Flux conditional flow implementation

Hi, I'm trying to figure out how Flux LoRA is trained.
According to the paper: https://arxiv.org/abs/2210.02747 (eq. 22), I guess that conditional flow should be implemented as follows: `x_t = t * x_1 + (1 - t) * x_0`, where `x_0` is sampled from Gaussian distribution and `x_1` represents data.

But current implementation: `noisy_model_input = (1 - t) * latents + t * noise` [(code)](https://github.com/kohya-ss/sd-scripts/blob/0047bb1fc30a9987138a20f52f774ca536ff7b6a/library/flux_train_utils.py#L397)
that I believe corresponds to `x_t = (1 - t) * x_1 + t * x_0`

Can you explain please where am I wrong?

Start with equation 22 in the linked paper and the implementation at library/flux_train_utils.py line 397. Compare the definitions of t, latents, and noise in the surrounding training flow; the investigation is complete when the apparent parameter-order discrepancy is explained or a concrete implementation correction is identified.

Written by the indexing model from the issue text.