_update",parameters:[{name:"model_output_list",val:": typing.List[torch.FloatTensor]"},{name:"*args",val:""},{name:"sample",val:": FloatTensor = None"},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"diffusers.DPMSolverSinglestepScheduler.singlestep_dpm_solver_third_order_update.model_output_list",description:`<strong>model_output_list</strong> (<code>List[torch.FloatTensor]</code>) &#x2014;
The direct outputs from learned diffusion model at current and latter timesteps.`,name:"model_output_list"},{anchor:"diffusers.DPMSolverSinglestepScheduler.singlestep_dpm_solver_third_order_update.timestep",description:`<strong>timestep</strong> (<code>int</code>) &#x2014;
The current and latter discrete timestep in the diffusion chain.`,name:"timestep"},{anchor:"diffusers.DPMSolverSinglestepScheduler.singlestep_dpm_solver_third_order_update.prev_timestep",description:`<strong>prev_timestep</strong> (<code>int</code>) &#x2014;
The previous discrete timestep in the diffusion chain.`,name:"prev_timestep"},{anchor:"diffusers.DPMSolverSinglestepScheduler.singlestep_dpm_solver_third_order_update.sample",description:`<strong>sample</strong> (<code>torch.FloatTensor</code>) &#x2014;
A current instance of a sample created by diffusion process.`,name:"sample"}],source:"https://github.com/huggingface/diffusers/blob/v0.22.2/src/diffusers/schedulers/scheduling_dpmsolver_singlestep.py#L611",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.FloatTensor</code></p>
`}}),R=new $({props:{name:"singlestep_dpm_solver_update",anchor:"diffusers.DPMSolverSinglestepScheduler.singlestep_dpm_solver_update",parameters:[{name:"model_output_list",val:": typing.List[torch.FloatTensor]"},{name:"*args",val:""},{name:"sample",val:": FloatTensor = None"},{name:"order",val:": int = None"},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"diffusers.DPMSolverSinglestepScheduler.singlestep_dpm_solver_update.model_output_list",description:`<strong>model_output_list</strong> (<code>List[torch.FloatTensor]</code>) &#x2014;
The direct outputs from learned diffusion model at current and latter timesteps.`,name:"model_output_list"},{anchor:"diffusers.DPMSolverSinglestepScheduler.singlestep_dpm_solver_update.timestep",description:`<strong>timestep</strong> (<code>int</code>) &#x2014;
The current and latter discrete timestep in the diffusion chain.`,name:"timestep"},{anchor:"diffusers.DPMSolverSinglestepScheduler.singlestep_dpm_solver_update.prev_timestep",description:`<strong>prev_timestep</strong> (<code>int</code>) &#x2014;
The previous discrete timestep in the diffusion chain.`,name:"prev_timestep"},{anchor:"diffusers.DPMSolverSinglestepScheduler.singlestep_dpm_solver_update.sample",description:`<strong>sample</strong> (<code>torch.FloatTensor</code>) &#x2014;
A current instance of a sample created by diffusion process.`,name:"sample"},{anchor:"diffusers.DPMSolverSinglestepScheduler.singlestep_dpm_solver_update.order",description:`<strong>order</strong> (<code>int</code>) &#x2014;
