Classifier Free Guidance
Révision datée du 10 janvier 2023 à 14:23 par Jboscher (discussion | contributions) (Page créée avec « By default, the model doesn't often do what we ask. If we want it to follow the prompt better, we use a hack called CFG. There's a good explanation in this video (AI coffee break GLIDE). In the code, this comes down to us doing: noise_pred = noise_pred_uncond + guidance_scale * (noise_pred_text - noise_pred_uncond) This works suprisingly well :) Explore changing the guidance_scale in the code above and see how this affects the results. How high can you push it be... »)
By default, the model doesn't often do what we ask. If we want it to follow the prompt better, we use a hack called CFG. There's a good explanation in this video (AI coffee break GLIDE). In the code, this comes down to us doing: noise_pred = noise_pred_uncond + guidance_scale * (noise_pred_text - noise_pred_uncond) This works suprisingly well :) Explore changing the guidance_scale in the code above and see how this affects the results. How high can you push it before the results get worse?