Yu He

Hi, leffff, I'm confused about this part: ```python def add_noise(original_samples: torch.Tensor, noise: torch.Tensor, timestep: torch.Tensor) -> torch.Tensor: """ Add noise to the given sample Args: original_samples (`torch.Tensor`): The original sample...

> The thing is its the same xt=t∗x1+(1−t)∗x0 with target=x1−x0 and xt=(1−t)∗x1+t∗x0 with target=x0−x1 For proof https://github.com/leffff/InstructFlow look at the generations in the readme file) $x_t=t∗x_1+(1−t)∗x_0$ and $x_t=(1−t)∗x_1+t∗x_0$ are equivalent...