Compute lambda_t = log(alpha_t) - log(sigma_t) of a given continuous-time label t in [0, T].

Compute sigma_t of a given continuous-time label t in [0, T].

Compute log(alpha_t) of a given continuous-time label t in [0, T].

Convert the model to the noise prediction model or the data prediction model.

Compute the intermediate time steps for sampling. Args: skip_type: A `str`. The type for the spacing of the time steps. We suppor

Compute the continuous-time label t in [0, T] of a given half-logSNR lambda_t.

Compute alpha_t of a given continuous-time label t in [0, T].

DPM-Solver-1 (equivalent to DDIM) from time `s` to time `t`. Args: x: A pytorch tensor. The initial value at time `s`.

Expand the tensor `v` to the dim `dims`. Args: `v`: a PyTorch tensor with shape [N]. `dim`: a `int`. Returns: a

Extract some coefficients at specified timesteps, then reshape to [batch_size, 1, 1, 1, 1, ...] for broadcasting purposes.

Singlestep solver DPM-Solver-2 from time `s` to time `t`. Args: x: A pytorch tensor. The initial value at time `s`.

添加水印，然后保存图片

Return the data prediction model (with corrector).

生成mark图片，返回添加水印的函数

Convert the continuous-time `t_continuous` (in [epsilon, T]) to the model input time. For discrete-time DPMs, we convert `t_continuou

A piecewise linear function y = f(x), using xp and yp as keypoints. We implement f(x) in a differentiable way (i.e. applicable for autograd).

Multistep DPM-Solver with the order `order` from time `t_prev_list[-1]` to time `t`. Args: x: A pytorch tensor. The init

Return the noise prediction model.

Compute the sample at time `t_end` by DPM-Solver, given the initial `x` at time `t_start`. =========================================

Singlestep solver DPM-Solver-3 from time `s` to time `t`. Args: x: A pytorch tensor. The initial value at time `s`.

Compute the gradient of the classifier, i.e. nabla_{x} log p_t(cond | x_t).

裁剪图片边缘空白

Denoise at the final step, which is equivalent to solve the ODE from lambda_s to infty by first-order discretization.

The adaptive step size solver based on singlestep DPM-Solver. Args: x: A pytorch tensor. The initial value at time `t_T`

Get the order of each step for sampling by the singlestep DPM-Solver. We combine both DPM-Solver-1,2,3 to use all the function evalu

The noise predicition model function that is used for DPM-Solver.

Create a wrapper function for the noise prediction model. DPM-Solver needs to solve the continuous-time diffusion ODEs. For DPMs trained on discr

Multistep solver DPM-Solver-2 from time `t_prev_list[-1]` to time `t`. Args: x: A pytorch tensor. The initial value at t

Multistep solver DPM-Solver-3 from time `t_prev_list[-1]` to time `t`. Args: x: A pytorch tensor. The initial value at t

Compute y_noisy according to (6) p15 of [2]

设置水印透明度

Singlestep DPM-Solver with the order `order` from time `s` to time `t`. Args: x: A pytorch tensor. The initial value at

* `n_channels` is the number of dimensions in the embedding

* `in_channels` is the number of input channels * `out_channels` is the number of input channels * `time_channels` is the

* `image_channels` is the number of channels in the image. $3$ for RGB. * `n_channels` is number of channels in the initial feature

Create a wrapper class for the forward SDE (VP type). *** Update: We support discrete-time diffusion models by implementing a picewis

Construct a DPM-Solver. We support both DPM-Solver (`algorithm_type="dpmsolver"`) and DPM-Solver++ (`algorithm_type="dpmsolver++"`).

Compute the noised input xt = alpha_t * x + sigma_t * noise. Args: x: A `torch.Tensor` with shape `(batch_size, *shape)

The dynamic thresholding method.

* `x` has shape `[batch_size, in_channels, height, width]` * `t` has shape `[batch_size, time_channels]`

* `x` has shape `[batch_size, in_channels, height, width]` * `t` has shape `[batch_size]`

Algorithm 2.

Inverse the sample `x` from time `t_start` to `t_end` by DPM-Solver. For discrete-time DPMs, we use `t_start=1/N`, where `N` is the t

在im图片上添加水印 im为打开的原图