diffusers/pr_14252/en/_app/immutable/nodes/256.Cd4ypCKB.js

import"../chunks/DsnmJJEf.js";import{i as R,h as Z,C as K,H as n,D as o,E as j,s as Q}from"../chunks/BtE7mKSK.js";import{p as X,o as $,s as e,f as ee,a as O,b as oe,c as t,d as L,n as s,r}from"../chunks/jDjavuwI.js";const te='{"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}';var se=L('<meta name="hf:doc:metadata"/>'),re=L(`<p></p> <!> <!> <p><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.</p> <p>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.</p> <p>The original implementation can be found at <a href="https://github.com/LuChengTHU/dpm-solver" rel="nofollow">LuChengTHU/dpm-solver</a>.</p> <!> <p>It is recommended to set <code>solver_order</code> to 2 for guide sampling, and <code>solver_order=3</code> for unconditional sampling.</p> <p>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="dpmsolver++"</code> and <code>thresholding=True</code> to use dynamic
thresholding. This thresholding method is unsuitable for latent-space diffusion models such as
Stable Diffusion.</p> <!> <div class="docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"><!> <p><code>DPMSolverSinglestepScheduler</code> is a fast dedicated high-order solver for diffusion ODEs.</p> <p>This model inherits from <a href="/docs/diffusers/pr_14252/en/api/schedulers/overview#diffusers.SchedulerMixin">SchedulerMixin</a> and <a href="/docs/diffusers/pr_14252/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.</p> <div class="docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"><!> <p>Add noise to the original samples according to the noise schedule at the specified timesteps.</p></div> <div class="docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"><!> <p>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.</p> <blockquote class="tip"><p>> The algorithm and model type are decoupled. You can use either DPMSolver or DPMSolver++ for both
noise > prediction and data prediction models.</p></blockquote></div> <div class="docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"><!> <p>One step for the first-order DPMSolver (equivalent to DDIM).</p></div> <div class="docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"><!> <p>Computes the solver order at each time step.</p></div> <div class="docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"><!> <p>Find the index for a given timestep in the schedule.</p></div> <div class="docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"><!> <p>Ensures interchangeability with schedulers that need to scale the denoising model input depending on the
current timestep.</p></div> <div class="docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"><!> <p>Sets the begin index for the scheduler. This function should be run from pipeline before the inference.</p></div> <div class="docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"><!> <p>Sets the discrete timesteps used for the diffusion chain (to be run before inference).</p></div> <div class="docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"><!> <p>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>.</p></div> <div class="docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"><!> <p>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>.</p></div> <div class="docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"><!> <p>One step for the singlestep DPMSolver.</p></div> <div class="docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"><!> <p>Predict the sample from the previous timestep by reversing the SDE. This function propagates the sample with
the singlestep DPMSolver.</p></div></div> <!> <div class="docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"><!> <p>Base class for the output of a scheduler’s <code>step</code> function.</p></div> <!