diffusers/pr_14409/en/_app/immutable/nodes/255.COfhddQb.js

import"../chunks/DsnmJJEf.js";import{i as W,h as G,C as R,H as n,D as o,E as U,s as V}from"../chunks/BtE7mKSK.js";import{p as B,o as Y,s as e,f as H,a as T,b as J,c as s,d as P,n as t,r}from"../chunks/jDjavuwI.js";const X='{"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}';var Z=P('<meta name="hf:doc:metadata"/>'),j=P(`<p></p> <!> <!> <p><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.</p> <p>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>.</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 the 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>DPMSolverMultistepInverseScheduler</code> is the reverse scheduler of <a href="/docs/diffusers/pr_14409/en/api/schedulers/multistep_dpm_solver#diffusers.DPMSolverMultistepScheduler">DPMSolverMultistepScheduler</a>.</p> <p>This model inherits from <a href="/docs/diffusers/pr_14409/en/api/schedulers/overview#diffusers.SchedulerMixin">SchedulerMixin</a> and <a href="/docs/diffusers/pr_14409/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 clean <code>original_samples</code> using the scheduler’s equivalent function.</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>One step for the second-order multistep 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>One step for the third-order multistep 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>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 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>Predict the sample from the previous timestep by reversing the SDE. This function propagates the sample with
the multistep 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 ee(I,w){B(w,!1),Y(()=>{new URLSearchParams(window.location.search).get("fw")}),W();var f=j();G("ndoojn",y=>{var x=Z();V(x,"content",X),T(y,x)});var v=e(H(f),2);R(v,{containerStyle:"float: right; margin-left: 10px; display: inline-flex; position: relative; z-index: 10;"});var _=e(v,2);n(_,{title:"DPMSolverMultistepInverse",local:"dpmsolvermultistepinverse",headingTag:"h1"});var g=e(_,6);n(g,{title:"Tips",local:"tips",headingTag:"h2"});var b=e(g,4);n(b,{title:"DPMSolverMultistepInverseScheduler",local:"diffusers.DPMSolverMultistepInverseScheduler",headingTag:"h2"});var i=e(b,2),S=s(i);o(S,{name:"class diffusers.DPMSolverMultistepInverseScheduler",anchor:"diffusers.DPMSolverMultistepInverseScheduler",source:"https://github.com/huggingface/diffusers/blob/vr_14409/src/diffusers/schedulers/scheduling_dpmsolver_multistep_inverse.py#L86",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', 'sde-dpmsolver++'] = 'dpmsolver++'"},{name:"solver_type",val:": typing.Literal['midpoint', 'heun'] = 'midpoint'"},{name:"lower_order_final",val:": bool = True"},{name:"euler_at_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:"lambda_min_clipped",val:": float = -inf"},{name:"variance_type",val:": typing.Optional[typing.Literal['learned', 'learned_range']] = None"},{name:"timestep_spacing",val:": typing.Literal['linspace', 'leading', 'trailing'] = '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://huggingface.co/papers/2210.02303" 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.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.DPMSolverMultistepInverseScheduler.flow_shift",description:`<strong>flow_shift</strong> (<code>float</code>, <em>optional</em>, defaults to 1.0) &#x2014;
The flow shift factor. Valid only when <code>use_flow_sigmas=True</code>.`,name:"flow_shift"},{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"}]});var d=e(S,6),O=s(d);o(O,{name:"add_noise",anchor:"diffusers.DPMSolverMultistepInverseScheduler.add_noise",source:"https://github.com/huggingface/diffusers/blob/vr_14409/src/diffusers/schedulers/scheduling_dpmsolver_multistep_inverse.py#L1118",parameters:[{name:"original_samples",val:": Tensor"},{name:"noise",val:": Tensor"},{name:"timesteps",val:": IntTensor"}],parametersDescription:[{anchor:"diffusers.DPMSolverMultistepInverseScheduler.add_noise.original_samples",description:`<strong>original_samples</strong> (<code>torch.Tensor</code>) &#x2014;
The original samples to add noise to.`,name:"original_samples"},{anchor:"diffusers.DPMSolverMultistepInverseScheduler.add_noise.noise",description:`<strong>noise</strong> (<code>torch.Tensor</code>) &#x2014;
The noise tensor.`,name:"noise"},{anchor:"diffusers.DPMSolverMultistepInverseScheduler.add_noise.timesteps",description:`<strong>timesteps</strong> (<code>torch.IntTensor</code>) &#x2014;
The timesteps at which to add noise.`,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>
`}),t(2),r(d);var a=e(d,2),L=s(a);o(L,{name:"convert_model_output",anchor:"diffusers.DPMSolverMultistepInverseScheduler.convert_model_output",source:"https://github.com/huggingface/diffusers/blob/vr_14409/src/diffusers/schedulers/scheduling_dpmsolver_multistep_inverse.py#L600",parameters:[{name:"model_output",val:": Tensor"},{name:"*args",val:""},{name:"sample",val:": typing.Optional[torch.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>, <em>optional</em>) &#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>
`}),t(4),r(a);var l=e(a,2),N=s(l);o(N,{name:"dpm_solver_first_order_update",anchor:"diffusers.DPMSolverMultistepInverseScheduler.dpm_solver_first_order_update",source:"https://github.com/huggingface/diffusers/blob/vr_14409/src/diffusers/schedulers/scheduling_dpmsolver_multistep_inverse.py#L699",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.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>, <em>optional</em>) &#x2014;
A current instance of a sample created by the diffusion process.`,name:"sample"},{anchor:"diffusers.DPMSolverMultistepInverseScheduler.dpm_solver_first_order_update.noise",description:`<strong>noise</strong> (<code>torch.Tensor</code>, <em>optional</em>) &#x2014;
The noise tensor.`,name:"noise"}],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>
`}),t(2),r(l);var c=e(l,2),q=s(c);o(q,{name:"multistep_dpm_solver_second_order_update",anchor:"diffusers.DPMSolverMultistepInverseScheduler.multistep_dpm_solver_second_order_update",source:"https://github.com/huggingface/diffusers/blob/vr_14409/src/diffusers/schedulers/scheduling_dpmsolver_multistep_inverse.py#L774",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.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>, <em>optional</em>) &#x2014;
A current instance of a sample created by the diffusion process.`,name:"sample"},{anchor:"diffusers.DPMSolverMultistepInverseScheduler.multistep_dpm_solver_second_order_update.noise",description:`<strong>noise</strong> (<code>torch.Tensor</code>, <em>optional</em>) &#x2014;
Random noise used by the stochastic (<code>sde-*</code>) solver variants. Required when <code>algorithm_type</code> is set to
one of them, and unused otherwise.`,name:"noise"}],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>
`}),t(2),r(c);var p=e(c,2),C=s(p);o(C,{name:"multistep_dpm_solver_third_order_update",anchor:"diffusers.DPMSolverMultistepInverseScheduler.multistep_dpm_solver_third_order_update",source:"https://github.com/huggingface/diffusers/blob/vr_14409/src/diffusers/schedulers/scheduling_dpmsolver_multistep_inverse.py#L901",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.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>, <em>optional</em>) &#x2014;
A current instance of a sample created by diffusion process.`,name:"sample"},{anchor:"diffusers.DPMSolverMultistepInverseScheduler.multistep_dpm_solver_third_order_update.noise",description:`<strong>noise</strong> (<code>torch.Tensor</code>, <em>optional</em>) &#x2014;
The noise tensor.`,name:"noise"}],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>
`}),t(2),r(p);var u=e(p,2),F=s(u);o(F,{name:"scale_model_input",anchor:"diffusers.DPMSolverMultistepInverseScheduler.scale_model_input",source:"https://github.com/huggingface/diffusers/blob/vr_14409/src/diffusers/schedulers/scheduling_dpmsolver_multistep_inverse.py#L1103",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"}],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>
`}),t(2),r(u);var m=e(u,2),k=s(m);o(k,{name:"set_timesteps",anchor:"diffusers.DPMSolverMultistepInverseScheduler.set_timesteps",source:"https://github.com/huggingface/diffusers/blob/vr_14409/src/diffusers/schedulers/scheduling_dpmsolver_multistep_inverse.py#L283",parameters:[{name:"num_inference_steps",val:": int | None = None"},{name:"device",val:": typing.Union[str, torch.device, NoneType] = 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"}]}),t(2),r(m);var M=e(m,2),A=s(M);o(A,{name:"step",anchor:"diffusers.DPMSolverMultistepInverseScheduler.step",source:"https://github.com/huggingface/diffusers/blob/vr_14409/src/diffusers/schedulers/scheduling_dpmsolver_multistep_inverse.py#L1017",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:"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_14409/en/api/schedulers/dpm_discrete_ancestral#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_14409/en/api/schedulers/dpm_discrete_ancestral#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_14409/en/api/schedulers/dpm_discrete_ancestral#diffusers.schedulers.scheduling_utils.SchedulerOutput"
>SchedulerOutput</a> or <code>tuple</code></p>
`}),t(2),r(M),r(i);var D=e(i,2);n(D,{title:"SchedulerOutput",local:"diffusers.schedulers.scheduling_utils.SchedulerOutput",headingTag:"h2"});var h=e(D,2),E=s(h);o(E,{name:"class diffusers.schedulers.scheduling_utils.SchedulerOutput",anchor:"diffusers.schedulers.scheduling_utils.SchedulerOutput",source:"https://github.com/huggingface/diffusers/blob/vr_14409/src/diffusers/schedulers/scheduling_utils.py#L66",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"}]}),t(2),r(h);var z=e(h,2);U(z,{source:"https://github.com/huggingface/diffusers/blob/main/docs/source/en/api/schedulers/multistep_dpm_solver_inverse.md"}),t(2),T(I,f),J()}export{ee as component};