Creating Stunning Portraits with Midjourney & ChatGPT

In this newsletter, read about:

• 🕵️‍♀️ High-quality photo portraits in Midjourney

• 🗞 News and Top Reads

• 📌 AI Art Tutorial: Blending Images in Midjourney

• 🎨 Featured Artist: YZA Voku

• 🖼 AI-Assisted Artwork of the Week

• 🤓 How to Get Started with Generative AI?

🕵️‍♀️ High-Quality Photo Portraits in Midjourney

Last week, we started our experiments with ChatGPT as Midjourney prompt generator. Today, I decided to continue these experiments with a focus on frontal photo portraits.

Getting a stunning photo portrait requires extensive photographic experience and outstanding skills. Is it possible to achieve similar results with Midjourney?

V5 of this AI image generator is extremely good at creating photorealistic and even hyperrealistic images. If we combine the superpowers of Midjourney with the remarkable linguistic skills of ChatGPT, we can get high-quality portraits generated from creative and extensive prompts, suggested by ChatGPT under our human direction and supervision. Let’s start!

Styles of Portrait Photography

I don’t have much experience with professional photography. So, I’ve started by asking ChatGPT to list different styles of portrait photography. Here’re the ones it listed:

1.  Traditional or Classical Portraiture: Focuses on capturing the subject's face and personality, often with simple backgrounds and straightforward poses.

2. Environmental Portraiture: Captures the subject in their natural environment or surroundings, providing context and storytelling elements.

3. Candid or Lifestyle Portraiture: Captures the subject in spontaneous, unposed moments, often highlighting their genuine emotions and expressions.

4. Glamour or Fashion Portraiture: Focuses on the subject's appearance, styling, and fashion elements, often with a more stylized and dramatic approach.

5. Fine Art Portraiture: Combines artistic expression with portrait photography, often using unique concepts, lighting, and post-processing techniques.

6. Conceptual Portraiture: Tells a story or conveys a message through the use of symbolic elements, props, and creative styling.

7. Editorial Portraiture: Captures portraits for publications, often focusing on storytelling or illustrating a specific theme or topic.

8. Black and White Portraiture: Uses the absence of color to emphasize the subject's features, expressions, and emotions, often resulting in a timeless and classic appearance.

Great! The styles are listed together with explanations, which can be very handy for inexperienced photographers. ChatGPT also noted that these are just a few examples, and many photographers may blend or experiment with multiple styles to create their unique approach to portrait photography.

Today I want to start with the basics to see how Midjourney can recreate these eight styles for a variety of men's and women's portraits.

Male Portraits

To get Midjourney prompt ideas from ChatGPT, I continued my last week’s conversation with the bot, where I trained it to write formatted Midjourney prompts.

Now I can simply provide some general idea about what I want to be depicted on the image and ChatGPT adds details and outputs a prompt, ready to be copied to Midjourney.

The first prompts suggested by ChatGPT resulted in nice Midjourney images, but there was too much of a background focus, while I was looking for a frontal photo portrait.

So, after some back and forth, I’ve decided to remove all the details unrelated to a person’s face from the prompt. And here’s the result:

Time to experiment with different styles! Here are images generated from the same prompt, except for replacing lifestyle photography with fine art photography and glamour or fashion photography, respectively.

The right one definitely looks more glamour 😆 

Female Portraits

To try other portrait styles, I’ve switched to female portraits. First, a traditional portrait was generated with the following prompt:

This prompt was suggested by ChatGPT based on my general idea of a traditional frontal photo portrait of an attractive woman. However, lots of details here are applicable to traditional portraits only. So, for other portrait styles, I’ve chosen a more general prompt:

The difference is quite notable here. And what about fashion photography vs editorial photography?

The images are very similar in this case, but you can notice more makeup in the first image, probably thanks to glamour in the prompt 😃 

To add some diversity to my photo portrait gallery, I’ve explicitly prompted ChatGPT and then Midjourney for images of Black and Asian women.

Here are the prompts for the portraits of Black women, as suggested by ChatGPT and adjusted by me.

You can clearly notice the difference in the style of these two images. I love both versions, but Fine Art one is my favorite here.

Finally, here are the prompts, generated with the help of ChatGPT for the photo portraits of Asian women.

I love the Black and White photo here! Which one is your favorite?

Midjourney & Photo Portraits

As you can see, Midjourney offers remarkable quality when it comes to photo portraits. I’ve just touched the surface here, while the opportunities for experiments are endless:

• choose your own topics and subjects,

• leverage ChatGPT for brainstorming ideas and extending your prompts,

• experiment with different photo styles,

• add more photo-related keywords (e.g, camera lens, focus), and

• get your unique and high-quality photo portraits.

I’m currently working on a Midjourney Prompt Guide, where I plan to share 100+ prompts and images across different subjects and styles. If you are not yet subscribed to this newsletter, make sure to subscribe as I will share this guide with my subscribers for free as soon as it’s ready.

Happy prompting!

🗞 News and Top Reads

• Midjourney is testing its new AI Moderator system.

  • The goal is to achieve an almost 100% chance of getting innocent prompts through.

  • First, fast AI is used to review all queries. If this system bans your query, you have the option to appeal, and your query will be sent to a larger, smarter, and more powerful AI. It can process words in context, and thus, is more likely to allow innocent prompts with “suspicious” words.

• A new style “scenic” was introduced to the anime-themed Midjourney model Nijijourney.

  • It is meant for creating beautiful backgrounds and environments for the characters.

  • To use it first enable Niji v5 with /settings and then choose your style with --style scenic.

• Stability AI released a new open-source language model, StableLM.

  • The advances of Stability AI in natural language processing might potentially have an impact on the performance of Stable Diffusion models.

  • If developers decide to follow the Midjourney path, Stable Diffusion might get better at processing full-text prompts or they might introduce something similar to the /desribe function in Midjourney.

📌 AI Art Tutorial: Blending Images in Midjourney

If you ever tried to experiment with the /blend command in Midjourney, you have probably noticed that the output images are usually not that good and include many noticeable artifacts. In this tutorial, Christian Heidorn introduces two unconventional but effective methods for blending images in Midjourney. The results are amazing!

🎨 Featured Artist: YZA Voku

YZA Voku is a photographer and designer from Madrid, Spain. The artist develops photography, digital art, design and video projects, offering a suggestive approach that transmits nostalgia, reverie, reminiscent of filmic narrative. See more of the artist’s works @yzavoku.

🖼 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. 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.

4. 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!