The solver order at this step.`,name:"order"}],source:"https://github.com/huggingface/diffusers/blob/v0.22.2/src/diffusers/schedulers/scheduling_dpmsolver_singlestep.py#L715",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.FloatTensor</code></p>
`}}),Q=new $({props:{name:"step",anchor:"diffusers.DPMSolverSinglestepScheduler.step",parameters:[{name:"model_output",val:": FloatTensor"},{name:"timestep",val:": int"},{name:"sample",val:": FloatTensor"},{name:"return_dict",val:": bool = True"}],parametersDescription:[{anchor:"diffusers.DPMSolverSinglestepScheduler.step.model_output",description:`<strong>model_output</strong> (<code>torch.FloatTensor</code>) &#x2014;
The direct output from learned diffusion model.`,name:"model_output"},{anchor:"diffusers.DPMSolverSinglestepScheduler.step.timestep",description:`<strong>timestep</strong> (<code>int</code>) &#x2014;
The current discrete timestep in the diffusion chain.`,name:"timestep"},{anchor:"diffusers.DPMSolverSinglestepScheduler.step.sample",description:`<strong>sample</strong> (<code>torch.FloatTensor</code>) &#x2014;
A current instance of a sample created by the diffusion process.`,name:"sample"},{anchor:"diffusers.DPMSolverSinglestepScheduler.step.return_dict",description:`<strong>return_dict</strong> (<code>bool</code>) &#x2014;
Whether or not to return a <a href="/docs/diffusers/v0.22.2/en/api/schedulers/dpm_discrete#diffusers.schedulers.scheduling_utils.SchedulerOutput">SchedulerOutput</a> or <code>tuple</code>.`,name:"return_dict"}],source:"https://github.com/huggingface/diffusers/blob/v0.22.2/src/diffusers/schedulers/scheduling_dpmsolver_singlestep.py#L796",returnDescription:`<script context="module">export const metadata = 'undefined';<\/script>


<p>If return_dict is <code>True</code>, <a
  href="/docs/diffusers/v0.22.2/en/api/schedulers/dpm_discrete#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/v0.22.2/en/api/schedulers/dpm_discrete#diffusers.schedulers.scheduling_utils.SchedulerOutput"
>SchedulerOutput</a> or <code>tuple</code></p>
`}}),X=new Ve({props:{title:"SchedulerOutput",local:"diffusers.schedulers.scheduling_utils.SchedulerOutput",headingTag:"h2"}}),ee=new $({props:{name:"class diffusers.schedulers.scheduling_utils.SchedulerOutput",anchor:"diffusers.schedulers.scheduling_utils.SchedulerOutput",parameters:[{name:"prev_sample",val:": FloatTensor"}],parametersDescription:[{anchor:"diffusers.schedulers.scheduling_utils.SchedulerOutput.prev_sample",description:`<strong>prev_sample</strong> (<code>torch.FloatTensor</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/v0.22.2/src/diffusers/schedulers/scheduling_utils.py#L50"}}),{c(){u=i("meta"),I=s(),x=i("p"),te=s(),m(E.$$.fragment),_e=s(),k=i("p"),k.innerHTML=dt,ve=s(),q=i("p"),q.textContent=lt,Se=s(),V=i("p"),V.innerHTML=at,be=s(),m(A.$$.fragment),xe=s(),N=i("p"),N.innerHTML=pt,$e=s(),z=i("p"),z.innerHTML=ct,De=s(),m(j.$$.fragment),Te=s(),l=i("div"),m(U.$$.fragment),Ae=s(),re=i("p"),re.innerHTML=ut,Ne=s(),se=i("p"),se.innerHTML=mt,ze=s(),D=i("div"),m(W.$$.fragment),je=s(),oe=i("p"),oe.textContent=ft,Ue=s(),m(P.$$.fragment),We=s(),M=i("div"),m(B.$$.fragment),Be=s(),ne=i("p"),ne.textContent=ht,Ge=s(),y=i("div"),m(G.