> <p></p>`,1);function ae(N,C){X(C,!1),$(()=>{new URLSearchParams(window.location.search).get("fw")}),R();var S=re();Z("1u6q6v5",q=>{var w=se();Q(w,"content",te),O(q,w)});var b=e(ee(S),2);K(b,{containerStyle:"float: right; margin-left: 10px; display: inline-flex; position: relative; z-index: 10;"});var x=e(b,2);n(x,{title:"DPMSolverSinglestepScheduler",local:"dpmsolversinglestepscheduler",headingTag:"h1"});var y=e(x,8);n(y,{title:"Tips",local:"tips",headingTag:"h2"});var D=e(y,6);n(D,{title:"DPMSolverSinglestepScheduler",local:"diffusers.DPMSolverSinglestepScheduler",headingTag:"h2"});var i=e(D,2),T=t(i);o(T,{name:"class diffusers.DPMSolverSinglestepScheduler",anchor:"diffusers.DPMSolverSinglestepScheduler",source:"https://github.com/huggingface/diffusers/blob/vr_14252/src/diffusers/schedulers/scheduling_dpmsolver_singlestep.py#L88",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:": typing.Literal['linear', 'scaled_linear', 'squaredcos_cap_v2'] = 'linear'"},{name:"trained_betas",val:": numpy.ndarray | list[float] | None = None"},{name:"solver_order",val:": int = 2"},{name:"prediction_type",val:": typing.Literal['epsilon', 'sample', 'v_prediction', 'flow_prediction'] = '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:": typing.Literal['dpmsolver', 'dpmsolver++', 'sde-dpmsolver++'] = 'dpmsolver++'"},{name:"solver_type",val:": typing.Literal['midpoint', 'heun'] = 'midpoint'"},{name:"lower_order_final",val:": bool = False"},{name:"use_karras_sigmas",val:": bool = False"},{name:"use_exponential_sigmas",val:": bool = False"},{name:"use_beta_sigmas",val:": bool = False"},{name:"use_flow_sigmas",val:": bool = False"},{name:"flow_shift",val:": float = 1.0"},{name:"final_sigmas_type",val:": typing.Literal['zero', 'sigma_min'] = 'zero'"},{name:"lambda_min_clipped",val:": float = -inf"},{name:"variance_type",val:": typing.Optional[typing.Literal['learned', 'learned_range']] = None"},{name:"use_dynamic_shifting",val:": bool = False"},{name:"time_shift_type",val:": typing.Literal['exponential'] = 'exponential'"}],parametersDescription:[{anchor:"diffusers.DPMSolverSinglestepScheduler.num_train_timesteps",description:`<strong>num_train_timesteps</strong> (<code>int</code>, defaults to <code>1000</code>) &#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 <code>0.0001</code>) &#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 <code>0.02</code>) &#x2014;
The final <code>beta</code> value.`,name:"beta_end"},{anchor:"diffusers.DPMSolverSinglestepScheduler.beta_schedule",description:`<strong>beta_schedule</strong> (<code>&quot;linear&quot;</code>, <code>&quot;scaled_linear&quot;</code>, or <code>&quot;squaredcos_cap_v2&quot;</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> or <code>list[float]</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 <code>2</code>) &#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>&quot;epsilon&quot;</code>, <code>&quot;sample&quot;</code>, <code>&quot;v_prediction&quot;</code>, or <code>&quot;flow_prediction&quot;</code>, defaults to <code>&quot;epsilon&quot;</code>) &#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>), </code>v_prediction<code>(see section 2.4 of [Imagen Video](https://huggingface.co/papers/2210.02303) paper), or</code>flow_prediction\`.`,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 <code>0.995</code>) &#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 <code>1.0</code>) &#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>&quot;dpmsolver&quot;</code>, <code>&quot;dpmsolver++&quot;</code>, or <code>&quot;sde-dpmsolver++&quot;</code>, defaults to <code>&quot;dpmsolver++&quot;</code>) &#x2014;
Algorithm type for the solver; can be <code>dpmsolver</code>, <code>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>&quot;midpoint&quot;</code> or <code>&quot;heun&quot;</code>, defaults to <code>&quot;midpoint&quot;</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>False</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.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.DPMSolverSinglestepScheduler.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.DPMSolverSinglestepScheduler.use_flow_sigmas",description:`<strong>use_flow_sigmas</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>False</code>) &#x2014;
Whether to use flow sigmas for step sizes in the noise schedule during the sampling process.`,name:"use_flow_sigmas"},{anchor:"diffusers.DPMSolverSinglestepScheduler.flow_shift",description:`<strong>flow_shift</strong> (<code>float</code>, <em>optional</em>, defaults to <code>1.0</code>) &#x2014;
The flow shift parameter for flow-based models.`,name:"flow_shift"},{anchor:"diffusers.DPMSolverSinglestepScheduler.final_sigmas_type",description:`<strong>final_sigmas_type</strong> (<code>&quot;zero&quot;</code> or <code>&quot;sigma_min&quot;</code>, <em>optional</em>, defaults to <code>&quot;zero&quot;</code>) &#x2014;
