NEW Midjourney V6 Features! Zoom Out, Pan, Inpainting Tutorial with Examples | Midjourney AI

Woollyfern
27 Jan 202406:18

TLDRThis video introduces the latest features of Midjourney V6, including the ability to zoom out, pan, and use inpainting on images. The zoom out feature extends the content of an image beyond its original boundaries, which is useful for changing from close-up portraits to full-body images or expanding scenes. The pan feature allows users to extend images in specific directions, and with the inpainting feature, users can modify specific parts of an image using a new or updated prompt. The video also provides tips on how to use these features effectively, such as using custom zoom values and adjusting the prompt text during panning. Additionally, the video mentions that a V6 style tuner is in development and will be released soon.

Takeaways

  • 🔍 **Zoom Out Feature**: Allows users to extend the content of an image beyond its original boundaries, useful for changing close-up portraits to full-body images or expanding scenes.
  • 🖼️ **Aspect Ratio Adjustment**: Custom Zoom enables users to adjust the image's aspect ratio while zooming out, with no limit to the number of consecutive zooms.
  • 📐 **Make Square Option**: For non-square aspect ratios, this feature adjusts the image to a square by expanding it horizontally or vertically.
  • 📚 **Remix Mode**: Essential for modifying the prompt text when panning or creating variations of an image.
  • ➡️ **Panning**: Extends the image in specific directions without altering the subject's central position, unlike zoom out.
  • 🖌️ **Inpainting (Vary Region)**: A feature that lets users modify specific parts of an image with a new or updated prompt.
  • 📸 **Image Selection for Inpainting**: Users can select areas for modification using either the rectangle or lasso tool, with a suggestion to select a larger area for better results.
  • 🚫 **Aspect Ratio Changes During Panning**: Changes to the aspect ratio are ignored when panning as it inherently alters the ratio.
  • ➕ **Adding Text to Images**: Users can insert text or conversation bubbles into images using the Vary Region feature.
  • 🛠️ **Style Tuner Update**: A V6 style tuner is in development and will be released soon.
  • 🎨 **Free Style Codes**: The presenter offers free style codes for experimentation in V5, with a link provided in the description.

Q & A

  • What new features have been released for Midjourney V6?

    -The new features for Midjourney V6 include the ability to zoom out, pan, and inpaint your images.

  • What should be enabled in settings to make the most out of the new features?

    -To maximize the use of the new features, ensure that remix mode is enabled in your settings.

  • How does the zoom out feature work?

    -The zoom out feature allows you to extend the content of an image beyond its original boundaries, which is useful for transitioning from close-up portraits to full-body images, fixing cropping issues, or expanding a scene.

  • What does the 'make square' button do in the zoom out feature?

    -The 'make square' button adjusts the aspect ratio of the image to make it a square by either expanding it horizontally or vertically.

  • How can custom zoom be used to adjust the aspect ratio?

    -Custom zoom can be used to adjust the aspect ratio by setting the zoom level and the custom zoom value simultaneously, allowing for a wider aspect ratio without zooming out.

  • What is the pan feature and how does it differ from zoom out?

    -The pan feature allows you to extend your image in specific directions. Unlike zoom out, which keeps the subject in the center, pan lets you move the subject around by adding content in one specific direction at a time.

  • How does the inpainting feature work in Midjourney V6?

    -The inpainting feature, known as 'vary region', enables you to modify specific parts of your image using a new or updated prompt. You can select the area to modify and submit a new prompt for that region.

  • How can you use the inpainting feature on an older image?

    -To use the inpainting feature on an older image, locate the upscaled image in your Midjourney gallery, copy its job ID, and use it in Discord with the 'vary region' command followed by the job ID.

  • What is the purpose of the 'Das Dash' parameter in the prompt?

    -The 'Das Dash' parameter followed by specific words can help downweight those words in the results, allowing for more control over the generated image.

  • How can you add text to an image using the inpainting feature?

    -You can add text to an image by selecting the region where you want the text to appear and including the text within quotes in your prompt.

  • Is there a V6 style tuner available?

    -As of the time of the video, the V6 style tuner is in development and will be released soon.

  • Where can one find free style codes to experiment with in V5?

    -Free style codes for experimentation in V5 can be found in the video description, where a link is provided.

Outlines

00:00

📽️ New Features in MidJourney V6

The video introduces new features released for MidJourney V6, focusing on the ability to zoom out, pan, and inpainting on V6 images. It emphasizes the importance of having remix mode enabled to modify the prompt text and create variations of an image. The host guides viewers through how to use these features, starting with zoom out, which allows extending the content of an image beyond its original boundaries. The video also covers the custom zoom feature, the use of 'das' parameter to address vignetting issues, and the pan feature that extends images in specific directions. Lastly, the video discusses the inpainting feature, which enables modifying specific parts of an image with a new prompt, and provides a method to apply these features to older images.

