Buckets:

hf-doc-build
/

doc-dev

Files
xet
hf-doc-build/doc-dev / diffusers /pr_14921 /en /_app /immutable /nodes /265.DclL3mFW.js
HuggingFaceDocBuilder
21 days ago
download
raw
21.9 kB
import"../chunks/DsnmJJEf.js";import{i as I,h as L,C as O,H as x,D as o,E as A,s as F}from"../chunks/BLbO27j4.js";import{p as q,o as z,s as e,f as E,a as D,b as R,c as t,d as T,n as r,r as s}from"../chunks/jDjavuwI.js";const G='{"title":"CogVideoXDPMScheduler","local":"cogvideoxdpmscheduler","sections":[{"title":"CogVideoXDPMScheduler","local":"diffusers.CogVideoXDPMScheduler","sections":[],"depth":2}],"depth":1}';var W=T('<meta name="hf:doc:metadata"/>'),U=T(`<p></p> <!> <!> <p><code>CogVideoXDPMScheduler</code> is based on <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>, specifically for CogVideoX models.</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>DDIMScheduler</code> extends the denoising procedure introduced in denoising diffusion probabilistic models (DDPMs) with
non-Markovian guidance.</p> <p>This model inherits from <a href="/docs/diffusers/pr_14921/en/api/schedulers/overview#diffusers.SchedulerMixin">SchedulerMixin</a> and <a href="/docs/diffusers/pr_14921/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 magnitude at each timestep (this is the forward
diffusion process).</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>Compute the multipliers for the previous sample and the predicted original sample.</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>Compute the variables used for DPM-Solver++ (2M) referencing the original implementation.</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>Compute the velocity prediction from the sample and noise according to the velocity formula.</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 diffusion
process from the learned model outputs (most often the predicted noise).</p></div></div> <!> <p></p>`,1);function J(S,M){q(M,!1),z(()=>{new URLSearchParams(window.location.search).get("fw")}),I();var u=U();L("kvtxc5",v=>{var b=W();F(b,"content",G),D(v,b)});var h=e(E(u),2);O(h,{containerStyle:"float: right; margin-left: 10px; display: inline-flex; position: relative; z-index: 10;"});var m=e(h,2);x(m,{title:"CogVideoXDPMScheduler",local:"cogvideoxdpmscheduler",headingTag:"h1"});var f=e(m,4);x(f,{title:"CogVideoXDPMScheduler",local:"diffusers.CogVideoXDPMScheduler",headingTag:"h2"});var n=e(f,2),g=t(n);o(g,{name:"class diffusers.CogVideoXDPMScheduler",anchor:"diffusers.CogVideoXDPMScheduler",source:"https://github.com/huggingface/diffusers/blob/vr_14921/src/diffusers/schedulers/scheduling_dpm_cogvideox.py#L134",parameters:[{name:"num_train_timesteps",val:": int = 1000"},{name:"beta_start",val:": float = 0.00085"},{name:"beta_end",val:": float = 0.012"},{name:"beta_schedule",val:": typing.Literal['linear', 'scaled_linear', 'squaredcos_cap_v2'] = 'scaled_linear'"},{name:"trained_betas",val:": numpy.ndarray | list[float] | None = None"},{name:"clip_sample",val:": bool = True"},{name:"set_alpha_to_one",val:": bool = True"},{name:"steps_offset",val:": int = 0"},{name:"prediction_type",val:": typing.Literal['epsilon', 'sample', 'v_prediction'] = 'epsilon'"},{name:"clip_sample_range",val:": float = 1.0"},{name:"sample_max_value",val:": float = 1.0"},{name:"timestep_spacing",val:": typing.Literal['leading', 'linspace', 'trailing'] = 'leading'"},{name:"rescale_betas_zero_snr",val:": bool = False"},{name:"snr_shift_scale",val:": float = 3.0"}],parametersDescription:[{anchor:"diffusers.CogVideoXDPMScheduler.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.CogVideoXDPMScheduler.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.CogVideoXDPMScheduler.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.CogVideoXDPMScheduler.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.CogVideoXDPMScheduler.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.CogVideoXDPMScheduler.clip_sample",description:`<strong>clip_sample</strong> (<code>bool</code>, defaults to <code>True</code>) &#x2014;
Clip the predicted sample for numerical stability.`,name:"clip_sample"},{anchor:"diffusers.CogVideoXDPMScheduler.clip_sample_range",description:`<strong>clip_sample_range</strong> (<code>float</code>, defaults to 1.0) &#x2014;
