# DPMSolverMultistepScheduler `DPMSolverMultistepScheduler` is a multistep scheduler from [DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps](https://huggingface.co/papers/2206.00927) and [DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models](https://huggingface.co/papers/2211.01095) by Cheng Lu, Yuhao Zhou, Fan Bao, Jianfei Chen, Chongxuan Li, and Jun Zhu. 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. ## Tips It is recommended to set `solver_order` to 2 for guide sampling, and `solver_order=3` for unconditional sampling. Dynamic thresholding from [Imagen](https://huggingface.co/papers/2205.11487) is supported, and for pixel-space diffusion models, you can set both `algorithm_type="dpmsolver++"` and `thresholding=True` to use the dynamic thresholding. This thresholding method is unsuitable for latent-space diffusion models such as Stable Diffusion. The SDE variant of DPMSolver and DPM-Solver++ is also supported, but only for the first and second-order solvers. This is a fast SDE solver for the reverse diffusion SDE. It is recommended to use the second-order `sde-dpmsolver++`. ## DPMSolverMultistepScheduler[[diffusers.DPMSolverMultistepScheduler]] #### diffusers.DPMSolverMultistepScheduler[[diffusers.DPMSolverMultistepScheduler]] [Source](https://github.com/huggingface/diffusers/blob/v0.37.1/src/diffusers/schedulers/scheduling_dpmsolver_multistep.py#L123) `DPMSolverMultistepScheduler` is a fast dedicated high-order solver for diffusion ODEs. This model inherits from [SchedulerMixin](/docs/diffusers/v0.37.1/en/api/schedulers/overview#diffusers.SchedulerMixin) and [ConfigMixin](/docs/diffusers/v0.37.1/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.DPMSolverMultistepScheduler.add_noisehttps://github.com/huggingface/diffusers/blob/v0.37.1/src/diffusers/schedulers/scheduling_dpmsolver_multistep.py#L1297[{"name": "original_samples", "val": ": Tensor"}, {"name": "noise", "val": ": Tensor"}, {"name": "timesteps", "val": ": IntTensor"}]- **original_samples** (`torch.Tensor`) -- The original samples without noise. - **noise** (`torch.Tensor`) -- The noise to add to the samples. - **timesteps** (`torch.IntTensor`) -- The timesteps at which to add noise to the samples.0`torch.Tensor`The noisy samples. Add noise to the original samples according to the noise schedule at the specified timesteps. **Parameters:** num_train_timesteps (`int`, defaults to 1000) : The number of diffusion steps to train the model. beta_start (`float`, defaults to 0.0001) : The starting `beta` value of inference. beta_end (`float`, defaults to 0.02) : The final `beta` value. beta_schedule (`"linear"`, `"scaled_linear"`, or `"squaredcos_cap_v2"`, defaults to `"linear"`) : The beta schedule, a mapping from a beta range to a sequence of betas for stepping the model. trained_betas (`np.ndarray`, *optional*) : Pass an array of betas directly to the constructor to bypass `beta_start` and `beta_end`. solver_order (`int`, defaults to 2) : The DPMSolver order which can be `1` or `2` or `3`. It is recommended to use `solver_order=2` for guided sampling, and `solver_order=3` for unconditional sampling. prediction_type (`"epsilon"`, `"sample"`, `"v_prediction"`, or `"flow_prediction"`, defaults to `"epsilon"`) : Prediction type of the scheduler function. `epsilon` predicts the noise of the diffusion process, `sample` directly predicts the noisy sample, `v_prediction` predicts the velocity (see section 2.4 of [Imagen Video](https://huggingface.co/papers/2210.02303) paper), and `flow_prediction` predicts the flow. thresholding (`bool`, defaults to `False`) : Whether to use the "dynamic thresholding" method. This is unsuitable for latent-space diffusion models such as Stable Diffusion. dynamic_thresholding_ratio (`float`, defaults to 0.995) : The ratio for the dynamic thresholding method. Valid only when `thresholding=True`. sample_max_value (`float`, defaults to 1.0) : The threshold value for dynamic thresholding. Valid only when `thresholding=True` and `algorithm_type="dpmsolver++"`. algorithm_type (`"dpmsolver"`, `"dpmsolver++"`, `"sde-dpmsolver"`, or `"sde-dpmsolver++"`, defaults to `"dpmsolver++"`) : Algorithm type for the solver. The `dpmsolver` type implements the algorithms in the [DPMSolver](https://huggingface.co/papers/2206.00927) paper, and the `dpmsolver++` type implements the algorithms in the [DPMSolver++](https://huggingface.co/papers/2211.01095) paper. It is recommended to use `dpmsolver++` or `sde-dpmsolver++` with `solver_order=2` for guided sampling like in Stable Diffusion. solver_type (`"midpoint"` or `"heun"`, defaults to `"midpoint"`) : Solver type for the second-order solver. 