In the paper, CLASSIFIER-FREE DIFFUSION GUIDANCE, epsilont = (1 + w)epsilonθ(zt, c) - wepsilonθ(zt).
But, codes's epsilont = lerp(epsilonθ(zt), epsilonθ(zt, c), w) = (1 - w)*epsilonθ(zt) + epsilonθ(zt, c)?
Am I right? Are those two the same?
Just a issue.
dome272
commented
1 year ago
In the paper, CLASSIFIER-FREE DIFFUSION GUIDANCE, epsilont = (1 + w)epsilonθ(zt, c) - wepsilonθ(zt). But, codes's epsilont = lerp(epsilonθ(zt), epsilonθ(zt, c), w) = (1 - w)*epsilonθ(zt) + epsilonθ(zt, c)? Am I right? Are those two the same? Just a issue.