> For example Retro Diffusion worked pretty well for its era - no mixels, proper palettes, etc.
That's the wrong layer to tackle this problem. Or I should say: that's necessary, but not sufficient. Yes, the model should be trained to roughly generate something which looks like pixel art (i.e. with a concrete pixel size, reduced/consistent-ish palette, etc.), but enforcing that should be done deterministically in post-processing.
That's the wrong layer to tackle this problem. Or I should say: that's necessary, but not sufficient. Yes, the model should be trained to roughly generate something which looks like pixel art (i.e. with a concrete pixel size, reduced/consistent-ish palette, etc.), but enforcing that should be done deterministically in post-processing.