So we're using a color space that has two channels dedicated entirely to color, which is the only thing the model needs to learn.
The model doesn't need to touch the lightness channel at all, only predict the noised added to the color channels at train time.
At inference time, we start with a real lightness channel (b/w image), and initialize the color channels to random noise. The model iteratively denoises the color channels while keeping the lightness channel locked.
The model doesn't need to touch the lightness channel at all, only predict the noised added to the color channels at train time.
At inference time, we start with a real lightness channel (b/w image), and initialize the color channels to random noise. The model iteratively denoises the color channels while keeping the lightness channel locked.