# CosineDPMSolverMultistepScheduler The [CosineDPMSolverMultistepScheduler](/docs/diffusers/v0.36.0/en/api/schedulers/cosine_dpm#diffusers.CosineDPMSolverMultistepScheduler) is a variant of [DPMSolverMultistepScheduler](/docs/diffusers/v0.36.0/en/api/schedulers/multistep_dpm_solver#diffusers.DPMSolverMultistepScheduler) with cosine schedule, proposed by Nichol and Dhariwal (2021). It is being used in the [Stable Audio Open](https://huggingface.co/papers/2407.14358) paper and the [Stability-AI/stable-audio-tool](https://github.com/Stability-AI/stable-audio-tools) codebase. This scheduler was contributed by [Yoach Lacombe](https://huggingface.co/ylacombe). ## CosineDPMSolverMultistepScheduler[[diffusers.CosineDPMSolverMultistepScheduler]] #### diffusers.CosineDPMSolverMultistepScheduler[[diffusers.CosineDPMSolverMultistepScheduler]] [Source](https://github.com/huggingface/diffusers/blob/v0.36.0/src/diffusers/schedulers/scheduling_cosine_dpmsolver_multistep.py#L28) Implements a variant of `DPMSolverMultistepScheduler` with cosine schedule, proposed by Nichol and Dhariwal (2021). This scheduler was used in Stable Audio Open [1]. [1] Evans, Parker, et al. "Stable Audio Open" https://huggingface.co/papers/2407.14358 This model inherits from [SchedulerMixin](/docs/diffusers/v0.36.0/en/api/schedulers/overview#diffusers.SchedulerMixin) and [ConfigMixin](/docs/diffusers/v0.36.0/en/api/configuration#diffusers.ConfigMixin). Check the superclass documentation for the generic methods the library implements for all schedulers such as loading and saving. add_noisediffusers.CosineDPMSolverMultistepScheduler.add_noisehttps://github.com/huggingface/diffusers/blob/v0.36.0/src/diffusers/schedulers/scheduling_cosine_dpmsolver_multistep.py#L566[{"name": "original_samples", "val": ": Tensor"}, {"name": "noise", "val": ": Tensor"}, {"name": "timesteps", "val": ": Tensor"}]- **original_samples** (`torch.Tensor`) -- The original samples to which noise will be added. - **noise** (`torch.Tensor`) -- The noise tensor to add to the original samples. - **timesteps** (`torch.Tensor`) -- The timesteps at which to add noise, determining the noise level from the schedule.0`torch.Tensor`The noisy samples with added noise scaled according to the timestep schedule. Add noise to the original samples according to the noise schedule at the specified timesteps. **Parameters:** sigma_min (`float`, *optional*, defaults to 0.3) : Minimum noise magnitude in the sigma schedule. This was set to 0.3 in Stable Audio Open [1]. sigma_max (`float`, *optional*, defaults to 500) : Maximum noise magnitude in the sigma schedule. This was set to 500 in Stable Audio Open [1]. sigma_data (`float`, *optional*, defaults to 1.0) : The standard deviation of the data distribution. This is set to 1.0 in Stable Audio Open [1]. sigma_schedule (`str`, *optional*, defaults to `exponential`) : Sigma schedule to compute the `sigmas`. By default, we the schedule introduced in the EDM paper (https://huggingface.co/papers/2206.00364). Other acceptable value is "exponential". The exponential schedule was incorporated in this model: https://huggingface.co/stabilityai/cosxl. num_train_timesteps (`int`, defaults to 1000) : The number of diffusion steps to train the model. solver_order (`int`, defaults to 2) : The DPMSolver order which can be `1` or `2`. It is recommended to use `solver_order=2`. prediction_type (`str`, defaults to `v_prediction`, *optional*) : Prediction type of the scheduler function; can be `epsilon` (predicts the noise of the diffusion process), `sample` (directly predicts the noisy sample`) or `v_prediction` (see section 2.4 of [Imagen Video](https://huggingface.co/papers/2210.02303) paper). solver_type (`str`, defaults to `midpoint`) : Solver type for the second-order solver; can be `midpoint` or `heun`. The solver type slightly affects the sample quality, especially for a small number of steps. It is recommended to use `midpoint` solvers. lower_order_final (`bool`, defaults to `True`) : Whether to use lower-order solvers in the final steps. Only valid for [!TIP] > The algorithm and model type are decoupled. You can use either DPMSolver or DPMSolver++ for both noise > prediction and data prediction models. **Parameters:** model_output (`torch.Tensor`) : The direct output from the learned diffusion model. sample (`torch.Tensor`) : A current instance of a sample created by the diffusion process. **Returns:** ``torch.Tensor`` The converted model output. #### dpm_solver_first_order_update[[diffusers.CosineDPMSolverMultistepScheduler.dpm_solver_first_order_update]] [Source](https://github.com/huggingface/diffusers/blob/v0.36.0/src/diffusers/schedulers/scheduling_cosine_dpmsolver_multistep.py#L338) One step for the first-order DPMSolver (equivalent to DDIM). **Parameters:** model_output (`torch.Tensor`) : The