The maximum magnitude for sample clipping. Valid only when <code>clip_sample=True</code>.`,name:"clip_sample_range"},{anchor:"diffusers.CogVideoXDPMScheduler.set_alpha_to_one",description:`<strong>set_alpha_to_one</strong> (<code>bool</code>, defaults to <code>True</code>) &#x2014;
Each diffusion step uses the alphas product value at that step and at the previous one. For the final step
there is no previous alpha. When this option is <code>True</code> the previous alpha product is fixed to <code>1</code>,
otherwise it uses the alpha value at step 0.`,name:"set_alpha_to_one"},{anchor:"diffusers.CogVideoXDPMScheduler.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"},{anchor:"diffusers.CogVideoXDPMScheduler.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.CogVideoXDPMScheduler.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.CogVideoXDPMScheduler.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.CogVideoXDPMScheduler.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>.`,name:"sample_max_value"},{anchor:"diffusers.CogVideoXDPMScheduler.timestep_spacing",description:`<strong>timestep_spacing</strong> (<code>str</code>, defaults to <code>&quot;leading&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. Choose from
<code>leading</code>, <code>linspace</code> or <code>trailing</code>.`,name:"timestep_spacing"},{anchor:"diffusers.CogVideoXDPMScheduler.rescale_betas_zero_snr",description:`<strong>rescale_betas_zero_snr</strong> (<code>bool</code>, defaults to <code>False</code>) &#x2014;
Whether to rescale the betas to have zero terminal SNR. This enables the model to generate very bright and
dark samples instead of limiting it to samples with medium brightness. Loosely related to
<a href="https://github.com/huggingface/diffusers/blob/74fd735eb073eb1d774b1ab4154a0876eb82f055/examples/dreambooth/train_dreambooth.py#L506" rel="nofollow"><code>--offset_noise</code></a>.`,name:"rescale_betas_zero_snr"},{anchor:"diffusers.CogVideoXDPMScheduler.snr_shift_scale",description:`<strong>snr_shift_scale</strong> (<code>float</code>, defaults to 3.0) &#x2014;
Shift scale for SNR.`,name:"snr_shift_scale"}]});var d=e(g,6),y=t(d);o(y,{name:"add_noise",anchor:"diffusers.CogVideoXDPMScheduler.add_noise",source:"https://github.com/huggingface/diffusers/blob/vr_14921/src/diffusers/schedulers/scheduling_dpm_cogvideox.py#L522",parameters:[{name:"original_samples",val:": Tensor"},{name:"noise",val:": Tensor"},{name:"timesteps",val:": IntTensor"}],parametersDescription:[{anchor:"diffusers.CogVideoXDPMScheduler.add_noise.original_samples",description:`<strong>original_samples</strong> (<code>torch.Tensor</code>) &#x2014;
The original samples to which noise will be added.`,name:"original_samples"},{anchor:"diffusers.CogVideoXDPMScheduler.add_noise.noise",description:`<strong>noise</strong> (<code>torch.Tensor</code>) &#x2014;
The noise to add to the samples.`,name:"noise"},{anchor:"diffusers.CogVideoXDPMScheduler.add_noise.timesteps",description:`<strong>timesteps</strong> (<code>torch.IntTensor</code>) &#x2014;
The timesteps indicating the noise level for each sample.`,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>
`}),r(2),s(d);var i=e(d,2),C=t(i);o(C,{name:"get_mult",anchor:"diffusers.CogVideoXDPMScheduler.get_mult",source:"https://github.com/huggingface/diffusers/blob/vr_14921/src/diffusers/schedulers/scheduling_dpm_cogvideox.py#L364",parameters:[{name:"h",val:": Tensor"},{name:"r",val:": Tensor"},{name:"alpha_prod_t",val:": Tensor"},{name:"alpha_prod_t_prev",val:": Tensor"},{name:"alpha_prod_t_back",val:": typing.Optional[torch.Tensor] = None"}],parametersDescription:[{anchor:"diffusers.CogVideoXDPMScheduler.get_mult.h",description:`<strong>h</strong> (<code>torch.Tensor</code>) &#x2014;
The log-SNR difference.`,name:"h"},{anchor:"diffusers.CogVideoXDPMScheduler.get_mult.r",description:`<strong>r</strong> (<code>torch.Tensor</code>) &#x2014;
The ratio of log-SNR differences.`,name:"r"},{anchor:"diffusers.CogVideoXDPMScheduler.get_mult.alpha_prod_t",description:`<strong>alpha_prod_t</strong> (<code>torch.Tensor</code>) &#x2014;
