Midjourney v5 is out: How to use it?
The newest version of the popular AI image generator's neural network, Midjourney v5, can produce strikingly lifelike visuals. The v5 model employs cutting-edge tools and a new neural architecture to generate aesthetics and designs.
It took five months to complete the updated edition of Midjourney, and yes, it can draw hands now! The team announced the news on the project's official Discord channel.
Midjourney v5: What is new?
According to the announcement, these are the changes that come with the update:
- Much wider stylistic range and more responsive prompting.
- Much higher image quality (2x resolution increase) improved dynamic range.
- More detailed images. Details are more likely to be correct. Less unwanted text.
- Improved performance with image prompting.
- Supports --tile argument for seamless tiling (experimental).
- Supports --ar aspect ratios greater than 2:1 (experimental).
- Supports --iw for weighing image prompts versus text prompts.
What do they mean?
- Stylistics: Midjourney v5's aesthetic range is greater, and it understands user requests more accurately. The significance of mentioning the artist's or movement's names has grown in recent years. If no style is specified, the neural network will use its default to create photorealistic output.
- Quality: There is now twice as much resolution and a wider dynamic range. Now, high-quality images may be made instantly. In version 4, the request was processed while the user waited for each image to be up-scaled by hand. As of right now, clicking the Upscale button will immediately load a larger version of the image.
- Detailing: When it comes to small details, the neural network excels. Therefore, it makes five fingers on each hand and doesn't add hundred even teeth. Developers also claimed to have "dramatically" enhanced facial detailing.
This new edition of Midjourney will let users create photorealistic visuals, which may throw off more than one person's ability to tell reality from simulation. We have come a long way in just a few months with Midjourney v4, and now we can find images with a higher level of graphic detail than we ever could have anticipated.
The creators caution that two-word requests may not be as effective as before and instead suggest coming up with longer, more specific prompts. The beta phase of development for the fifth generation is still under progress. The developers caution that the neural network may undergo significant changes before the final release. Generation, though, is already accessible to people
Starting today our community can test Midjourney V5. It has much higher image quality, more diverse outputs, wider stylistic range, support for seamless textures, wider aspect ratios, better image prompting, wider dynamic range and more. Let’s explore!
— Midjourney (@midjourney) March 15, 2023
How to use Midjourney v5?
Currently, Midjourney's default neural network version is v4. You have two options for activating the fifth:
- Just type /settings in Discord, choose the MJ option and hit the enter key to apply the changes. Choose MJ 5 in the menu that appears, and then click Apply.
- Add —v 5 at the command prompt when generating an image.
Midjourney v4 vs Midjourney v5
The fifth edition is a significant improvement, especially when it comes to creating well-known figures from popular culture. The distinction is most noticeable when the neural network attempts to depict a realistic scene, such as an image, landscape, or indoor space.
1990s era, photo of a young man, sitting, mechanical keyboard, working, desk, 1990s CRT monitor, monstera, 1 glass of oj, juice, wide shot, side view, natural lighting, home, polaroid, 4k --ar 16:9
v4 (left) v5 (right) pic.twitter.com/iMvG5z81mU
— Nick St. Pierre (@nickfloats) March 15, 2023
You can check out more examples by looking at Nick St. Pierre's tweet series.Advertisement