Midjourney v5 is now available. The new model can generate much more realistic and detailed images. We explain all this to you.
If you follow Frandroid diligently, you’ve probably noticed images designed thanks to Midjourney. We use this tool to generate illustrations. A fifth version was recently released, featuring significantly reworked neural architecture and incorporating new aesthetic approaches. While GPT-4 is receiving a lot of media coverage, Midjourney is another tool that also deserves our attention and should be watched closely.
What is Midjourney?
Midjourney is an independent research laboratory that has developed a self-titled program based on artificial intelligence. This program is designed to generate images from textual descriptions, like DALL-E and OpenAI’s Stable Diffusion. Although the underlying technology seems to be Stable Diffusion, the creators of Midjourney have developed their own unique style, with an internal algorithm, which has drawn a lot of attention.
Midjourney’s V5 has arrived, and it’s finally doing 5-fingered hands 🖐️ pic.twitter.com/euP2VkKWfm
— Numerama (@Numerama) March 16, 2023
The tool has been in open beta since July 2022. Since then, it has been attracting an increasing number of users: version 2 of its algorithm was released in April 2022, followed by version 3 in July of the same year. . On November 10, 2022, the alpha iteration of version 4 was released to users. Finally, Midjourney in version 5 is available from March 15, 2022.
Midjourney works with simple words, but also uses “prompts” (advanced commands) to create detailed and precise images with the Midjourney bot. These indications provides a textual description of the image you want to generate and guides the bot to achieve it. Whether you want a photograph, a painting or a quick drawing, the immediate you can help the bot create the precise image you want to achieve.
What changes in this fifth mount?
Midjourney creator David Holz describes V5 as a professional tool because, unlike its previous versions, it doesn’t limit itself to specific artistic styles and offers a greater variety of visual results. However, this V5 is still in alpha and will undergo “major changes” before the final release.
In short, it allows for greater creative freedom, but this freedom must be tamed. According to David Holz, this may involve the use of indications more elaborate details that explicitly detail aspects of the image, such as lighting and atmosphere, to achieve the desired result. Note, in passing, that it’s important to specify precise details in order for the bot to generate specific items. Think about subject matter, medium, setting, lighting, color, mood, and composition. Anything not mentioned will be randomly generated.
After testing V5, we saw more accurate and relevant results and fewer anomalies or crashes. However, imaging is slower. This situation is similar to what can be seen with GPT-4 in ChatGPT. Version V5 offers significant improvements in language understanding, accuracy, and aesthetic flexibility, all of which contribute to the generation of impressive images. The depth and richness of the images it produces are truly astounding, and the range of aesthetics it can conjure is staggering.
How to use Midjourney V5?
MidJourney is currently only accessible via Discord (take the opportunity to join our server), so to start using it, you need a Discord account. First, visit the MidJourney website and click on the beta participation program.
After that, you need to accept an invitation to the Discord Midjourney server. Now open your Discord app and click on the MidJourney server ship icon. Use the flag with the command /imagine and start creating images from your imagination. You can do it on the server you want, obviously you will have to configure Midjourney on the latter.
To activate V5, you need a paid account, then activate this version with the command /settings.
How to use the prompts?
Basic commands are as simple as a single word, phrase, or even an emoji. The bot doesn’t understand grammar or sentence structure, so word choice is important. More specific synonyms work better than generic ones, while using fewer words gives each word more weight. You also have the option of using indicationsthe famous advanced commandos.
Advanced commands can include one or more image URLs, multiple text phrases, and one or more parameters. Image URLs can be added to an ad to influence the style and content of the final result, and indications you can modify the way an image is generated, such as aspect ratio, models, etc. Numerama mentions several examples to get you started. In addition, this site generates indications on the progress.
It’s also essential to focus on what you want in the image rather than what you don’t want. Finally, speak to Midjourney in English for more accurate results. If this is not your native language, feel free to use DeepL for translations.
Some examples generated with Midjourney V5
Here are some additional examples of images generated with Midjourney V5.
Our colleagues from Numerama launch Watt Else, their newsletter dedicated to the mobility of the future. Sign up here to make sure you receive the next issue!