Midjourney V6 is OUT! The Absolute Best AI Image Generator? | ALL NEW FEATURES

AI Catalyst
21 Dec 202305:26

TLDRMidjourney V6, a highly anticipated AI image generator, has been released with significant improvements in photorealism and coherence. The update allows for more natural language prompts, simplifying the process of describing desired images. V6 now supports the creation of high-quality pixel art and better aesthetics with its 'style raw' parameter. While it can generate images with multiple characters and real people, privacy concerns may lead to future restrictions. The ability to add text to images is in its early stages but expected to improve. V6 also introduces two new upscalers, 'creative' and 'subtle,' and enhanced image prompts based on reference images. Some V5 features are temporarily unavailable but will be reintroduced. The website is being updated to allow image generation outside of Discord. Although V6 shows promise, the $30 subscription may not yet be worth it until all features are restored and improved. For now, the $10 subscription is recommended for casual use, with Di 3 on Bing Image Creator as a free alternative.

Takeaways

  • 🎉 Midjourney V6 has been released with significant improvements in photorealism and coherence in generated images.
  • 📈 The new version has enhanced natural language understanding, allowing users to prompt with everyday language rather than technical terms.
  • 🖼 Use the 'style raw' parameter followed by 'photorealistic' and your subject for the best photorealistic results.
  • 📝 Midjourney V6 can now generate images with multiple characters and real people, although this feature might face future privacy restrictions.
  • 📜 A new feature allows the generation of short text on images, with promises of significant improvement in the future.
  • 🔍 V6 has made strides in generating pixel art and other image styles, showing noticeable improvements over previous versions.
  • 🚫 There's a current lack of reaction to real artist names and general art style descriptions, which the developers aim to fix soon.
  • 🔄 Some V5 features like Zoom inpainting, 4X upscaling, and style tuning are temporarily unavailable but will be reintroduced.
  • 🔍 Two new upscalers, 'creative' and 'subtle', are available, with the former adding details and the latter preserving the original image.
  • 🖼️ Image prompts have been improved, allowing users to upload a reference image and generate new images based on it.
  • 🌐 The MIDJourney website is being improved to allow image generation outside of Discord, with a full release date yet to be announced.
  • 💲 The $30 subscription is not yet considered worth it due to missing tools and features; the $10 subscription is suggested for fun.

Q & A

  • What is the main focus of Midjourney V6 update?

    -The main focus of Midjourney V6 is to enhance photorealism, coherence, and detail in generated images, as well as improving its understanding of natural language prompts.

  • How has Midjourney V6 improved its prompt understanding?

    -Midjourney V6 has improved its prompt understanding by allowing users to describe the image they want to create in a more human-like manner without needing to use specific technical terms.

  • What is the recommended parameter to use for photorealistic images in Midjourney V6?

    -To get a photorealistic image, use the 'style raw' parameter and simply type 'photo of' followed by your subject in the description.

  • What are the two new upscalers introduced in Midjourney V6?

    -The two new upscalers introduced in Midjourney V6 are 'creative' and 'subtle', with the creative upscaler adding new details and the subtle upscaler focusing on preserving the original image.

  • How does Midjourney V6 handle generating images of real people like actors and celebrities?

    -Midjourney V6 has an enhanced ability to generate images of real people, but this feature might be removed or heavily censored in the future due to privacy concerns.

  • What are the limitations of Midjourney V6 when it comes to generating pixel art style images?

    -Previously, Midjourney had difficulties creating pixel art style images, but V6 can now generate very high-quality and precise pixel art images.

  • What are the current subscription options for Midjourney V6, and which one is recommended for trying it out for fun?

    -The current subscription options for Midjourney V6 are $10 and $30. The $10 subscription is recommended for trying it out for fun, as it should be sufficient for casual use.

  • What is the status of Midjourney V6's features that are not yet available?

    -Features like Zoom inpainting, 4X upscaling, and style tuning are not currently available in Midjourney V6 but are expected to be reintroduced gradually in the coming months.

  • How can users generate short text on images using Midjourney V6?

    -Users must write their text in quotations and keep their prompt as short as possible. Using the 'style raw' parameter or lower 'stylized' values may also help.

  • What are the improvements made to image prompts in Midjourney V6?

    -Image prompts have been improved in Midjourney V6, allowing users to upload a reference image, write a prompt, and generate new images based on the initial image.

  • What is the current status of the Midjourney website?

    -The Midjourney website currently serves more as a gallery where users can browse, rate, and examine community-created images and their prompts. It is being improved to allow image generation outside of Discord, but the full release date is not yet known.

  • Is the $30 subscription for Midjourney V6 considered worth it at the moment?

    -The $30 subscription is not yet considered worth it as some features are still missing. It is suggested to give Midjourney V6 some time to fully improve and regain all the missing tools and features.

Outlines

00:00

🚀 Mid Journey Version 6 Release and Features Overview

Mid Journey version 6 has been released, offering enhanced photorealism and improved coherence in generated images. The update allows for more natural language prompts, reducing the need for specific technical terms. It introduces a 'style raw' parameter for photorealistic images and a 'stylized' parameter that balances prompt understanding and aesthetics. The ability to generate multiple characters and real person images has been enhanced, though this may face future privacy restrictions. Mid Journey can now also generate short text on images, with improvements expected. Pixel art style generation has seen significant improvement. However, some features from version 5 are temporarily unavailable but will be reintroduced. New upscalers 'creative' and 'subtle' have been added, and prompts have been improved to allow for reference image uploads and new image generation based on initial images. The Mid Journey website is being improved to serve as a gallery and image generation platform, with a beta version accessible to paid members. The subscription value is currently considered not fully worth it until all missing tools and features are restored.