The final <code>sigma</code> value for the noise schedule during the sampling process. If <code>&quot;sigma_min&quot;</code>, the final
sigma is the same as the last sigma in the training schedule. If <code>&quot;zero&quot;</code>, the final sigma is set to 0.`,name:"final_sigmas_type"},{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>&quot;learned&quot;</code> or <code>&quot;learned_range&quot;</code>, <em>optional</em>) &#x2014;
Set to <code>&quot;learned&quot;</code> or <code>&quot;learned_range&quot;</code> for diffusion models that predict variance. If set, the model&#x2019;s
output contains the predicted Gaussian variance.`,name:"variance_type"},{anchor:"diffusers.DPMSolverSinglestepScheduler.use_dynamic_shifting",description:`<strong>use_dynamic_shifting</strong> (<code>bool</code>, defaults to <code>False</code>) &#x2014;
Whether to use dynamic shifting for the noise schedule.`,name:"use_dynamic_shifting"},{anchor:"diffusers.DPMSolverSinglestepScheduler.time_shift_type",description:`<strong>time_shift_type</strong> (<code>&quot;exponential&quot;</code>, defaults to <code>&quot;exponential&quot;</code>) &#x2014;
The type of time shifting to apply.`,name:"time_shift_type"}]});var d=e(T,6),F=t(d);o(F,{name:"add_noise",anchor:"diffusers.DPMSolverSinglestepScheduler.add_noise",source:"https://github.com/huggingface/diffusers/blob/vr_14252/src/diffusers/schedulers/scheduling_dpmsolver_singlestep.py#L1262",parameters:[{name:"original_samples",val:": Tensor"},{name:"noise",val:": Tensor"},{name:"timesteps",val:": IntTensor"}],parametersDescription:[{anchor:"diffusers.DPMSolverSinglestepScheduler.add_noise.original_samples",description:`<strong>original_samples</strong> (<code>torch.Tensor</code>) &#x2014;
The original samples without noise.`,name:"original_samples"},{anchor:"diffusers.DPMSolverSinglestepScheduler.add_noise.noise",description:`<strong>noise</strong> (<code>torch.Tensor</code>) &#x2014;
The noise to add to the samples.`,name:"noise"},{anchor:"diffusers.DPMSolverSinglestepScheduler.add_noise.timesteps",description:`<strong>timesteps</strong> (<code>torch.IntTensor</code>) &#x2014;
The timesteps at which to add noise to the samples.`,name:"timesteps"}],returnDescription:`<script context="module">export const metadata = 'undefined';<\/script>


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


<p><code>torch.Tensor</code></p>
`}),s(2),r(d);var a=e(d,2),I=t(a);o(I,{name:"convert_model_output",anchor:"diffusers.DPMSolverSinglestepScheduler.convert_model_output",source:"https://github.com/huggingface/diffusers/blob/vr_14252/src/diffusers/schedulers/scheduling_dpmsolver_singlestep.py#L663",parameters:[{name:"model_output",val:": Tensor"},{name:"*args",val:""},{name:"sample",val:": typing.Optional[torch.Tensor] = None"},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"diffusers.DPMSolverSinglestepScheduler.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.DPMSolverSinglestepScheduler.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"}],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>
`}),s(4),r(a);var l=e(a,2),k=t(l);o(k,{name:"dpm_solver_first_order_update",anchor:"diffusers.DPMSolverSinglestepScheduler.dpm_solver_first_order_update",source:"https://github.com/huggingface/diffusers/blob/vr_14252/src/diffusers/schedulers/scheduling_dpmsolver_singlestep.py#L759",parameters:[{name:"model_output",val:": Tensor"},{name:"*args",val:""},{name:"sample",val:": typing.Optional[torch.Tensor] = None"},{name:"noise",val:": typing.Optional[torch.Tensor] = None"},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"diffusers.DPMSolverSinglestepScheduler.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.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.Tensor</code>) &#x2014;
A current instance of a sample created by the diffusion process.`,name:"sample"}],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>
`}),s(2),r(l);var c=e(l,2),z=t(c);o(z,{name:"get_order_list",anchor:"diffusers.DPMSolverSinglestepScheduler.get_order_list",source:"https://github.com/huggingface/diffusers/blob/vr_14252/src/diffusers/schedulers/scheduling_dpmsolver_singlestep.py#L253",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"}],returnDescription:`<script context="module">export const metadata = 'undefined';<\/script>