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`, *optional*) : A current instance of a sample created by the diffusion process. **Returns:** ``torch.Tensor`` The converted model output. #### dpm_solver_first_order_update[[diffusers.DPMSolverMultistepScheduler.dpm_solver_first_order_update]] [Source](https://github.com/huggingface/diffusers/blob/v0.37.1/src/diffusers/schedulers/scheduling_dpmsolver_multistep.py#L844) 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`, *optional*) : A current instance of a sample created by the diffusion process. noise (`torch.Tensor`, *optional*) : The noise tensor. **Returns:** ``torch.Tensor`` The sample tensor at the previous timestep. #### index_for_timestep[[diffusers.DPMSolverMultistepScheduler.index_for_timestep]] [Source](https://github.com/huggingface/diffusers/blob/v0.37.1/src/diffusers/schedulers/scheduling_dpmsolver_multistep.py#L1138) 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.DPMSolverMultistepScheduler.multistep_dpm_solver_second_order_update]] [Source](https://github.com/huggingface/diffusers/blob/v0.37.1/src/diffusers/schedulers/scheduling_dpmsolver_multistep.py#L918) 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`, *optional*) : A current instance of a sample created by the diffusion process. **Returns:** ``torch.Tensor`` The sample tensor at the previous timestep. #### multistep_dpm_solver_third_order_update[[diffusers.DPMSolverMultistepScheduler.multistep_dpm_solver_third_order_update]] [Source](https://github.com/huggingface/diffusers/blob/v0.37.1/src/diffusers/schedulers/scheduling_dpmsolver_multistep.py#L1041) One step for the third-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`, *optional*) : A current instance of a sample created by diffusion process. noise (`torch.Tensor`, *optional*) : The noise tensor. **Returns:** ``torch.Tensor`` The sample tensor at the previous timestep. #### scale_model_input[[diffusers.DPMSolverMultistepScheduler.scale_model_input]] [Source](https://github.com/huggingface/diffusers/blob/v0.37.1/src/diffusers/schedulers/scheduling_dpmsolver_multistep.py#L1282) Ensures interchangeability with schedulers that need to scale the denoising model input depending on the current timestep. **Parameters:** sample (`torch.Tensor`) : The input sample. **Returns:** ``torch.Tensor`` A scaled input sample. #### set_begin_index[[diffusers.DPMSolverMultistepScheduler.set_begin_index]] [Source](https://github.com/huggingface/diffusers/blob/v0.37.1/src/diffusers/schedulers/scheduling_dpmsolver_multistep.py#L357) 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.DPMSolverMultistepScheduler.set_timesteps]] [Source](https://github.com/huggingface/diffusers/blob/v0.37.1/src/diffusers/schedulers/scheduling_dpmsolver_multistep.py#L367) Sets the discrete timesteps used for the diffusion chain (to be run before inference). **Parameters:** num_inference_steps (`int`, *optional*) : 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. timesteps (`list[int]`, *optional*) : Custom timesteps used to support arbitrary timesteps schedule. If `None`, timesteps will be generated based on the `timestep_spacing` attribute. If `timesteps` is passed, `num_inference_steps` and `sigmas` must be `None`, and `timestep_spacing` attribute will be ignored. #### step[[diffusers.DPMSolverMultistepScheduler.step]] [Source](https://github.com/huggingface/diffusers/blob/v0.37.1/src/diffusers/schedulers/scheduling_dpmsolver_multistep.py#L1190) 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 the learned diffusion model. timestep (`int` or `torch.Tensor`) : 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. variance_noise (`torch.Tensor`, *optional*) : Alternative to generating noise with `generator` by directly providing the noise for the variance itself. Useful for methods such as `LEdits++`. return_dict (`bool`, defaults to `True`) : Whether or not to return a [SchedulerOutput](/docs/diffusers/v0.37.1/en/api/schedulers/overview#diffusers.schedulers.scheduling_utils.SchedulerOutput) or `tuple`. **Returns:** `[SchedulerOutput](/docs/diffusers/v0.37.1/en/api/schedulers/overview#diffusers.schedulers.scheduling_utils.SchedulerOutput) or `tuple`` If `return_dict` is `True`, [SchedulerOutput](/docs/diffusers/v0.37.1/en/api/schedulers/overview#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/v0.37.1/src/diffusers/schedulers/scheduling_utils.py#L61) 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.