Discover how to use multi-prompts effectively with the Midjourney Bot, which allows you to separate concepts and assign importance to different parts of a prompt. In this comprehensive guide, you will learn about multi-prompt basics, prompt weights, negative prompt weights, and the
With the Midjourney Bot, you can separate concepts in a prompt using the double colon
::. For example, the prompt
hot dog produces images of tasty hotdogs, but separating the concepts using
hot:: dog creates a picture of a warm dog. Multi-prompts work with various model versions and parameters, which can be added at the end of the prompt.
hot dog hot:: dog
You can assign relative importance to different parts of a multi-prompt using weights. For example,
hot::2 dog makes the word "hot" twice as important as the word "dog," producing an image of a very hot dog. The weight can be a whole number or a decimal depending on the model version.
hot:: dog hot::2 dog
You can also use negative weights in multi-prompts to remove unwanted elements from the generated image. For instance,
vibrant tulip fields:: red::-.5 reduces the likelihood of red tulips in the image.
vibrant tulip fields vibrant tulip fields:: red::-.5
It is possible to combine both positive and negative weights with the
--no parameter for more refined control over the output of your Midjourney Bot. This can help achieve a more desirable balance of elements in your generated images.
--no parameter is equivalent to a negative weight of -0.5. Therefore, using
--no and a negative weight in the same prompt might produce unexpected results. It's best to use one or the other for a more predictable outcome.