$$.fragment),Je=s(),ie=i("p"),ie.textContent=gt,Ye=s(),w=i("div"),m(J.$$.fragment),Ze=s(),de=i("p"),de.textContent=_t,Ke=s(),C=i("div"),m(Y.$$.fragment),Re=s(),le=i("p"),le.textContent=vt,Qe=s(),F=i("div"),m(Z.$$.fragment),Xe=s(),ae=i("p"),ae.innerHTML=St,et=s(),L=i("div"),m(K.$$.fragment),tt=s(),pe=i("p"),pe.innerHTML=bt,rt=s(),O=i("div"),m(R.$$.fragment),st=s(),ce=i("p"),ce.textContent=xt,ot=s(),H=i("div"),m(Q.$$.fragment),nt=s(),ue=i("p"),ue.textContent=$t,Pe=s(),m(X.$$.fragment),Me=s(),T=i("div"),m(ee.$$.fragment),it=s(),me=i("p"),me.innerHTML=Dt,ye=s(),he=i("p"),this.h()},l(e){const n=Ct("svelte-u9bgzb",document.head);u=d(n,"META",{name:!0,content:!0}),n.forEach(r),I=o(e),x=d(e,"P",{}),S(x).forEach(r),te=o(e),f(E.$$.fragment,e),_e=o(e),k=d(e,"P",{"data-svelte-h":!0}),c(k)!=="svelte-zw7rt6"&&(k.innerHTML=dt),ve=o(e),q=d(e,"P",{"data-svelte-h":!0}),c(q)!=="svelte-l6rv24"&&(q.textContent=lt),Se=o(e),V=d(e,"P",{"data-svelte-h":!0}),c(V)!=="svelte-1mk5p6f"&&(V.innerHTML=at),be=o(e),f(A.$$.fragment,e),xe=o(e),N=d(e,"P",{"data-svelte-h":!0}),c(N)!=="svelte-pt2glg"&&(N.innerHTML=pt),$e=o(e),z=d(e,"P",{"data-svelte-h":!0}),c(z)!=="svelte-171mkif"&&(z.innerHTML=ct),De=o(e),f(j.$$.fragment,e),Te=o(e),l=d(e,"DIV",{class:!0});var a=S(l);f(U.$$.fragment,a),Ae=o(a),re=d(a,"P",{"data-svelte-h":!0}),c(re)!=="svelte-1g2jbmp"&&(re.innerHTML=ut),Ne=o(a),se=d(a,"P",{"data-svelte-h":!0}),c(se)!=="svelte-1in9wop"&&(se.innerHTML=mt),ze=o(a),D=d(a,"DIV",{class:!0});var fe=S(D);f(W.$$.fragment,fe),je=o(fe),oe=d(fe,"P",{"data-svelte-h":!0}),c(oe)!=="svelte-1st02i8"&&(oe.textContent=ft),Ue=o(fe),f(P.$$.fragment,fe),fe.forEach(r),We=o(a),M=d(a,"DIV",{class:!0});var Ce=S(M);f(B.$$.fragment,Ce),Be=o(Ce),ne=d(Ce,"P",{"data-svelte-h":!0}),c(ne)!=="svelte-4nw43d"&&(ne.textContent=ht),Ce.forEach(r),Ge=o(a),y=d(a,"DIV",{class:!0});var Fe=S(y);f(G.$$.fragment,Fe),Je=o(Fe),ie=d(Fe,"P",{"data-svelte-h":!0}),c(ie)!=="svelte-13tpuy9"&&(ie.textContent=gt),Fe.forEach(r),Ye=o(a),w=d(a,"DIV",{class:!0});var Le=S(w);f(J.$$.fragment,Le),Ze=o(Le),de=d(Le,"P",{"data-svelte-h":!0}),c(de)!=="svelte-1rkfgpx"&&(de.textContent=_t),Le.forEach(r),Ke=o(a),C=d(a,"DIV",{class:!0});var Oe=S(C);f(Y.$$.fragment,Oe),Re=o(Oe),le=d(Oe,"P",{"data-svelte-h":!0}),c(le)!=="svelte-1vzm9q"&&(le.textContent=vt),Oe.forEach(r),Qe=o(a),F=d(a,"DIV",{class:!0});var He=S(F);f(Z.$$.fragment,He),Xe=o(He),ae=d(He,"P",{"data-svelte-h":!0}),c(ae)!=="svelte-1rmndna"&&(ae.innerHTML=St),He.forEach(r),et=o(a),L=d(a,"DIV",{class:!0});var Ie=S(L);f(K.$$.fragment,Ie),tt=o(Ie),pe=d(Ie,"P",{"data-svelte-h":!0}),c(pe)!=="svelte-17kajtk"&&(pe.innerHTML=bt),Ie.forEach(r),rt=o(a),O=d(a,"DIV",{class:!0});var Ee=S(O);f(R.$$.fragment,Ee),st=o(Ee),ce=d(Ee,"P",{"data-svelte-h":!0}),c(ce)!=="svelte-zgpbva"&&(ce.textContent=xt),Ee.forEach(r),ot=o(a),H=d(a,"DIV",{class:!0});var ke=S(H);f(Q.$$.fragment,ke),nt=o(ke),ue=d(ke,"P",{"data-svelte-h":!0}),c(ue)!=="svelte-7earhm"&&(ue.textContent=$t),ke.forEach(r),a.forEach(r),Pe=o(e),f(X.$$.fragment,e),Me=o(e),T=d(e,"DIV",{class:!0});var qe=S(T);f(ee.$$.fragment,qe),it=o(qe),me=d(qe,"P",{"data-svelte-h":!0}),c(me)!