DDPM interpolation formula error

[jjjuuuun]

annotated_deep_learning_paper_implementations/labml_nn/diffusion/ddpm/evaluate.py

Line 138 in a0679ec

$$\bar{x}_t = (1 - \lambda)x_t + \lambda x'_0$$

I know how to interpolate by interpolating in the diffused space and then sending it back to the original space. That's why I think the notation is wrong. Please check it.

Interpolation to

$$\bar{x}_t = (1 - \lambda)x_t + \lambda x'_t$$

and then

$$\bar{x}_0 \sim p(x_0 | \bar{x}_t)$$