05:00

💡 Evaluating the Subscription Value and Alternatives

The video discusses the value of the Mid Journey V6 subscription, suggesting that it's not yet worth the $30 price point. It recommends waiting for the tool to fully improve and regain all missing features. For those who wish to experiment with the tool for fun, the $10 limited subscription is deemed sufficient, although it may deplete generation credits more quickly. An alternative to Mid Journey is Bing image Creator, which is a free option that matches Mid Journey in all aspects except photo realism. The video concludes with an invitation to find a full guide on using Mid Journey V6 on their website and a promise to keep the audience updated as AI image generation technology evolves.

Mindmap

Keywords

💡Midjourney V6

Midjourney V6 refers to the latest version of an AI image generator that has been recently released. It is known for its photorealistic image generation capabilities, which have been further enhanced in this version. The update aims to provide more coherent and detailed images, making it a significant upgrade from its predecessors.

💡Photorealism

Photorealism in the context of this video refers to the quality of digital images generated by the AI that closely resemble real-life photographs. Midjourney V6 has improved upon this by making the images more coherent and detailed, which is a major selling point for the software.

💡Natural Language Understanding

Natural Language Understanding (NLU) is the AI's ability to comprehend and interpret human language in a way that is natural and intuitive. Midjourney V6 has made strides in this area, allowing users to describe the image they want in plain language, without needing to use specific technical terms.

💡Style Raw Parameter

The 'Style raw' parameter is a feature in Midjourney V6 that, when used, instructs the AI to generate images in a more photorealistic style. It is mentioned in the script as a way to achieve high-quality, aesthetically pleasing images by typing 'photo of' followed by the subject in the description.

💡Stylized Parameter

The 'Stylized' parameter is another feature that affects the output of the AI image generator. Lower values for this parameter improve the AI's prompt understanding, while higher values result in images with better aesthetics. It is a tool for users to fine-tune the style of the generated images.

💡Multiple Characters Generation

This feature allows Midjourney V6 to generate images containing multiple characters or real people, such as actors, politicians, and celebrities. It is an interesting and fun addition, although the script notes that it might face future restrictions due to privacy concerns.

💡Text on Images

The ability to generate short text on images is a new feature in Midjourney V6. While it is not yet highly developed, the developers have promised significant improvements in the near future. Users must input their text in quotations and keep their prompts concise to utilize this feature effectively.

💡Pixel Art Style

Pixel art is a digital art form characterized by the use of small, square-shaped pixels to create images. Midjourney V6 has notably improved its ability to generate high-quality and precise pixel art images, which was a weakness in the previous version.

💡Upscaling

Upscaling in the context of Midjourney V6 refers to the process of increasing the resolution of an image while maintaining or enhancing its quality. Two new upscalers, 'creative' and 'subtle,' are introduced, with the former adding new details and the latter focusing on preserving the original image's integrity.

💡Image Prompts

Image prompts are reference images that users can upload to guide the AI in generating new images. This feature has been improved in Midjourney V6, allowing for more accurate and relevant image generation based on the initial image provided by the user.

💡Discord Polls

Discord polls are a method used by the Midjourney community to vote on which features they would like to see prioritized in the post-launch updates of the software. This democratic approach helps the developers understand user preferences and focus on the most desired functionalities.

💡Subscription Pricing

The video discusses the value of different subscription pricing tiers for Midjourney V6. It suggests that the higher-priced subscription may not yet be worth it due to some missing tools and features, and recommends the $10 subscription for those looking to try the software for fun.

Highlights

Midjourney V6 has been released with significant improvements in photorealism and coherence.

Images generated by V6 are more detailed and coherent than previous versions.

The AI's understanding of natural language has been greatly improved, allowing for more human-like prompts.

Users no longer need to use specific technical terms for prompts; a more natural description is sufficient.

The 'style raw' parameter can be used to create photorealistic images by simply describing the subject.

Lower values of the 'stylized' parameter improve prompt understanding, while higher values enhance aesthetics.

Short prompts work best for generating images, and unnecessary words should be avoided.

Midjourney V6 has an enhanced ability to generate images with multiple characters and real people.

The feature to generate short text on images is currently basic but will be significantly improved in the future.

V6 can now generate high-quality pixel art images, a significant improvement over V5.

Other image styles have also been improved, although some users report issues with real artist names and art style descriptions.

Two new upscalers, 'creative' and 'subtle', are available for enhancing image resolution.

The 'creative' upscaler adds new details, while the 'subtle' upscaler preserves the original image.

Image prompts have been improved with the ability to upload a reference image and generate new images based on it.

The new Midjourney website is being improved to serve as a gallery and image generation platform.

Paid Midjourney members can access the beta version of the website.

Some features from V5, such as Zoom inpainting and 4X upscaling, are temporarily unavailable but will be reintroduced.

The $30 subscription may not yet be worth it due to missing tools and features, but the $10 subscription is sufficient for fun.

Dolly 3 on Bing Image Creator is a free alternative that matches Midjourney in all aspects except photo realism.

A full guide on using Midjourney V6 is available on the website, with updates as AI image generation technology evolves.