Advanced Midjourney V6 Guide (Pushing Boundaries of Lifelike Cinematic AI Photography)

23 Dec 202330:00

TLDRThis comprehensive video guide introduces viewers to the advanced features of Midjourney V6, a cutting-edge AI photography tool. The host provides an in-depth comparison between V6 and its predecessor, highlighting the improvements in natural language understanding, photorealism, and detail accuracy. Through a structured prompt system, users can create highly realistic and detailed images by defining their creative direction at three levels: organism, molecules, and atoms. The guide also explores various photography types, camera angles, lighting techniques, and fashion styles that can be incorporated into prompts for more nuanced and expressive AI-generated photos. The video concludes with a demonstration of the new text-on-image feature, offering yet another creative tool for users to enhance their AI photography.


  • πŸŽ₯ **Midjourney V6 Introduction**: The video provides an in-depth guide to using Midjourney V6 for creating photorealistic and cinematic AI photos.
  • πŸ” **Version Comparison**: A structured comparison is made between Midjourney V6 and V5, focusing on aesthetics, natural language understanding, photorealism, accuracy of details, and image-to-image prompt performance.
  • 🌟 **Improvements in V6**: V6 demonstrates significant improvements in natural language understanding, allowing for nuanced prompt interpretation and better character rendering.
  • πŸ“Έ **Photorealism Enhancement**: V6 produces more realistic and detailed images, with notable enhancements in skin realism and a less 'airbrushed' feel compared to V5.
  • πŸ”Ž **Detail Accuracy**: V6 shows a high improvement score in rendering detailed elements such as hands, objects, and faces in crowded scenes.
  • πŸ–ΌοΈ **Image Prompt Performance**: While V6 has better overall performance, V5 outperformed in maintaining resemblance to an original image in a specific test.
  • πŸ“ **Prompting Structure**: V6 allows for a simplified and more effective prompting structure, reducing the need for 'junk words' and enabling more detailed creative direction.
  • πŸŒ„ **Photography Types**: The video explores various photography types supported by V6, from portrait to food photography, each with its unique characteristics and applications.
  • 🎨 **Fashion and Style**: V6 offers advanced capabilities for describing fashion styles and outfits, allowing for greater specificity and creativity in fashion photography.
  • 🀌 **Hand Expressions**: The new version has improved the depiction of hand expressions and positions, adding more expressiveness to the AI-generated photos.
  • ✍️ **Text on Images**: A new feature in V6 is the ability to add text to images, which is particularly useful for product photography and enhancing the narrative of the image.
  • πŸ‘ **Viewer Engagement**: The video concludes by encouraging viewers to engage with the content through likes and subscriptions for further tutorials on AI photo and film creation.

Q & A

  • What is the main focus of the video?

    -The video provides a comprehensive guide on creating photorealistic cinematic AI photos using the recently launched mid Journey version 6, highlighting the differences and improvements over version 52.

  • How can one access mid Journey V6 on Discord?

    -To access mid Journey V6 on Discord, you need to use the slash settings command. Although V6 will be the default model in January, until then, it has to be turned on manually.

  • What are the key improvements in mid Journey V6 over V5?

    -Mid Journey V6 has significant improvements in natural language understanding, photorealism, accuracy of details, and image prompting. It also has a more nuanced rendering of characters and objects in response to prompts.

  • How does the simplified prompting structure for V6 help in storytelling with AI?

    -The simplified prompting structure for V6 allows for a more detailed and precise definition of the desired art, enabling users to organize components of their prompt into levels of organism, molecules, and atoms, which helps in fully understanding and directing the creative vision.

  • What are some of the photography types that can be explored with mid Journey V6?

    -Mid Journey V6 can be used to explore a wide range of photography types including portrait, street, product, fashion, documentary, architectural, landscape, food, still life, low-fi, fantasy, macro, whimsical, highkey, lowkey, wildlife, sports, aerial, infrared, night, and underwater photography.

  • How does V6 handle fashion and style in AI photography?

    -V6 takes fashion and style to the next level by allowing users to describe specific combinations of outfits, including tops, bottoms, footwear, and accessories. It also enables the replication of distinctive fashion styles and the inclusion of iconic fashion brands in the prompts.

  • What is the new feature introduced in V6 that allows for additional creative control?