05:03

🖌️ Advanced Techniques with MidJourney V6

This paragraph delves into advanced techniques using MidJourney V6. It explains how to downweight certain words in the prompt using the '--no' parameter, which is particularly useful in V6. The video demonstrates adding text to images with the 'vary region' feature, showing how to add multiple text phrases in separate steps. It also discusses the upcoming V6 style tuner and offers free style codes for experimentation in V5. The host encourages viewers to like, subscribe, and provides links in the description for further resources.

Mindmap

Keywords

💡Zoom Out

Zoom Out is a feature that allows users to extend the content of an image beyond its original boundaries. It is particularly useful for changing close-up portraits to full-body images, fixing cropping issues, or expanding a scene. In the video, the presenter demonstrates how to use the Zoom Out feature to adjust the aspect ratio and extend an image, showcasing its utility in creative editing.

💡Pan

Pan is a functionality that enables users to extend an image in specific directions, which can be useful for moving the subject around within the image or adding content in one direction at a time. Unlike Zoom Out, which keeps the subject centered, Pan allows for the subject to be repositioned. The script illustrates this by showing how to use the Pan feature to create variations of an image.

💡Inpainting

Inpainting is a feature of Midjourney AI that allows users to modify specific parts of an image using a new or updated prompt. It is showcased in the video as a powerful tool for making targeted changes, such as adding a hat to a dog in an image or removing objects. The presenter explains how to use the Inpainting feature with the Varying Region tool to make precise modifications.

💡Remix Mode

Remix Mode is a setting in Midjourney AI that, when enabled, allows users to modify the prompt text as they pan or create variations of an image. This feature is crucial for the new functionalities discussed in the video, as it provides the flexibility to adjust the image according to the user's creative direction. The script emphasizes the importance of having Remix Mode enabled to fully utilize the new features.

💡Aspect Ratio

Aspect Ratio refers to the proportional relationship between the width and the height of an image. In the context of the video, the presenter discusses how to adjust the aspect ratio using the Zoom Out feature, changing it from a 9 by 6 image to a wider 3:2 aspect ratio. This is significant for users looking to change the composition of their images for different display purposes.

💡Vignetting

Vignetting is a visual effect where the corners of an image gradually get darker. The video mentions that after several consecutive Zoom Outs, there seems to be a bit of vignetting. The presenter suggests adding parameters to the prompt, such as 'Vibrant Black Border' or 'Black Corners', to mitigate this effect, although it's noted that this isn't always foolproof.

💡Job ID

Job ID is a unique identifier for a specific task or process. In the video, the presenter explains how to retrieve the Job ID of an upscaled image from the Midjourney website, which is then used in Discord to bring the image back for further editing with the new features. The Job ID is essential for locating and manipulating existing images within the platform.

💡Style Tuner

The Style Tuner is a feature that is mentioned as being in development and will be released soon. It is implied that this tool will allow users to fine-tune the style of their images. While the video does not provide specific details on how the Style Tuner will work, it generates anticipation for users interested in advanced image editing capabilities.

💡Style Codes

Style Codes are sets of parameters that users can experiment with to achieve different visual effects in their images. The video mentions that the presenter has free style codes available for users to try out in V5 of Midjourney AI. These codes can be used to customize the appearance of generated images, offering users more control over the final output.

💡Denoising Parameter

The Denoising Parameter, often represented as '--' followed by a value, is a command used in the prompt to control the level of detail and noise in the generated image. In the video, the presenter uses the Denoising Parameter with terms like 'beagle' and 'dog' appended to the end of the prompt, which downweights these words in the results, allowing for more control over the final image.

💡Text Images

Text Images refer to the ability to add text to an image using the Inpainting feature. The video demonstrates how to use the Varying Region tool to select an area of the image and add text, such as conversation bubbles, to create a narrative or add context to the visual content. This feature is particularly useful for creating images with captions or dialogue.

Highlights

Midjourney AI has released new features for V6, including zoom out, pan, and inpainting.

Zoom out allows extending the content of an image beyond its original boundaries, useful for full body images or establishing shots.

The make square button adjusts the aspect ratio to create a square image.

Custom Zoom provides the opportunity to change the aspect ratio and zoom level simultaneously.

Panning in V6 lets you extend the image in specific directions and move the subject around.

Inpainting feature enables modifying specific parts of an image with a new or updated prompt.

Remix mode allows modifying the prompt text as you pan or create variations of an image.

Existing images in the Midjourney gallery can be used with the new features without starting from scratch.

Zooming out several times may result in vignetting, where the corners of the image get darker.

Adding parameters like 'ar black border black corners' to the prompt can help with vignetting.

Panning inherently alters the aspect ratio, unlike zoom out which keeps the subject centered.

Inpainting can be used to add or remove objects from an image, or to modify specific areas.

The job ID is required to use existing upscaled images with the new features in Discord.

Text can be added to images by selecting a region and inputting the text in quotes.

Multiple text phrases can be added in separate steps using the inpainting feature.

A V6 style tuner is in development and will be released soon.

Free style codes for V5 are available for experimentation and can be found in the video description.