Advanced Prompting

In some cases you may want to create entirely new and unusual subjects.

That might be easy to prompt, but if you want to create something very similar to the subjects in the original dataset with a few very notably different characteristics, then longer prompts are useful.

Typically, when you’re using a generic model designed from Stable Diffusion, you need to add a lot of prompts to get a good result. That’s because the basic Stable Diffusion model is not finetuned or guided. When you prompt with a token it uses that information as a reference point in it’s inference process.

However, if you don’t have enough tokens, it needs to grab other points from latent space which can get strange results.

Finetuned models, or Generators, solve that problem by creating tokens with a lot of information baked in.

So, typically, you need fewer words.

The situations where you need longer prompts tend to be when you’re trying to direct your Generator a little further away from it’s finetuning.

The CLIP Interrogator is an excellent tool for identifying a good, long, base prompt.

It is useful when trying to emulate a general style while still avoiding copying an image.

It creates a point of reference that is removed from whatever image you put into the CLIP Interrogator.

You can try CLIP interrogator here

Updated on: 17/04/2023

Was this article helpful?

Thank you!