The cumulative product of alphas at the current timestep.`,name:"alpha_prod_t"},{anchor:"diffusers.CogVideoXDPMScheduler.get_mult.alpha_prod_t_prev",description:`<strong>alpha_prod_t_prev</strong> (<code>torch.Tensor</code>) &#x2014;
The cumulative product of alphas at the previous timestep.`,name:"alpha_prod_t_prev"},{anchor:"diffusers.CogVideoXDPMScheduler.get_mult.alpha_prod_t_back",description:`<strong>alpha_prod_t_back</strong> (<code>torch.Tensor</code>, <em>optional</em>) &#x2014;
The cumulative product of alphas at the timestep before the previous timestep.`,name:"alpha_prod_t_back"}],returnDescription:`<script context="module">export const metadata = 'undefined';<\/script>
<p>A tuple containing the multipliers.</p>
`,returnType:`<script context="module">export const metadata = 'undefined';<\/script>
<p><code>tuple</code></p>
`}),r(2),s(i);var a=e(i,2),P=t(a);o(P,{name:"get_variables",anchor:"diffusers.CogVideoXDPMScheduler.get_variables",source:"https://github.com/huggingface/diffusers/blob/vr_14921/src/diffusers/schedulers/scheduling_dpm_cogvideox.py#L331",parameters:[{name:"alpha_prod_t",val:": Tensor"},{name:"alpha_prod_t_prev",val:": Tensor"},{name:"alpha_prod_t_back",val:": typing.Optional[torch.Tensor] = None"}],parametersDescription:[{anchor:"diffusers.CogVideoXDPMScheduler.get_variables.alpha_prod_t",description:`<strong>alpha_prod_t</strong> (<code>torch.Tensor</code>) &#x2014;
The cumulative product of alphas at the current timestep.`,name:"alpha_prod_t"},{anchor:"diffusers.CogVideoXDPMScheduler.get_variables.alpha_prod_t_prev",description:`<strong>alpha_prod_t_prev</strong> (<code>torch.Tensor</code>) &#x2014;
The cumulative product of alphas at the previous timestep.`,name:"alpha_prod_t_prev"},{anchor:"diffusers.CogVideoXDPMScheduler.get_variables.alpha_prod_t_back",description:`<strong>alpha_prod_t_back</strong> (<code>torch.Tensor</code>, <em>optional</em>) &#x2014;
The cumulative product of alphas at the timestep before the previous timestep.`,name:"alpha_prod_t_back"}],returnDescription:`<script context="module">export const metadata = 'undefined';<\/script>
<p>A tuple containing the variables <code>h</code>, <code>r</code>, <code>lamb</code>, <code>lamb_next</code>.</p>
`,returnType:`<script context="module">export const metadata = 'undefined';<\/script>
<p><code>tuple</code></p>
`}),r(2),s(a);var c=e(a,2),V=t(c);o(V,{name:"get_velocity",anchor:"diffusers.CogVideoXDPMScheduler.get_velocity",source:"https://github.com/huggingface/diffusers/blob/vr_14921/src/diffusers/schedulers/scheduling_dpm_cogvideox.py#L565",parameters:[{name:"sample",val:": Tensor"},{name:"noise",val:": Tensor"},{name:"timesteps",val:": IntTensor"}],parametersDescription:[{anchor:"diffusers.CogVideoXDPMScheduler.get_velocity.sample",description:`<strong>sample</strong> (<code>torch.Tensor</code>) &#x2014;
The input sample.`,name:"sample"},{anchor:"diffusers.CogVideoXDPMScheduler.get_velocity.noise",description:`<strong>noise</strong> (<code>torch.Tensor</code>) &#x2014;
The noise tensor.`,name:"noise"},{anchor:"diffusers.CogVideoXDPMScheduler.get_velocity.timesteps",description:`<strong>timesteps</strong> (<code>torch.IntTensor</code>) &#x2014;
The timesteps for velocity computation.`,name:"timesteps"}],returnDescription:`<script context="module">export const metadata = 'undefined';<\/script>
<p>The computed velocity.</p>
`,returnType:`<script context="module">export const metadata = 'undefined';<\/script>
<p><code>torch.Tensor</code></p>
`}),r(2),s(c);var l=e(c,2),X=t(l);o(X,{name:"scale_model_input",anchor:"diffusers.CogVideoXDPMScheduler.scale_model_input",source:"https://github.com/huggingface/diffusers/blob/vr_14921/src/diffusers/schedulers/scheduling_dpm_cogvideox.py#L262",parameters:[{name:"sample",val:": Tensor"},{name:"timestep",val:": int | None = None"}],parametersDescription:[{anchor:"diffusers.CogVideoXDPMScheduler.scale_model_input.sample",description:`<strong>sample</strong> (<code>torch.Tensor</code>) &#x2014;
The input sample.`,name:"sample"},{anchor:"diffusers.CogVideoXDPMScheduler.scale_model_input.timestep",description:`<strong>timestep</strong> (<code>int</code>, <em>optional</em>) &#x2014;
The current timestep in the diffusion chain.`,name:"timestep"}],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>