<p>The list of solver orders for each timestep.</p>
`,returnType:`<script context="module">export const metadata = 'undefined';<\/script>


<p><code>list[int]</code></p>
`}),s(2),r(c);var p=e(c,2),A=t(p);o(A,{name:"index_for_timestep",anchor:"diffusers.DPMSolverSinglestepScheduler.index_for_timestep",source:"https://github.com/huggingface/diffusers/blob/vr_14252/src/diffusers/schedulers/scheduling_dpmsolver_singlestep.py#L1120",parameters:[{name:"timestep",val:": typing.Union[int, torch.Tensor]"},{name:"schedule_timesteps",val:": typing.Optional[torch.Tensor] = None"}],parametersDescription:[{anchor:"diffusers.DPMSolverSinglestepScheduler.index_for_timestep.timestep",description:`<strong>timestep</strong> (<code>int</code> or <code>torch.Tensor</code>) &#x2014;
The timestep for which to find the index.`,name:"timestep"},{anchor:"diffusers.DPMSolverSinglestepScheduler.index_for_timestep.schedule_timesteps",description:`<strong>schedule_timesteps</strong> (<code>torch.Tensor</code>, <em>optional</em>) &#x2014;
The timestep schedule to search in. If <code>None</code>, uses <code>self.timesteps</code>.`,name:"schedule_timesteps"}],returnDescription:`<script context="module">export const metadata = 'undefined';<\/script>


<p>The index of the timestep in the schedule.</p>
`,returnType:`<script context="module">export const metadata = 'undefined';<\/script>


<p><code>int</code></p>
`}),s(2),r(p);var u=e(p,2),E=t(u);o(E,{name:"scale_model_input",anchor:"diffusers.DPMSolverSinglestepScheduler.scale_model_input",source:"https://github.com/huggingface/diffusers/blob/vr_14252/src/diffusers/schedulers/scheduling_dpmsolver_singlestep.py#L1246",parameters:[{name:"sample",val:": Tensor"},{name:"*args",val:""},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"diffusers.DPMSolverSinglestepScheduler.scale_model_input.sample",description:`<strong>sample</strong> (<code>torch.Tensor</code>) &#x2014;
The input sample.`,name:"sample"}],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>
`}),s(2),r(u);var m=e(u,2),W=t(m);o(W,{name:"set_begin_index",anchor:"diffusers.DPMSolverSinglestepScheduler.set_begin_index",source:"https://github.com/huggingface/diffusers/blob/vr_14252/src/diffusers/schedulers/scheduling_dpmsolver_singlestep.py#L320",parameters:[{name:"begin_index",val:": int = 0"}],parametersDescription:[{anchor:"diffusers.DPMSolverSinglestepScheduler.set_begin_index.begin_index",description:`<strong>begin_index</strong> (<code>int</code>, defaults to <code>0</code>) &#x2014;
The begin index for the scheduler.`,name:"begin_index"}]}),s(2),r(m);var h=e(m,2),U=t(h);o(U,{name:"set_timesteps",anchor:"diffusers.DPMSolverSinglestepScheduler.set_timesteps",source:"https://github.com/huggingface/diffusers/blob/vr_14252/src/diffusers/schedulers/scheduling_dpmsolver_singlestep.py#L330",parameters:[{name:"num_inference_steps",val:": int = None"},{name:"device",val:": typing.Union[str, torch.device] = None"},{name:"mu",val:": float | None = None"},{name:"timesteps",val:": list[int] | None = None"}],parametersDescription:[{anchor:"diffusers.DPMSolverSinglestepScheduler.set_timesteps.num_inference_steps",description:`<strong>num_inference_steps</strong> (<code>int</code>, <em>optional</em>) &#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"},{anchor:"diffusers.DPMSolverSinglestepScheduler.set_timesteps.timesteps",description:`<strong>timesteps</strong> (<code>list[int]</code>, <em>optional</em>) &#x2014;
Custom timesteps used to support arbitrary spacing between timesteps. If <code>None</code>, then the default
timestep spacing strategy of equal spacing between timesteps schedule is used. If <code>timesteps</code> is
passed, <code>num_inference_steps</code> must be <code>None</code>.`,name:"timesteps"}]}),s(2),r(h);var f=e(h,2),G=t(f);o(G,{name:"singlestep_dpm_solver_second_order_update",anchor:"diffusers.DPMSolverSinglestepScheduler.singlestep_dpm_solver_second_order_update",source:"https://github.com/huggingface/diffusers/blob/vr_14252/src/diffusers/schedulers/scheduling_dpmsolver_singlestep.py#L823",parameters:[{name:"model_output_list",val:": list"},{name:"*args",val:""},{name:"sample",val:": typing.Optional[torch.Tensor] = None"},{name:"noise",val:": typing.Optional[torch.Tensor] = 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.Tensor]</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.Tensor</code>) &#x2014;