    -One of the latest features introduced in V6 is the ability to write text on the images. This can be particularly useful for product photography or any scenario where text integration is desired.

  • How does V6 improve the rendering of hands and facial expressions in AI photos?

    -V6 shows significant improvement in rendering hands and facial expressions, providing a more accurate and expressive depiction of emotions and actions in the generated AI photos.

  • What is the significance of the 'ERs' in the prompt structure for V6?

    -The 'ERs' in the prompt structure for V6 stands for organism, molecules, and atoms, which are used to organize and define the components of the prompt. This structure allows for a more detailed and precise communication of the creative direction to the AI.

  • How can one enhance the retro look of AI photos using V6?

    -To enhance the retro look of AI photos using V6, one can add keywords related to specific years, decades, or eras, as well as film stocks with retro features like Kodak, Portra, or Fujifilm. This helps in achieving the desired vintage aesthetic.

  • What are some of the motion keywords that can be used to impact the image in V6?

    -Motion keywords that can be used in V6 to impact the image include 'motion blur', 'motion trail', and 'Phantom high-speed camera'. These keywords help in indicating motion and can significantly change the vibe of the image.

  • How does V6 handle the challenge of rendering world knowledge and well-known characters?

    -V6 does a good job of rendering world knowledge and well-known characters, as demonstrated by its attempt to create a realistic cyberpunk version of a character from the Demon Slayer universe. It shows an improved ability to maintain the character's original features while integrating new elements.



🎨 Introduction to Midjourney V6 for AI Photography

This paragraph introduces the video's focus on creating photorealistic AI images using Midjourney V6, the latest model for AI photography. It discusses the differences between V6 and its predecessor, V5, and outlines the improvements and new features. The video promises to explore storytelling with AI, simplified prompting structures, and a visual style guide. It also explains how to activate V6 on Discord and emphasizes the need for a structured comparison between the two versions for various photography aesthetics, including natural language understanding, coherence, photorealism, and accuracy of details.


πŸ“Έ Photorealism and Detail Accuracy in V6

The second paragraph delves into the photorealism challenge, comparing the outputs of V6 and V5 across different prompts designed to maximize photorealism. It highlights the significant improvements in skin realism and the reduction of the 'airbrushed' look from V5 in V6's images. The paragraph also addresses the accuracy of details, such as the depiction of hands, objects, and faces in crowded scenes, noting that V6 has made substantial improvements in these areas, although there is still room for enhancement. The discussion includes the use of specific prompts to test the models and the results of these tests.


πŸŒ„ Exploring Various Photography Genres with V6

This paragraph explores the wide spectrum of photography types that can be utilized with Midjourney V6, from portrait and street photography to product and fashion photography. It discusses how V6 can capture different styles, such as documentary, architectural, landscape, food, still life, low-fi, fantasy, macro, whimsical, highkey, and lowkey photography. The paragraph also touches on how to combine various elements like color schemes, weather types, and locations to enhance the creative process and create a cinematic universe within the AI-generated images.


πŸ“Ή Camera Angles and Retro Styles in AI Photography

The fourth paragraph focuses on the control of camera angles and shot types in Midjourney V6, providing examples of how to achieve different perspectives and effects. It discusses the use of keywords to achieve a retro look by specifying eras or using film stocks with retro features. The paragraph also covers the impact of different cameras on the final image, comparing photography cameras versus cinematic ones, and how lighting serves as a fundamental medium that determines the mood and aesthetic of an image.


πŸ§₯ Fashion, Style, and Emotional Expression in V6

The fifth paragraph discusses the advancements in fashion and style with Midjourney V6, allowing for specific outfit combinations and the replication of distinctive fashion styles. It explores the impact of brands and styles in fashion photography and how to control facial expressions and emotions in AI images. The paragraph also introduces the new feature of adding text to images within V6, providing a creative tool for product photography and other applications.


🌈 Lighting Techniques and Fashion Elements in V6

The final paragraph covers the natural and artificial lighting methods available in Midjourney V6, including directional lighting techniques and how they can be applied to create specific compositions. It discusses the impact of different film stocks on the retro look of images and the subtle differences between various cinematic cameras. The paragraph concludes with a discussion on how lighting and photography elements can be used to enhance the emotional impact of AI-generated photos.



