Yeah, and InvokeAI has a similar "IP-adapter" model.
Still, even with it turned off, the quality is quite remarkable.
Still, even with it turned off, the quality is quite remarkable.
Ip adapter uses an image to guide denoising.
Fooocus and MJ take a prompt and expand it in a variety of ways (eg a language model or more simplistic text manipulation). The actual prompt that creates the conditioning is not what you typed in. That’s what I mean by prompt massaging