Guide to Prompts for Midjourney V5 with ChatGPT-4

I have designed a text prompt for ChatGPT-4 that helps create efficient text prompts for Midjourney V5 based on various concepts and ideas. Below is the text prompt that I utilized in ChatGPT-4:

Can you assist me in generating good text prompts for an AI text-to-image software known as Midjourney? Here’s a guide to Midjourney, as well as a prompt guide:

Midjourney is an AI text-to-image generator that aims to ‘explore new mediums of thought and expand the imaginative powers of the human species.’ You can input a worded prompt for an image, such as ‘a fox wearing a top hat in the style of a Roald Dahl illustration.’ In a few seconds, you’ll receive multiple attempts at this image in the form of a 4×4 image grid.

Midjourney has been taught the relationship between an image and the text used to describe it. The team behind Midjourney has recently released its fifth iteration (V5), which offers higher image quality, wider stylistic range, more diverse outputs, better image promoting, support for seamless textures, and dynamic range.

To utilize Midjourney V5, add the –v five parameter to the end of a prompt. This model has high coherency and excels at interpreting natural language prompts. It is also higher resolution and supports advanced features like –stylize, –chaos, and aspect ratios.

To generate something other than a photographic image, you can reference art movements, artistic techniques, genres, media types, game titles, directors, artist names, influences, periods, etc. To invoke the aesthetic style of an image, try referencing two or more of these:

  • Art movement: Identifying the art movement in the prompt will introduce its style and techniques. Examples include Impressionism, Surrealism, and Pop Art.
  • Media type: Identifying the medium of an image will determine its aesthetic. Examples include photography, illustration, comics, concept art, storyboard, sculpture, etc.
  • Media title: Identifying a media influence will influence its look. For example, from Spirited Away, The Wizard of Oz, Sid Meier’s Civilization, or the video game Joust.
  • Artist name: Referencing a specific artist’s name or work will roughly invoke their unique style. Examples include Vincent van Gogh, Frida Kahlo, and Banksy.
  • Technique: Referencing techniques will add that style to the image. Examples include impasto, pencil sketch, watercolor, or digital art.
  • Period: Identifying the historical context of an image will invoke its aesthetic. For example, images from the Renaissance, Baroque, or Modernist periods.
  • Geographic location: Referencing regions and countries will influence style. Examples include Japanese Ukiyo-e prints, African tribal art, and American Abstract Expressionism.
See also  How To Translate text with ChatGPT Translator

The –aspect or –ar parameter changes the aspect ratio of the generated image. The aspect ratio is the width-to-height ratio of an image and is typically expressed as two numbers separated by a colon, such as 7:4 or 4:3. The default aspect ratio is 1:1.

Add –aspect: or-ar: to the end of your prompt to use aspect ratios. The aspect ratio impacts the shape and composition of a generated image.

The parameter –chaos or –c affects the variability of the initial image grids in Midjourney V5. A higher –chaos value leads to more unique and unexpected compositions, while a lower value results in more consistent and repeatable images.

The default value for –chaos is 0, and you can use values between 0 and 100 by adding –chaos or –c to the end of your prompt. Higher –chaos values generate more diverse and surprising styles for each square in the grid, similar to having multiple artists working on the prompt. If you prefer fewer surprising details in your grid, set –chaos to 0 or specify in the prompt what you want from Midjourney.

The parameter –stylize or –s determines how much Midjourney applies its training in artistic color, composition, and forms to the generated images. A low –stylize value produces images that closely match the prompt but are less artistic, while a high value creates highly artistic but less connected images.

The default value for –stylize is 100, and you can use values between 0 and 1000 by adding –stylize or –s to the end of your prompt.

If you want to generate prompts using Midjourney V5, you can provide ideas or concepts, and I can help you create a corresponding prompt using the parameters mentioned above.

See also  Google Bard vs. ChatGPT vs. Bing Chat vs Claude 2: Which is Better?
Mohamed SAKHRI
Mohamed SAKHRI

I'm the creator and editor-in-chief of Tech To Geek. Through this little blog, I share with you my passion for technology. I specialize in various operating systems such as Windows, Linux, macOS, and Android, focusing on providing practical and valuable guides.

Articles: 1725

Newsletter Updates

Enter your email address below and subscribe to our newsletter

Leave a Reply

Your email address will not be published. Required fields are marked *