direct output from the learned diffusion model. sample (`torch.Tensor`) : A current instance of a sample created by the diffusion process. **Returns:** ``torch.Tensor`` The sample tensor at the previous timestep. #### index_for_timestep[[diffusers.CosineDPMSolverMultistepScheduler.index_for_timestep]] [Source](https://github.com/huggingface/diffusers/blob/v0.36.0/src/diffusers/schedulers/scheduling_cosine_dpmsolver_multistep.py#L432) Find the index for a given timestep in the schedule. **Parameters:** timestep (`int` or `torch.Tensor`) : The timestep for which to find the index. schedule_timesteps (`torch.Tensor`, *optional*) : The timestep schedule to search in. If `None`, uses `self.timesteps`. **Returns:** ``int`` The index of the timestep in the schedule. #### multistep_dpm_solver_second_order_update[[diffusers.CosineDPMSolverMultistepScheduler.multistep_dpm_solver_second_order_update]] [Source](https://github.com/huggingface/diffusers/blob/v0.36.0/src/diffusers/schedulers/scheduling_cosine_dpmsolver_multistep.py#L373) One step for the second-order multistep DPMSolver. **Parameters:** model_output_list (`List[torch.Tensor]`) : The direct outputs from learned diffusion model at current and latter timesteps. sample (`torch.Tensor`) : A current instance of a sample created by the diffusion process. **Returns:** ``torch.Tensor`` The sample tensor at the previous timestep. #### scale_model_input[[diffusers.CosineDPMSolverMultistepScheduler.scale_model_input]] [Source](https://github.com/huggingface/diffusers/blob/v0.36.0/src/diffusers/schedulers/scheduling_cosine_dpmsolver_multistep.py#L174) Ensures interchangeability with schedulers that need to scale the denoising model input depending on the current timestep. Scales the denoising model input by `(sigma**2 + 1) ** 0.5` to match the Euler algorithm. **Parameters:** sample (`torch.Tensor`) : The input sample. timestep (`int`, *optional*) : The current timestep in the diffusion chain. **Returns:** ``torch.Tensor`` A scaled input sample. #### set_begin_index[[diffusers.CosineDPMSolverMultistepScheduler.set_begin_index]] [Source](https://github.com/huggingface/diffusers/blob/v0.36.0/src/diffusers/schedulers/scheduling_cosine_dpmsolver_multistep.py#L135) Sets the begin index for the scheduler. This function should be run from pipeline before the inference. **Parameters:** begin_index (`int`, defaults to `0`) : The begin index for the scheduler. #### set_timesteps[[diffusers.CosineDPMSolverMultistepScheduler.set_timesteps]] [Source](https://github.com/huggingface/diffusers/blob/v0.36.0/src/diffusers/schedulers/scheduling_cosine_dpmsolver_multistep.py#L198) Sets the discrete timesteps used for the diffusion chain (to be run before inference). **Parameters:** num_inference_steps (`int`) : The number of diffusion steps used when generating samples with a pre-trained model. device (`str` or `torch.device`, *optional*) : The device to which the timesteps should be moved to. If `None`, the timesteps are not moved. #### step[[diffusers.CosineDPMSolverMultistepScheduler.step]] [Source](https://github.com/huggingface/diffusers/blob/v0.36.0/src/diffusers/schedulers/scheduling_cosine_dpmsolver_multistep.py#L483) Predict the sample from the previous timestep by reversing the SDE. This function propagates the sample with the multistep DPMSolver. **Parameters:** model_output (`torch.Tensor`) : The direct output from learned diffusion model. timestep (`int`) : The current discrete timestep in the diffusion chain. sample (`torch.Tensor`) : A current instance of a sample created by the diffusion process. generator (`torch.Generator`, *optional*) : A random number generator. return_dict (`bool`) : Whether or not to return a [SchedulerOutput](/docs/diffusers/v0.36.0/en/api/schedulers/pndm#diffusers.schedulers.scheduling_utils.SchedulerOutput) or `tuple`. **Returns:** `[SchedulerOutput](/docs/diffusers/v0.36.0/en/api/schedulers/pndm#diffusers.schedulers.scheduling_utils.SchedulerOutput) or `tuple`` If return_dict is `True`, [SchedulerOutput](/docs/diffusers/v0.36.0/en/api/schedulers/pndm#diffusers.schedulers.scheduling_utils.SchedulerOutput) is returned, otherwise a tuple is returned where the first element is the sample tensor. ## SchedulerOutput[[diffusers.schedulers.scheduling_utils.SchedulerOutput]] #### diffusers.schedulers.scheduling_utils.SchedulerOutput[[diffusers.schedulers.scheduling_utils.SchedulerOutput]] [Source](https://github.com/huggingface/diffusers/blob/v0.36.0/src/diffusers/schedulers/scheduling_utils.py#L62) Base class for the output of a scheduler's `step` function. **Parameters:** prev_sample (`torch.Tensor` of shape `(batch_size, num_channels, height, width)` for images) : Computed sample `(x_{t-1})` of previous timestep. `prev_sample` should be used as next model input in the denoising loop.