shap_e/diffusion/k_diffusion.py [240:266]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    denoiser,
    x,
    sigmas,
    progress=False,
    s_churn=0.0,
    s_tmin=0.0,
    s_tmax=float("inf"),
    s_noise=1.0,
):
    """Implements Algorithm 2 (Heun steps) from Karras et al. (2022)."""
    s_in = x.new_ones([x.shape[0]])
    indices = range(len(sigmas) - 1)
    if progress:
        from tqdm.auto import tqdm

        indices = tqdm(indices)

    for i in indices:
        gamma = (
            min(s_churn / (len(sigmas) - 1), 2**0.5 - 1) if s_tmin <= sigmas[i] <= s_tmax else 0.0
        )
        eps = th.randn_like(x) * s_noise
        sigma_hat = sigmas[i] * (gamma + 1)
        if gamma > 0:
            x = x + eps * (sigma_hat**2 - sigmas[i] ** 2) ** 0.5
        denoised = denoiser(x, sigma_hat * s_in)
        d = to_d(x, sigma_hat, denoised)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



shap_e/diffusion/k_diffusion.py [284:310]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    denoiser,
    x,
    sigmas,
    progress=False,
    s_churn=0.0,
    s_tmin=0.0,
    s_tmax=float("inf"),
    s_noise=1.0,
):
    """A sampler inspired by DPM-Solver-2 and Algorithm 2 from Karras et al. (2022)."""
    s_in = x.new_ones([x.shape[0]])
    indices = range(len(sigmas) - 1)
    if progress:
        from tqdm.auto import tqdm

        indices = tqdm(indices)

    for i in indices:
        gamma = (
            min(s_churn / (len(sigmas) - 1), 2**0.5 - 1) if s_tmin <= sigmas[i] <= s_tmax else 0.0
        )
        eps = th.randn_like(x) * s_noise
        sigma_hat = sigmas[i] * (gamma + 1)
        if gamma > 0:
            x = x + eps * (sigma_hat**2 - sigmas[i] ** 2) ** 0.5
        denoised = denoiser(x, sigma_hat * s_in)
        d = to_d(x, sigma_hat, denoised)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -