Prompt Part 2

Going Beyond the Basics

In Part 1 of our Prompt-Crafting Guide, we covered the absolute essentials – the building blocks of a prompt, how to structure one effectively, and the basics to kickstart your creative journey.

Now, in Part 2, we're diving into a slightly more advanced technique that's crucial for any prompter: adding emphasis or attention to specific tokens in your prompt. This skill lets us highlight or de-emphasize certain elements, giving us control over the final image that AI generates.

Mastering the art of emphasis can significantly enhance the precision and impact of our artworks.


Boosting or Diminishing Attention

The way we emphasize tokens can vary depending on the platform or interface you're using for your art creation. However, when working with Automatic1111's Web UI or's On-Site Generator (among others), the syntax follows a standard format.


  • To make a model pay more attention to specific tokens, use parentheses ( ). 
  • Conversely, to reduce a model's attention to a token, employ square brackets [ ]. 
  • This syntax, which has been the original method of emphasis, is still widely used (and quite effective!) in most Stable Diffusion interfaces.
  • The more parentheses we use around a token, the greater the attention it receives. You can include parentheses and square brackets up to four times, like this: (((( )))) or [[[[ ]]]].

The table below explains precisely how much each set of parentheses or square brackets increases or decreases attention:



Demonstrating the Power of Emphasis

In this extreme example, we showcase the profound impact of emphasis on an image. We take the word "stars" as our token and demonstrate how we can decrease its significance, reducing the prevalence of stars in the first image. Conversely, we dramatically increase the number and prominence of stars, both in the background and foreground, in the second image.



Token Weighting

Token Weighting works on exactly the same principle as the parenthesis emphasis syntax, but is a later addition to Stable Diffusion interfaces, and is far more common to see in prompts, having become the de-facto standard.

A token is weighted with the syntax (token:n.n), n being the desired factor of attention. Generally, when weighting tokens, we stay within the (token:0.5) to (token:1.6) range, as higher and lower values may produce unexpected results in our images!

Finding the “correct” Weight for a particular image requires trial and error, but it largely boils down to personal preference for particular features in the image.

The following table shows the syntax and the effect upon the token;



Examples of Token Weighting in Prompts

The following examples show the progression from a very low weight (moonlight:0.3) to an extremely high weight (moonlight:1.7), with the effect it has on our image output being immediately apparent;



Token Weighting for LoRA

You’ll often see Weights wrapping LoRA names in prompt, as Weighting is a fantastic way of adjusting the strength of a LoRA in our images. Often, LoRA are very “strong” and can overpower our prompt, or produce visual artifacts and undesirable details. To combat this, it’s common practice to reduce the strength of a LoRA to between 0.6 and 0.8.

This will vary from LoRA to LoRA, so testing and experimentation is required!

The example below shows the effect of a high powered LoRA, vs a slightly down-weighted LoRA , which produces a much more coherent and natural result.


Tips & Tricks

It’s best not to combine the two methods of weighting! It’s confusing to read, and they may conflict!

In many interfaces, selecting a word and using the CTRL + UP ARROW, or DOWN ARROW, will automatically increase the Weight of the selected word by 0.1.

Specifying Weight only works with ( ). You cannot use the syntax [token:n.n]


In this guide we’ve looked at an essential aspect of prompting, but there are many, many, advanced prompting techniques, syntax, tips and tricks, which we’ll cover in the final prompt-crafting guide!