Midjourney v6 Tips and Tricks for Beginners and Advanced Prompters. Part 1

Thaeyne
26 Dec 202308:22

TLDRIn this video, TH explores the new features and changes in Midjourney V6, an AI technology for image generation. The tutorial covers how to activate V6, use the aspect ratio argument for image shape control, and navigate the menu for upscaling and rerolling prompts. TH also discusses the limitations of V6 compared to previous versions, such as the absence of pan and zoom features, and shares initial tips for overcoming these limitations, such as using negative prompting to avoid close-ups. The video promises more advanced features in the next part, inviting viewers to share their own tips and subscribe for updates.

Takeaways

  • 😀 Midjourney V6 is a different model from earlier versions and offers new ways to prompt for images.
  • 🔧 Use the '/slash settings' command to check which model is active or add '--V6' or '--V6.0' to specify V6 in your prompts.
  • 🖼️ The 'D-AR' argument allows control over the aspect ratio of the generated image, affecting its shape and size.
  • 📏 The default image size is 1:1 aspect ratio, which is 1,024 by 1,024 pixels, and changing the aspect ratio will adjust the image dimensions accordingly.
  • 🔄 There is a menu with nine buttons under the generated image in Discord for various actions like upscaling, rerolling, and variations.
  • 🔍 The 'U1' to 'U4' buttons are for selecting images from the grid for upscaling, but currently, they do not change the image size.
  • 🔄 The 'refresh' button rerolls the same prompt, which can be redundant unless the seed is set in the prompt.
  • 🎨 The 'V1' to 'V4' buttons offer variations of a liked image, with options for subtle or strong variations.
  • 🔍 The 'remix' feature allows for complete changes to the prompt if enabled in settings.
  • 📈 Upscaling in V6 currently provides a 2x upscale to 2,048x2,048 pixels, with options to maintain original details or allow creative changes.
  • 👀 V6 lacks some features from version 5.2, such as pan, zoom, and VAR region options, making it harder to control certain aspects of image generation.
  • 🛠️ Negative prompting, such as '--no closeup', can be used to adjust the focus of the image, avoiding close-ups if desired.
  • 👠 Specifying details like the type of shoes can influence the style and composition of the generated images, affecting whether the image is in photography or painted style.

Q & A

  • What is the main topic of the video?

    -The main topic of the video is discussing the new features and tips for using Midjourney V6, an AI technology for image generation.

  • How can you specify the use of Midjourney V6 in your prompts?

    -You can specify the use of Midjourney V6 by checking your settings with /settings to see the active model or by adding '--V6' or '--V6.0' at the end of your prompt.

  • What does the aspect ratio argument 'D-AR' control in Midjourney V6?

    -The aspect ratio argument 'D-AR' controls the shape of the generated image, allowing you to specify if you want a wider or taller image.

  • What is the default aspect ratio for images generated by Midjourney V6?

    -The default aspect ratio for images generated by Midjourney V6 is 1:1, producing an image that is 1,024 by 1,024 pixels.

  • What happens when you change the aspect ratio of an image in Midjourney V6?

    -Changing the aspect ratio will elongate the image in one direction and reduce it in the other, but it will not increase the total number of pixels.

  • What are the U1 to U4 buttons for in the Midjourney V6 image menu?

    -The U1 to U4 buttons are for upscaling an image from the grid, but they do not actually increase the image size; they just provide the image separately with additional buttons.

  • What does the refresh button do in the Midjourney V6 image menu?

    -The refresh button is for rerolling the same prompt, which means it will generate the image again with the same prompt, potentially changing the seed for variation.

  • What are the V1 to V4 buttons for in the Midjourney V6 image menu?

    -The V1 to V4 buttons are for creating variations of an image you like from the grid, allowing you to see images that look similar to the original.

  • What are the limitations of Midjourney V6 compared to version 5.2?

    -Midjourney V6 currently lacks some features that version 5.2 had, such as pan, zoom, and VAR region options. These features are expected to be added gradually.

  • How can you control the level of variation in upscaled images in Midjourney V6?

    -You can control the level of variation in upscaled images by using the 'very subtle' and 'very strong' buttons, which provide more or less variation compared to the original image.

  • What is the current limitation regarding the size of images on Midjourney's website?

    -The biggest size an image will go on Midjourney's website is the size of your browser window, not the actual size of the image, making it harder to access the full resolution image through the website.

  • What tip is given for avoiding close-ups in generated images with Midjourney V6?

    -To avoid close-ups, one can use negative prompting by specifying '--no closeup' in the prompt, which may help in zooming out and showing more of the subject.

Outlines

00:00

🤖 Introduction to Mid Journey V6 AI Prompting

The speaker introduces themselves and expresses excitement about exploring AI technologies, particularly the new Mid Journey V6 model. They guide viewers on how to check their settings or specify the V6 model in their prompts. The video explains the use of the D-AR argument to control the aspect ratio of generated images, with examples of how different ratios affect image dimensions. It also covers the menu options available for images in Discord, including upscaling, rerolling prompts, and variations. The speaker mentions the limitations of the new model compared to the previous version, such as the absence of certain features like pan and zoom, and concludes with an invitation for viewers to share their tips and subscribe to the channel for more content.

05:01

🔍 Exploring Advanced Features and Limitations of Mid Journey V6

This paragraph delves into the advanced features of Mid Journey V6, focusing on the absence of certain features like pan and zoom, which the speaker finds important for controlling image composition. They share their experiences with the new model, noting that it is more challenging to dictate the framing of images, such as avoiding close-ups. The speaker suggests using negative prompting to achieve different framing and describes their success with specifying details like the type of shoes to influence the image output. They also touch on the impact of the photography style and the use of negative prompts to alter the style. The paragraph concludes with a teaser for the next video, which will explore more advanced features of V6, and an invitation for viewers to share their findings and subscribe to the channel.

Mindmap

Keywords

💡Midjourney v6

Midjourney v6 refers to the sixth iteration of the AI technology by Midjourney, which is designed to generate images based on textual prompts. It is the main subject of the video, illustrating how it differs from previous versions and offering tips for effective prompting. For instance, the script mentions checking settings with '/slash settings' to ensure v6 is the active model.

💡Aspect Ratio (D-AR)

The aspect ratio, denoted as D-AR in the script, is a fundamental parameter that dictates the shape and dimensions of the generated image. It controls whether the image is wider or taller, with a default ratio of 1:1, producing a square image. Changing the aspect ratio elongates the image in one direction while reducing it in the other, as exemplified by a 16x9 ratio resulting in a 1456x816 pixel image.

💡Upscaling

Upscaling in the context of Midjourney v6 is the process of increasing the resolution of an image. The script describes a menu with U1 to U4 buttons for upscaling images from the grid, although it clarifies that no actual upscaling occurs with these buttons in v6—they simply provide the image separately. Upscaling options are crucial for enhancing image quality and are a point of comparison between v6 and previous versions.

💡Rerolling

Rerolling, represented by a refresh button in the script, is the action of generating a new image using the exact same prompt. It's a way to explore variations that can arise from the same input, although the script notes that it doesn't change the seed unless specified, which could be seen as inefficient use of generation hours.

💡Variations (V1-V4)

Variations, accessible through V1 to V4 buttons, allow users to see different renditions of an image they like from the grid. These buttons provide images that closely resemble the original but with slight alterations, offering a way to explore diverse outcomes from a single concept.

💡Remix Feature

The remix feature, mentioned in conjunction with the roll and variation buttons, is an option that enables users to completely change their prompt. It's a creative tool that can be enabled in settings, allowing for significant alterations to the original prompt, thus broadening the range of generated images.

💡Negative Prompting

Negative prompting is a technique used to exclude certain elements from the generated image by specifying what should not be included. In the script, it's used as a workaround to avoid close-ups, by adding '--no closeup' to the prompt, which helps in generating images that show more of the scene or subject.

💡Photography Language

Photography language refers to the specific terms and instructions used to describe camera angles, shots, and compositions. The script notes that Midjourney v6 seems less responsive to this language compared to previous versions, making it more challenging to control aspects like close-ups or full shots.

💡Pan and Zoom

Pan and zoom are features that allow users to control the field of view in an image, either by panning across a scene or zooming in on a subject. The script mentions that these features are currently missing in v6, which is a limitation for users who need more precise control over the image composition.

💡VAR Region Options

VAR region options, though not explicitly detailed in the script, likely refer to variable aspects or regions within an image that users can specify for generation. The absence of these options in v6 is noted as a drawback for those accustomed to fine-tuning image details.

💡Seed

The seed in the context of AI image generation is a value that helps determine the randomness in the output. The script mentions that rerolling with the same prompt but without an explicitly set seed will result in different images, while a set seed ensures the same image is produced.

Highlights

Midjourney V6 is different from earlier models and offers new ways to prompt for images.

Check settings with '/slash settings' to see the active model or add '--V6' to specify it in your prompt.

The 'D-AR' argument controls the aspect ratio of the image, allowing for wider or taller images.

Default image size is 1:1 ratio, producing a 1,024x1,024 pixel image.

Changing the aspect ratio elongates the image in one direction while reducing it in the other.

Upscaling options are available under the generated image in Discord, but do not increase the total pixel count.

The 'refresh' button rerolls the same prompt, which can be wasteful if the seed is set in the prompt.

V1-V4 buttons offer variations of a liked image from the grid, with options for more variation.

The 'remix' feature allows complete changes to the prompt if enabled in settings.

Upscaled images in V6 are currently limited to 2x upscale, with options to maintain originality or allow creative changes.

The 'very subtle' and 'very strong' buttons provide more variation options compared to V1-V4.

The 'heart' button sets the image rating to the highest on Midjourney's website for better organization.

The 'web' button links to the image on Midjourney's website, an alternative way to view or download images.

V6 currently lacks pan, zoom, and VAR region options, making it harder to control image composition.

Negative prompting, such as '--no closeup', can help avoid close-ups and adjust the image composition.

Specifying details like the type of shoes can influence the style and composition of the generated images.

The speaker will explore more advanced features of V6 in a follow-up video.

The video encourages viewers to share their own tips and subscribe for more content on Midjourney and V6.

Casual Browsing

Midjourney Prompts for Camera Film and Photography Styles - Part 1 | Midjourney v6 Tips

2024-08-02 03:56:00

Midjourney V6 Decoded: Tips, Tricks, and Expert Insights

2024-08-01 07:13:00

Advanced Midjourney Prompt Guide for Architecture and Landscape Design | Part 1 #midjourney

2024-05-19 12:15:01

Midjourney v5 - Style Prompt Tips and Reference Tricks

2024-05-23 10:30:01

PHOTOREALISM Guide for Midjourney V6 (F.O.C.A.L® - Part 1 of 5)

2024-08-02 03:45:00