How to Master Full-Body Images in Midjourney

In this newsletter, read about:

• 🕵️‍♀️ Full-Body Characters in Midjourney

• 🗞 News and Top Reads

• 📌 AI Art Tutorial: Generative Fill in Photoshop

• 🎨 Featured Artist: Armed Shutter

• 🖼 AI-Assisted Artwork of the Week

• 🤓 How to Get Started with Generative AI?

🕵️‍♀️ Full-Body Characters in Midjourney

I've noticed that many AI creators face difficulties in generating full-body images using Midjourney. The tool seems to have a preference for half-body portraits, making it challenging to achieve desired results. Simply adding "full-body" to the prompt usually doesn't yield satisfactory outcomes.

After extensive research and personal experimentation, I've discovered five recommendations that work effectively in most cases. I'm excited to share them with you!

1. Add details about shoes or feet

Based on my experience, this trick has proven to be highly effective. By simply adding a few descriptive words like "black shoes," "dirty boots," or even "barefoot," all four images in the set generated by Midjourney turn out to be full-body portraits.

Interestingly, there are instances where Midjourney may not precisely adhere to the request. For example, you might end up with red shoes instead of black, or a long dress that covers the feet without showing the shoes. But still, the likelihood of obtaining a full-body image significantly increases.

If mentioning shoes or feet isn't relevant to your desired outcome, describing specific types of clothing can also be helpful. Consider mentioning very long garments that extend below the knees. For instance, I've found that using "evening gown" instead of simply "dress" often produces full-body characters without any additional tricks. Presumably, this is because a "dress" can be either short or long, and Midjourney doesn't necessarily require a full-body representation to convey that someone is wearing a dress. In contrast, an "evening gown" typically reaches the ground, prompting the generation of a full-body image.

2. Avoid facial details

Including excessive details about facial expressions or features in your prompt tends to shift the AI algorithm's focus solely on the face, reducing the likelihood of generating a full-body image. While general descriptions like "smiling" or "sad" are acceptable, specifying particular facial features becomes a hindrance.

To illustrate, take a look at how removing the mention of "green eyes" from the prompt below transformed the results from all half-body portraits to at least two out of four full-body images.

Notice that even with half-body portraits, the eye color is not clearly visible. It becomes even less relevant in the context of a full-body portrait.

3. Incorporate verbs that convey dynamism and action

Through my observations, I've discovered that certain verbs significantly enhance the likelihood of obtaining full-body images in the output. These verbs are typically associated with movement, such as "walking," "twirling," "dancing," and more. It seems that showcasing someone engaged in action becomes more feasible when their entire body is visible.

However, be careful when using the word "walking" in your prompts, as Midjourney has a tendency to depict the act of walking from a rear perspective, rather than showcasing the front view.

4. Create vertical images

If your goal is to obtain a full-body image of a single person, I recommend opting for a vertical image format, such as --ar 4:5, --ar 2:3, etc. Composing a visually pleasing horizontal image with a single full-body character is more challenging, and the AI algorithm simply tends to optimize by generating half-body portraits.

5. Place your character in a specific environment

Another effective trick is to provide a specific environment for the subject, such as a "futuristic room," "misty forest," or an "abandoned building with graffiti walls." Including even a brief description of the environment prompts Midjourney to allocate more space for the corresponding details, which in turn reduces the space dedicated to the figure. As a result, you are more likely to obtain a full-body portrait within the described environment.

I trust you will find these tips valuable! If there are any other challenges you or others face while using Midjourney, feel free to let me know by replying to this email (if you received this as a newsletter) or commenting on the post. I'll see if I can research the problem and suggest a few tips. As the field of AI image generation is still very new, sharing and collaborating are crucial for its ongoing development.

Happy prompting! 😃 

🗞 News and Top Reads

• Adobe Firefly, the widely popular AI image generator, is now accessible to everyone, who has Adobe Id.

  • Firefly's text-to-image tool is still behind Midjourney in terms of quality, but its exceptional user interface and user-friendly experience make up for it.

  • With Firefly, you can also test an array of other image-editing features, including generative fill, text effects, and generative recolor.

  • Furthermore, Firefly is coming into your favorite apps. Photoshop (beta) with generative AI features is already available for download.

• The Midjourney team is meeting up in San Francisco this week to discuss their web and app plans for the year.

  • Hooray!

  • Get ready for the upcoming launch of a dedicated website and standalone app for Midjourney's image generation – probably, later this year.

• OpenAI published a blog post, discussing the governance of Superintelligence, which refers to AI systems more capable than AGI. Here are three essential propositions put forward:

  • Collaborative efforts among leading AI developers should be prioritized to establish agreed-upon methods for the safe integration of superintelligence into society.

  • The establishment of an international authority, similar to IAEA, becomes imperative to conduct inspections of these advanced systems and enforce robust safety standards.

  • Emphasis should primarily be placed on minimizing the significant risks associated with these systems, rather than merely attempting to control them.

📌 AI Art Tutorial: Generative Fill in Photoshop

Learn the basics of Generative Fill which is now integrated into the Beta version of Adobe Photoshop. This technology allows you to write simple text prompts to enhance your own images directly in Photoshop. It is truly magical!

🎨 Featured Artist: Armed Shutter

Meet Armed Shutter, a talented photographer hailing from Nigeria and now residing in Texas. Driven by curiosity, he embarked on his photographic journey in 2017, and since then, his captivating work has graced the pages of various esteemed fashion publications. As generative AI emerged with its innovative tools for producing breathtaking photography, Armed eagerly embraced this opportunity, leveraging his expertise as a photographer to consistently achieve remarkable results. To witness more of Armed's awe-inspiring AI-generated images, visit @armedshutterai.

 If you want to recommend an artist to be featured in this newsletter, feel free to respond to this email with the links to the artist’s website or Instagram profile. Self-promotion is also allowed 😃 

🖼 AI-Assisted Artwork of the Week

🤓 How to Get Started with AI Art?

1. DALL-E: Creating Images from Text – introduction to text-to-image generation.

2. The DALL-E 2 Prompt Book – a guidebook by OpenAI that explains how to effectively right prompts to generate images across different domains (e.g., photography, illustration, art history, 3D artwork).

3. All-In-One Guide For Midjourney: The Art Of Prompts – a comprehensive guide on creating effective Midjourney prompts by Karol Andruszków.

4. Best Midjourney Prompts – a guide that covers the basics of Midjourney prompts (e.g., which keywords to use to create abstract art, surreal art, minimalism, etc) as well as some more advanced options (e.g., keywords related to camera lenses and filters, imitating certain artists and photographers without using their names). Finally, they provide a list of 600+ creative text prompts for image generation.

5. Stable Diffusion Prompt Book – a prompt book prepared by OpenArt. The book discusses ideal prompt format, using modifiers to change the style, format, or perspective of the image, applying ”magic words” to improve image quality, adding negative prompts, and adjusting Stable Diffusion parameters.

Share Kiki and Mozart

If you like this newsletter and know somebody who might also like it, feel free to share this newsletter. Let’s have more people learn about AI art!

If you have been forwarded this email and you like it, please subscribe below. And welcome to the world of AI art!