Understanding classifier-free guidance for style transfer

I wrote this post because I wanted to know what effect one of the main latent diffusion model parameters -- the classifier guidance scale (cfg_scale) -- was having on the sampling process.<p>As well as smoothly varying the cfg_scale, I think it would be fascinating to do some mechanistic interpretability on latent diffusion models. Something like the microscope tool OpenAI used to have for convnets: <a href="https:&#x2F;&#x2F;microscope.openai.com&#x2F;models" rel="nofollow">https:&#x2F;&#x2F;microscope.openai.com&#x2F;models</a>

This is a really cool blogpost - that you can influence a model with guidance towards a desired outcome feels like a really valuable feature. I&#x27;m currently working on a project that is generating stable diffusion images and this kind of technique would be so useful ;-)

I&#x27;m curious what initial results you got when training only on 6 images. Were generated images not Wildsmith-ish enough?

It&#x27;s pretty wild how much value Automatic1111 webuid enabled to create.

I thought this was cool because it&#x27;s very different from the usual anime crap<p>And you can see how smoothly varying the math produces these varying images in response to the prompt