=="svelte-6ojmkw"&&(me.innerHTML=Dt),qe.forEach(r),ye=o(e),he=d(e,"P",{}),S(he).forEach(r),this.h()},h(){b(u,"name","hf:doc:metadata"),b(u,"content",Ht),b(D,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),b(M,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),b(y,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),b(w,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),b(C,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),b(F,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),b(L,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),b(O,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),b(H,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),b(l,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),b(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(e,n){t(document.head,u),p(e,I,n),p(e,x,n),p(e,te,n),h(E,e,n),p(e,_e,n),p(e,k,n),p(e,ve,n),p(e,q,n),p(e,Se,n),p(e,V,n),p(e,be,n),h(A,e,n),p(e,xe,n),p(e,N,n),p(e,$e,n),p(e,z,n),p(e,De,n),h(j,e,n),p(e,Te,n),p(e,l,n),h(U,l,null),t(l,Ae),t(l,re),t(l,Ne),t(l,se),t(l,ze),t(l,D),h(W,D,null),t(D,je),t(D,oe),t(D,Ue),h(P,D,null),t(l,We),t(l,M),h(B,M,null),t(M,Be),t(M,ne),t(l,Ge),t(l,y),h(G,y,null),t(y,Je),t(y,ie),t(l,Ye),t(l,w),h(J,w,null),t(w,Ze),t(w,de),t(l,Ke),t(l,C),h(Y,C,null),t(C,Re),t(C,le),t(l,Qe),t(l,F),h(Z,F,null),t(F,Xe),t(F,ae),t(l,et),t(l,L),h(K,L,null),t(L,tt),t(L,pe),t(l,rt),t(l,O),h(R,O,null),t(O,st),t(O,ce),t(l,ot),t(l,H),h(Q,H,null),t(H,nt),t(H,ue),p(e,Pe,n),h(X,e,n),p(e,Me,n),p(e,T,n),h(ee,T,null),t(T,it),t(T,me),p(e,ye,n),p(e,he,n),we=!0},p(e,[n]){const a={};n&2&&(a.$$scope={dirty:n,ctx:e}),P.$set(a)},i(e){we||(g(E.$$.fragment,e),g(A.$$.fragment,e),g(j.$$.fragment,e),g(U.$$.fragment,e),g(W.$$.fragment,e),g(P.$$.fragment,e),g(B.$$.fragment,e),g(G.$$.fragment,e),g(J.$$.fragment,e),g(Y.$$.fragment,e),g(Z.$$.fragment,e),g(K.$$.fragment,e),g(R.$$.fragment,e),g(Q.$$.fragment,e),g(X.$$.fragment,e),g(ee.$$.fragment,e),we=!0)},o(e){_(E.$$.fragment,e),_(A.$$.fragment,e),_(j.$$.fragment,e),_(U.$$.fragment,e),_(W.$$.fragment,e),_(P.$$.fragment,e),_(B.$$.fragment,e),_(G.$$.fragment,e),_(J.$$.fragment,e),_(Y.$$.fragment,e),_(Z.$$.fragment,e),_(K.$$.fragment,e),_(R.$$.fragment,e),_(Q.$$.fragment,e),_(X.$$.fragment,e),_(ee.$$.fragment,e),we=!1},d(e){e&&(r(I),r(x),r(te),r(_e),r(k),r(ve),r(q),r(Se),r(V),r(be),r(xe),r(N),r($e),r(z),r(De),r(Te),r(l),r(Pe),r(Me),r(T),r(ye),r(he)),r(u),v(E,e),v(A,e),v(j,e),v(U),v(W),v(P),v(B),v(G),v(J),v(Y),v(Z),v(K),v(R),v(Q),v(X,e),v(ee)}}}const Ht='{"title":"DPMSolverSinglestepScheduler","local":"dpmsolversinglestepscheduler","sections":[{"title":"Tips","local":"tips","sections":[],"depth":2},{"title":"DPMSolverSinglestepScheduler","local":"diffusers.DPMSolverSinglestepScheduler","sections":[],"depth":2},{"title":"SchedulerOutput","local":"diffusers.schedulers.scheduling_utils.SchedulerOutput","sections":[],"depth":2}],"depth":1}';function It(ge){return Pt(()=>{new URLSearchParams(window.location.search).get("fw")}),[]}class Nt extends yt{constructor(u){super(),wt(this,u,It,Ot,Tt,{})}}export{Nt as component};