`}),r(2),s(l);var p=e(l,2),w=t(p);o(w,{name:"set_timesteps",anchor:"diffusers.CogVideoXDPMScheduler.set_timesteps",source:"https://github.com/huggingface/diffusers/blob/vr_14921/src/diffusers/schedulers/scheduling_dpm_cogvideox.py#L279",parameters:[{name:"num_inference_steps",val:": int"},{name:"device",val:": typing.Union[str, torch.device, NoneType] = None"}],parametersDescription:[{anchor:"diffusers.CogVideoXDPMScheduler.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.CogVideoXDPMScheduler.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 default), the timesteps are not
moved.`,name:"device"}]}),r(2),s(p);var _=e(p,2),k=t(_);o(k,{name:"step",anchor:"diffusers.CogVideoXDPMScheduler.step",source:"https://github.com/huggingface/diffusers/blob/vr_14921/src/diffusers/schedulers/scheduling_dpm_cogvideox.py#L401",parameters:[{name:"model_output",val:": Tensor"},{name:"old_pred_original_sample",val:": Tensor"},{name:"timestep",val:": int"},{name:"timestep_back",val:": int"},{name:"sample",val:": Tensor"},{name:"eta",val:": float = 0.0"},{name:"use_clipped_model_output",val:": bool = False"},{name:"generator",val:": typing.Optional[torch.Generator] = None"},{name:"variance_noise",val:": typing.Optional[torch.Tensor] = None"},{name:"return_dict",val:": bool = False"}],parametersDescription:[{anchor:"diffusers.CogVideoXDPMScheduler.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.CogVideoXDPMScheduler.step.old_pred_original_sample",description:`<strong>old_pred_original_sample</strong> (<code>torch.Tensor</code>) &#x2014;
The predicted original sample from the previous timestep.`,name:"old_pred_original_sample"},{anchor:"diffusers.CogVideoXDPMScheduler.step.timestep",description:`<strong>timestep</strong> (<code>int</code>) &#x2014;
The current discrete timestep in the diffusion chain.`,name:"timestep"},{anchor:"diffusers.CogVideoXDPMScheduler.step.timestep_back",description:`<strong>timestep_back</strong> (<code>int</code>) &#x2014;
The timestep to look back to.`,name:"timestep_back"},{anchor:"diffusers.CogVideoXDPMScheduler.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.CogVideoXDPMScheduler.step.eta",description:`<strong>eta</strong> (<code>float</code>) &#x2014;
The weight of noise for added noise in diffusion step.`,name:"eta"},{anchor:"diffusers.CogVideoXDPMScheduler.step.use_clipped_model_output",description:`<strong>use_clipped_model_output</strong> (<code>bool</code>, defaults to <code>False</code>) &#x2014;
If <code>True</code>, computes &#x201C;corrected&#x201D; <code>model_output</code> from the clipped predicted original sample. Necessary
because predicted original sample is clipped to [-1, 1] when <code>self.config.clip_sample</code> is <code>True</code>. If no
clipping has happened, &#x201C;corrected&#x201D; <code>model_output</code> would coincide with the one provided as input and
<code>use_clipped_model_output</code> has no effect.`,name:"use_clipped_model_output"},{anchor:"diffusers.CogVideoXDPMScheduler.step.generator",description:`<strong>generator</strong> (<code>torch.Generator</code>, <em>optional</em>) &#x2014;
A random number generator.`,name:"generator"},{anchor:"diffusers.CogVideoXDPMScheduler.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.CogVideoXDPMScheduler.step.return_dict",description:`<strong>return_dict</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>True</code>) &#x2014;
Whether or not to return a <a href="/docs/diffusers/pr_14921/en/api/schedulers/ddim#diffusers.schedulers.scheduling_ddim.DDIMSchedulerOutput">DDIMSchedulerOutput</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_14921/en/api/schedulers/ddim#diffusers.schedulers.scheduling_ddim.DDIMSchedulerOutput"
>DDIMSchedulerOutput</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_14921/en/api/schedulers/ddim#diffusers.schedulers.scheduling_ddim.DDIMSchedulerOutput"
>DDIMSchedulerOutput</a> or <code>tuple</code></p>
`}),r(2),s(_),s(n);var N=e(n,2);A(N,{source:"https://github.com/huggingface/diffusers/blob/main/docs/source/en/api/schedulers/multistep_dpm_solver_cogvideox.md"}),r(2),D(S,u),R()}export{J as component};
Xet Storage Details

Size:: 21.9 kB
Xet hash:: 7ae0d99dd5f9b28d43b68e4448a2781e62693532bedac8b176af48c6f3874b9b
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.