πŸ’‘Midjourney V6

Midjourney V6 refers to the latest version of a highly advanced AI model designed for creating photorealistic and cinematic images. It is the central focus of the video, which aims to showcase its capabilities and improvements over the previous version. In the script, it is discussed in detail, highlighting its enhanced natural language understanding and photorealism.


Photorealistic refers to the quality of an image or visual representation that closely resembles a real-life photograph. In the context of the video, photorealism is a key metric for evaluating the output of Midjourney V6, with the script emphasizing the significant improvements in skin realism and the reduction of an 'airbrushed' effect.

πŸ’‘Natural Language Understanding

Natural Language Understanding (NLU) is the AI's ability to comprehend and interpret human language in a way that is both meaningful and useful. The video script discusses how Midjourney V6 has improved in this area, allowing for better comprehension of complex prompts and leading to more accurate and nuanced image generation.

πŸ’‘AI Photography

AI Photography involves the use of artificial intelligence to create or enhance photographs. The video is a guide to creating cinematic AI photos with Midjourney V6, exploring how the AI can be directed to produce images that mimic various styles and techniques of traditional photography.

πŸ’‘Prompting Structure

The prompting structure refers to the method of providing instructions or 'prompts' to the AI in order to guide the generation of images. The video explains that Midjourney V6 has a simplified prompting structure, allowing users to define their desired art in great detail, from foundational decisions to secondary and atomic level details.


Cinematic pertains to the creation of images that have the visual style, quality, or feel of a movie. The video script provides a guide on achieving a cinematic look with AI photography, using Midjourney V6 to create images that are not only realistic but also evoke the emotional depth and visual storytelling associated with film.

πŸ’‘Visual Style Guide

A visual style guide is a set of visual examples or a collection of images that illustrate how different elements, such as keywords, affect the final output of an AI image generation model. In the video, a visual style guide is used to compare how various keywords are rendered in Midjourney V6, providing a reference for users to understand the impact of their choices.

πŸ’‘Camera Angles

Camera angles are different perspectives from which a scene or subject can be photographed. The script discusses how Midjourney V6 allows for more precise control over camera angles, which is crucial for achieving specific visual effects and enhancing the storytelling aspect of AI-generated images.


Lighting in photography refers to the way light interacts with the subject and affects the mood, atmosphere, and overall aesthetic of an image. The video script explains that Midjourney V6 offers significant updates in how it interprets and applies various lighting conditions and techniques, from natural light sources to artificial ones, impacting the emotional tone of the AI photos.

πŸ’‘Fashion Photography

Fashion photography is a genre that focuses on displaying clothing and fashion items in an appealing manner. The script highlights the ability of Midjourney V6 to understand and render specific fashion styles and garments, allowing users to create images that capture the essence of different fashion aesthetics.

πŸ’‘Emotion in Images

Incorporating emotion in images is about creating a visual narrative that evokes feelings and connects with the viewer on an emotional level. The video discusses how Midjourney V6 has improved its ability to reflect emotions not just in the characters' faces but also throughout the entire composition, adding depth to the AI-generated photos.


Mid Journey V6 is the most advanced model for creating photorealistic cinematic AI photos.

V6 introduces a simplified prompting structure for enhanced AI storytelling.

To use V6, it must be manually activated via the '/settings' command on Discord until January.

V6 demonstrates improved natural language understanding, particularly with nuanced prompts.

The model renders more realistic images with better skin realism and less of a 'stock image' feel.

Accuracy of details is significantly improved in V6, especially in rendering hands and objects.

V6 better captures nuances in language, leading to more accurate photorealism.

The new version allows for more creative control with a three-tiered prompt structure: Foundational, Secondary, and Atomic levels.

Photography types like portrait, street, and fashion photography can be further enhanced with specific keywords and styles.

V6 introduces the ability to write text on images, useful for product photography and branding.

Camera angle and shot type keywords provide more creative control for the final image composition.

The addition of film stocks and camera types to prompts can significantly influence the style and color of the final image.

Fashion elements can be described in detail, allowing for more accurate representation of outfits and styles.

Emotion and hand expressions are better captured in V6, adding depth to character representation.

Lighting techniques and conditions can be specified in prompts for greater control over the image's mood and aesthetic.

V6's improved language understanding allows for more precise control over the relationship between light source and subject.

The video provides a comprehensive guide on using Mid Journey V6 for various photography styles and creative applications.