You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
The classifier-free guidance equation of diffusion models here is wrong, which is $$\epsilon_\theta(x_t, c) = s\epsilon_\text{cond}(x_t, c) + (s - 1)\epsilon_\text{cond}(x_t, c_u).$$
However, the correct equation is given in the Imagen paper, Section 2.2, Equation (2), as $$\epsilon_\theta(x_t, c) = s\epsilon_\text{cond}(x_t, c) + (1 - s)\epsilon_\text{cond}(x_t, c_u).$$
The code here implements the correct equation, though. So there should be no need to fix the code.
I believe all the sampling articles such as this and this use the wrong equation, so they should also be corrected.
The text was updated successfully, but these errors were encountered:
The classifier-free guidance equation of diffusion models here is wrong, which is
$$\epsilon_\theta(x_t, c) = s\epsilon_\text{cond}(x_t, c) + (s - 1)\epsilon_\text{cond}(x_t, c_u).$$
$$\epsilon_\theta(x_t, c) = s\epsilon_\text{cond}(x_t, c) + (1 - s)\epsilon_\text{cond}(x_t, c_u).$$
However, the correct equation is given in the Imagen paper, Section 2.2, Equation (2), as
The code here implements the correct equation, though. So there should be no need to fix the code.
I believe all the sampling articles such as this and this use the wrong equation, so they should also be corrected.
The text was updated successfully, but these errors were encountered: