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

Thaeyne
26 Dec 202308:22

TLDRIn this tutorial, TH explores the new features of Midjourney V6, an AI technology for image generation. The video covers how to activate the model, use aspect ratio controls, and navigate the menu for upscaling and rerolling images. It also discusses the limitations of V6 compared to previous versions, such as the absence of pan and zoom features, and offers tips on how to work around these limitations, such as using negative prompting to avoid close-ups. The video promises more advanced features in the next installment, inviting viewers to share their own tips and subscribe for updates.

Takeaways

  • 🔧 Use the `/settings` command to check or set the active model to Midjourney V6.
  • 📐 The `--ar` argument allows you to control the aspect ratio of your image, affecting its shape and pixel dimensions.
  • 🖼️ The default image size from Midjourney V6 is 1:1 aspect ratio, resulting in a 1242x1242 pixel image.
  • 🔄 Changing the aspect ratio can elongate the image in one direction while reducing it in the other, but it does not increase the total pixel count.
  • 📚 After generating an image, you can find a menu with nine buttons for various actions, including upscaling and rerolling the prompt.
  • 🔄 The U1-U4 buttons are for selecting specific images from the grid for upscaling, but they do not change the image size initially.
  • 🔄 The 'refresh' button rerolls the same prompt, which can be wasteful if the seed is set in the prompt.
  • 🔄 The V1-V4 buttons offer variations of a liked image from the grid, with options for subtle or strong variations.
  • 🖼️ Upscaling in V6 currently results in a 248x248 pixel image, with options for subtle or creative changes from the original.
  • 👀 V6 does not yet have features like pan/zoom or VAR region options, making it harder to control certain aspects of image generation.
  • 🚫 Negative prompting, such as specifying `--no closeup`, can help avoid unwanted close-ups in the generated images.

Q & A

  • What is the main topic of the video transcript?

    -The main topic of the video transcript is discussing the features and usage tips of Midjourney V6, an AI technology, for both beginners and advanced prompters.

  • How can one check or set the active model in Midjourney?

    -To check or set the active model in Midjourney, one should use the '/ Slash settings' command or add '--V6' or '--V6.0' at the end of the prompt.

  • What does the 'D-AR' argument stand for in Midjourney V6, and how does it affect the image?

    -The 'D-AR' argument stands for 'Dynamic Aspect Ratio'. It allows users to control the shape of the image, making it wider or taller, which affects the image's dimensions and orientation.

  • What is the default aspect ratio for images in Midjourney V6, and what are its pixel dimensions?

    -The default aspect ratio for images in Midjourney V6 is 1:1, which results in an image size of 1,024 by 1,024 pixels.

  • How does changing the aspect ratio affect the size of the image in Midjourney V6?

    -Changing the aspect ratio makes the image elongated in one direction while reducing its size in the other direction, but it does not increase the total number of pixels.

  • What are the U1, U2, U3, and U4 buttons for in the Midjourney V6 image menu?

    -The U1, U2, U3, and U4 buttons are used for upscaling an image from the grid. However, in V6, pressing these buttons does not upscale the image but provides the image separately with additional buttons.

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

    -The refresh button is used for rerolling the same prompt, generating the image again with the same prompt, which might change the seed unless it's explicitly set.

  • What are the V1, V2, V3, and V4 buttons for in the Midjourney V6 image menu?

    -The V1, V2, V3, and V4 buttons are for creating variations of an image that a user likes from the grid, providing 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. It also has a different approach to upscaling, with only 2x upscale available initially.

  • How can users get more variation in their upscaled images in Midjourney V6?

    -Users can get more variation in their upscaled images by using the 'very subtle' and 'very strong' buttons, which provide different levels of variation compared to the original image.

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

    -The size of images on Midjourney's website is currently limited to the size of the browser window, and the full size of the image is not as easily accessible through the website.

  • How can users avoid getting close-ups in their images with Midjourney V6?

    -Users can avoid close-ups by using negative prompting, such as specifying '--no closeup' in their prompt, which can help to zoom out in the image.

  • What is the role of the 'heart' button in the Midjourney V6 image menu?

    -The 'heart' button sets the rating of the image to the highest option on Midjourney's website, helping users to organize and find their favorite images more easily later on.

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

    -The 'web' button takes users to the particular image on Midjourney's website, providing a way to download or view the images.

Outlines

00:00

🤖 Introduction to Mid Journey V6 and Prompting Techniques

The video script introduces the viewer to the new features of Mid Journey V6, an AI technology for image generation. It explains how to check the active model and suggests adding '--V6' or '--v6.0' to prompts for version-specific results. The script details the use of the 'D-AR' argument to control the aspect ratio of generated images, emphasizing the default 1:1 ratio and the limitations when altering it. It also introduces the menu options available under the generated image in Discord, including upscaling, rerolling, and variation buttons, as well as the remix feature for prompt editing. The script notes the absence of certain features from version 5.2 and mentions the gradual addition of these features in V6.

05:01

🔍 Exploring Advanced Features and Challenges in Mid Journey V6

This paragraph delves into the advanced features of Mid Journey V6, focusing on the current limitations such as the lack of pan, zoom, and VAR region options. It discusses the difficulties in controlling image composition, particularly with close-ups and full shots, and suggests using negative prompting to avoid undesired results. The script shares personal experiences with aspect ratio adjustments and the impact of specifying details like shoes on image style. It also mentions the varying responses to similar prompts and the influence of the photography style on image generation. The paragraph concludes with a teaser for the next video, which will explore more advanced features of V6, and encourages viewers to share their tips and subscribe for more content.

Mindmap

Keywords

💡Midjourney V6

Midjourney V6 refers to the sixth iteration of the AI model developed by the company Midjourney, which is used for generating images based on textual prompts. It is a significant upgrade from its earlier versions and is the central focus of the video. The script discusses its unique features and how to effectively use it for image generation.

💡Aspect Ratio (D-AR)

The aspect ratio, denoted as D-AR in the script, is the proportional relationship between the width and height of an image, controlling its shape. In the context of Midjourney V6, it allows users to specify whether they want a wider or taller image, with the default being 1:1. The script explains how changing the aspect ratio affects the dimensions and size of the generated image.

💡Upscaling

Upscaling in the video script refers to the process of increasing the resolution of an image while maintaining its quality. Midjourney V6 provides options for upscaling images to a larger size, such as 2x upscale, though it's noted that there is no 4x upscale option yet. The script mentions specific buttons for upscaling within the Discord menu.

💡Rerolling

Rerolling is the action of generating a new image using the exact same prompt to see variations in the output. The script mentions a refresh button that allows for rerolling, but cautions that it does not change the seed unless specified, which could lead to the same image being generated.

💡Variations (V1-V4)

Variations, indicated by the buttons V1-V4 in the script, are options that allow users to see different renditions of an image they like from their grid. These variations can provide a range of images that are similar to the original but with some differences, offering more creative options.

💡Remix Feature

The remix feature, as mentioned in the script, is an option that allows users to completely change their prompt. It can be enabled in the settings, and when used, it presents a popup with the prompt text for editing, offering flexibility in the image generation process.

💡Negative Prompting

Negative prompting is a technique used in AI image generation where users specify what they do not want to see in the image. In the script, it is suggested as a method to avoid close-ups by adding '--no closeup' to the prompt, which can help in controlling the focus and composition of the generated images.

💡Photography Language

Photography language in the script refers to the descriptive terms used to convey specific visual effects or compositions, such as 'close-up' or 'full shot'. The video discusses how Midjourney V6's response to such language has changed, requiring users to adapt their prompting strategies.

💡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 or out. The script notes that these features are currently missing in Midjourney V6, which affects the control users have over the composition of their generated images.

💡VAR Region Options

VAR region options, though not explicitly defined in the script, likely refer to variable aspects of the image generation process that users can control, such as the region of focus within an image. The absence of these options in V6 is mentioned as a limitation.

💡Seed

In the context of AI image generation, a seed is a value that helps determine the randomness in the output. The script mentions that rerolling an image without changing the seed will result in the same image, highlighting the importance of seed manipulation for creating unique images.

Highlights

Midjourney V6 is a new model with significant differences from earlier versions.

To use Midjourney V6, check settings with '/slash settings' or add '--v6' to your prompt.

The 'D-AR' argument allows control over the aspect ratio of the generated image.

The default aspect ratio is 1:1, 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 with specific buttons.

Upscaling does not increase the total number of pixels in the image.

The 'refresh' button rerolls the same prompt, potentially wasting generation hours.

Variation buttons (V1-V4) allow for variations of a liked image from the grid.

The 'remix' feature can be enabled for complete prompt changes.

V6 currently lacks some features of version 5.2, such as pan, zoom, and VAR region options.

Negative prompting, like '--no closeup', can help control the image composition.

Specifying details like shoe types can influence the style and composition of generated images.

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

The 'web' button links to the image on Midjourney's website for easy access and download.

The speaker is still learning and discovering how to prompt effectively in V6.

An upcoming video will explore more advanced features of Midjourney V6.

The speaker encourages viewers to share their tips and subscribe for more content.