A current instance of a sample created by the diffusion process.`,name:"sample"}],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>
`}),s(2),r(f);var g=e(f,2),H=t(g);o(H,{name:"singlestep_dpm_solver_third_order_update",anchor:"diffusers.DPMSolverSinglestepScheduler.singlestep_dpm_solver_third_order_update",source:"https://github.com/huggingface/diffusers/blob/vr_14252/src/diffusers/schedulers/scheduling_dpmsolver_singlestep.py#L934",parameters:[{name:"model_output_list",val:": list"},{name:"*args",val:""},{name:"sample",val:": typing.Optional[torch.Tensor] = None"},{name:"noise",val:": typing.Optional[torch.Tensor] = 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.Tensor]</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.Tensor</code>) &#x2014;
A current instance of a sample created by diffusion process.`,name:"sample"}],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>
`}),s(2),r(g);var _=e(g,2),B=t(_);o(B,{name:"singlestep_dpm_solver_update",anchor:"diffusers.DPMSolverSinglestepScheduler.singlestep_dpm_solver_update",source:"https://github.com/huggingface/diffusers/blob/vr_14252/src/diffusers/schedulers/scheduling_dpmsolver_singlestep.py#L1056",parameters:[{name:"model_output_list",val:": list"},{name:"*args",val:""},{name:"sample",val:": typing.Optional[torch.Tensor] = None"},{name:"order",val:": int = None"},{name:"noise",val:": typing.Optional[torch.Tensor] = None"},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"diffusers.DPMSolverSinglestepScheduler.singlestep_dpm_solver_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.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.Tensor</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"}],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>
`}),s(2),r(_);var M=e(_,2),V=t(M);o(V,{name:"step",anchor:"diffusers.DPMSolverSinglestepScheduler.step",source:"https://github.com/huggingface/diffusers/blob/vr_14252/src/diffusers/schedulers/scheduling_dpmsolver_singlestep.py#L1173",parameters:[{name:"model_output",val:": Tensor"},{name:"timestep",val:": typing.Union[int, torch.Tensor]"},{name:"sample",val:": Tensor"},{name:"generator",val:": typing.Optional[torch.Generator] = None"},{name:"return_dict",val:": bool = True"}],parametersDescription:[{anchor:"diffusers.DPMSolverSinglestepScheduler.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.DPMSolverSinglestepScheduler.step.timestep",description:`<strong>timestep</strong> (<code>int</code> or <code>torch.Tensor</code>) &#x2014;
The current discrete timestep in the diffusion chain.`,name:"timestep"},{anchor:"diffusers.DPMSolverSinglestepScheduler.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.DPMSolverSinglestepScheduler.step.generator",description:`<strong>generator</strong> (<code>torch.Generator</code>, <em>optional</em>) &#x2014;
A random number generator for stochastic sampling.`,name:"generator"},{anchor:"diffusers.DPMSolverSinglestepScheduler.step.return_dict",description:`<strong>return_dict</strong> (<code>bool</code>, defaults to <code>True</code>) &#x2014;
Whether or not to return a <a href="/docs/diffusers/pr_14252/en/api/schedulers/cosine_dpm#diffusers.schedulers.scheduling_utils.SchedulerOutput">SchedulerOutput</a> or <code>tuple</code>.`,name:"return_dict"}],returnDescription:`<script context="module">export const metadata = 'undefined';<\/script>


<p>If return_dict is <code>True</code>, <a
  href="/docs/diffusers/pr_14252/en/api/schedulers/cosine_dpm#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_14252/en/api/schedulers/cosine_dpm#diffusers.schedulers.scheduling_utils.SchedulerOutput"
>SchedulerOutput</a> or <code>tuple</code></p>
`}),s(2),r(M),r(i);var P=e(i,2);n(P,{title:"SchedulerOutput",local:"diffusers.schedulers.scheduling_utils.SchedulerOutput",headingTag:"h2"});var v=e(P,2),Y=t(v);o(Y,{name:"class diffusers.schedulers.scheduling_utils.SchedulerOutput",anchor:"diffusers.schedulers.scheduling_utils.SchedulerOutput",source:"https://github.com/huggingface/diffusers/blob/vr_14252/src/diffusers/schedulers/scheduling_utils.py#L61",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"}]}),s(2),r(v);var J=e(v,2);j(J,{source:"https://github.com/huggingface/diffusers/blob/main/docs/source/en/api/schedulers/singlestep_dpm_solver.md"}),s(2),O(N,S),oe()}export{ae as component};