Method sample

schedule/dpm_solver_pytorch.py:1055–1253

Compute the sample at time `t_end` by DPM-Solver, given the initial `x` at time `t_start`. ===================================================== We support the following algorithms for both noise prediction model and data prediction model: - 'singlestep':

(self, x, steps=20, t_start=None, t_end=None, order=2, skip_type='time_uniform',
        method='multistep', lower_order_final=True, denoise_to_zero=False, solver_type='dpmsolver',
        atol=0.0078, rtol=0.05, return_intermediate=False,
    )

            atol=atol, rtol=rtol, return_intermediate=return_intermediate)

    def sample(self, x, steps=20, t_start=None, t_end=None, order=2, skip_type='time_uniform',
        method='multistep', lower_order_final=True, denoise_to_zero=False, solver_type='dpmsolver',
        atol=0.0078, rtol=0.05, return_intermediate=False,
    ):
        """
        Compute the sample at time `t_end` by DPM-Solver, given the initial `x` at time `t_start`.

        =====================================================

        We support the following algorithms for both noise prediction model and data prediction model:
            - 'singlestep':
                Singlestep DPM-Solver (i.e. "DPM-Solver-fast" in the paper), which combines different orders of singlestep DPM-Solver. 
                We combine all the singlestep solvers with order <= `order` to use up all the function evaluations (steps).
                The total number of function evaluations (NFE) == `steps`.
                Given a fixed NFE == `steps`, the sampling procedure is:
                    - If `order` == 1:
                        - Denote K = steps. We use K steps of DPM-Solver-1 (i.e. DDIM).
                    - If `order` == 2:
                        - Denote K = (steps // 2) + (steps % 2). We take K intermediate time steps for sampling.
                        - If steps % 2 == 0, we use K steps of singlestep DPM-Solver-2.
                        - If steps % 2 == 1, we use (K - 1) steps of singlestep DPM-Solver-2 and 1 step of DPM-Solver-1.
                    - If `order` == 3:
                        - Denote K = (steps // 3 + 1). We take K intermediate time steps for sampling.
                        - If steps % 3 == 0, we use (K - 2) steps of singlestep DPM-Solver-3, and 1 step of singlestep DPM-Solver-2 and 1 step of DPM-Solver-1.
                        - If steps % 3 == 1, we use (K - 1) steps of singlestep DPM-Solver-3 and 1 step of DPM-Solver-1.
                        - If steps % 3 == 2, we use (K - 1) steps of singlestep DPM-Solver-3 and 1 step of singlestep DPM-Solver-2.
            - 'multistep':
                Multistep DPM-Solver with the order of `order`. The total number of function evaluations (NFE) == `steps`.
                We initialize the first `order` values by lower order multistep solvers.
                Given a fixed NFE == `steps`, the sampling procedure is:
                    Denote K = steps.
                    - If `order` == 1:
                        - We use K steps of DPM-Solver-1 (i.e. DDIM).
                    - If `order` == 2:
                        - We firstly use 1 step of DPM-Solver-1, then use (K - 1) step of multistep DPM-Solver-2.
                    - If `order` == 3:
                        - We firstly use 1 step of DPM-Solver-1, then 1 step of multistep DPM-Solver-2, then (K - 2) step of multistep DPM-Solver-3.
            - 'singlestep_fixed':
                Fixed order singlestep DPM-Solver (i.e. DPM-Solver-1 or singlestep DPM-Solver-2 or singlestep DPM-Solver-3).
                We use singlestep DPM-Solver-`order` for `order`=1 or 2 or 3, with total [`steps` // `order`] * `order` NFE.
            - 'adaptive':
                Adaptive step size DPM-Solver (i.e. "DPM-Solver-12" and "DPM-Solver-23" in the paper).
                We ignore `steps` and use adaptive step size DPM-Solver with a higher order of `order`.
                You can adjust the absolute tolerance `atol` and the relative tolerance `rtol` to balance the computatation costs
                (NFE) and the sample quality.
                    - If `order` == 2, we use DPM-Solver-12 which combines DPM-Solver-1 and singlestep DPM-Solver-2.
                    - If `order` == 3, we use DPM-Solver-23 which combines singlestep DPM-Solver-2 and singlestep DPM-Solver-3.

        =====================================================

        Some advices for choosing the algorithm:
            - For **unconditional sampling** or **guided sampling with small guidance scale** by DPMs:
                Use singlestep DPM-Solver or DPM-Solver++ ("DPM-Solver-fast" in the paper) with `order = 3`.
                e.g., DPM-Solver:
                    >>> dpm_solver = DPM_Solver(model_fn, noise_schedule, algorithm_type="dpmsolver")
                    >>> x_sample = dpm_solver.sample(x, steps=steps, t_start=t_start, t_end=t_end, order=3,
                            skip_type='time_uniform', method='singlestep')
                e.g., DPM-Solver++: