Build a resized Embedding Module from a provided token Embedding Module. Increasing the size will add newly initialized vectors at

Build a resized Embedding Module from a provided token Embedding Module. Increasing the size will add newly initialized vectors at

Create a 1D, 2D, or 3D average pooling module.

Wrapper for grid_sample, uses pixel coordinates

Finds the python object with the given name and calls it as a function.

Photometric augmentation

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

Converts the Lora from multiple pytorch .pt files into a single safetensor file. modelmap is a dictionary of { "module name": (p

r""" Returns:

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`

encode frame by frame

Occlusion augmentation

Applies the flow color wheel to (possibly clipped) flow components u and v. According to the C++ source code of Daniel Scharstein Accord

Estimate optical flow between pair of frames

get learnable params

get learnable params

get learnable params