ml-recall

#guidance

2 questions from Diffusion Models

Timed test

2 questions · 2 min · score and explanations at the end

Take a test

Q 1 / 2Score 0 / 0

Shuffle questions

Question 1: Short answer

mediumAI-checkedDiffusion Models

Classifier-free guidance combines the conditional and unconditional noise predictions of one network as $\tilde\epsilon = (1+w)\,\epsilon_\theta(z, c) - w\,\epsilon_\theta(z)$ . At one pixel, $\epsilon_\theta(z, c) = 0.6$ and $\epsilon_\theta(z) = 0.2$ . What is $\tilde\epsilon$ for the guidance strength $w = 3$ ?

Enter: check / next