Midjourney v6 is something I've been patiently anticipating for a very long time. There have been multiple announcements from the Midjourney team during 2023 saying that this version would be released soon. Since it's the end of the year, I honestly thought that I'd get a chance to use this upgraded model in 2024. Turns out I was wrong because the Midjorney version 6 has officially been released.
In this article, I'm going to share some exciting prompt examples and show you what's possible to create with Midjourney v6. Although I have been using Midjourney for more than a year, this will be my first time using this specific version. I've yet to really dive deep into this and do thorough research on the model, but you can expect more detailed articles from me on this subject in the near future.
For now, let's check out what's new with the Midjourney model released on December 21.
What's New With Midjourney V6?
The sixth iteration of the Midjourney text-to-image model came with a massive update. What was most surprising to me personally is how prompting has changed. But I'll talk about that in more detail later on.
For now, I want to acknowledge some of the core changes made to the model:
- The knowledge of the model has increased significantly, meaning that it can now understand even more terms that you use in your prompts. It also has enhanced coherence.
- The Midjourney generative model has become more accurate when following instructions in prompts. This is honestly very impressive considering that previous iterations were known to often follow only certain instructions.
- The Midjourney v6 base model has a better capability of following longer prompts. This is also an issue that people wanted to see fixed for months since the model would usually only follow instructions in the first 60 words of a prompt.
- The model now has minor text drawing ability. This was also an anticipated feature, especially after OpenAI became the first to introduce it with its third iteration of the Dall-E text-to-image model.
Those are some of the highlights when it comes to the improvements made to the base model. At the time of writing this article, Midjourney v6 is still in its alpha test phase. This means that things can change frequently and without notice.
How Has Prompting Changed in Midjourney v6
This is something I've been waiting to talk about since the beginning of this article. The first tool powered by artificial intelligence that I was ever introduced to is Midjourney. I got really interested in AI because I was so impressed with the capabilities of the Midjourney model. And that's back when it wasn't nearly as impressive as it is today.
The first few weeks I spent in the Midjourney Discord server consisted of me mostly writing simple prompts that featured 5-10 words and patiently awaiting the results. However, since I got to experiment with this model on a public server, I could see the prompts other users were writing.
I was a bit confused at first but quickly started learning and got better each day. As a community, we all learned how to prompt together. And with the release of Midjourney v6, it's time to relearn how to prompt.
In an announcement that was released along Midjourney v6, the founder noted that this iteration of the model is significantly more sensitive to the prompt. It's more capable than ever before to understand the words in the prompt, which is why you should avoid keywords like "photorealistic, 4k, 8k, award winning, etc."
The team notes that users should use the '--style raw' parameter if they want more photographic results. At the same time, you should be mindful of how you use the stylization parameter. Increased values will provide better aesthetics, while lower values will be more connected to your prompt.
Although the changes may not be massive, as someone who has been using Midjourney regularly for more than a year, I definitely needed time to get used to this new style of prompting. And I'm excited to share the results with you in the next section of the article.
Midjourney v6 Prompt Examples
Although I can talk all day about how Midjourney v6 is better than all of the previous iterations, it's best that I simply show you with prompt examples. Let's start with a simple example and then gradually work up to see what this model is truly capable of.
/imagine close-up shot of a wild horse in Iceland --style raw --ar 16:9
These are the types of prompts that I would write when I first started using Midjourney. I revisited those simple prompts just to see what the result would be like. And I'm blown away. This is the first prompt I used to test the Midjourney v6 model.
The horse is in full focus and the level of detail here is absolutely incredible. There are no words to describe how impressed I am with this iteration of the model. The background is also impressive and perfectly showcases a landscape that you'd see in Iceland.
/imagine young woman with blonde hair and an adventurous spirit is dressed in an emerald sundress smiling and taking in the sun --style raw --ar 16:9
When the Midjourey v6 model was released, the first thing I saw was people talking about how good it was when it came to generating images of people. Of course, I had to put this to the test. Notice that I used the 'style raw' option in both this prompt and the previous one. As a reminder, you should use this option whenever you want to generate a photorealistic image.
The prompt here is quite simple. I didn't want to go into too much detail so I described the age, gender, outfit, and facial expression of the character. The result looks much better than anything the previous iteration would generate. The image looks more natural.
If I were to write the same prompt and use it with Midjourney v5, I'd likely generate an image of a character looking directly at the camera. This has a more artistic feel to it. Notice that I didn't describe the environment in my prompt, but I'm impressed that the model repeatedly chooses a background that matches the clothes of this young woman.
/imagine fantasy-themed illustration showing a young sorceress practicing how to use a fireball spell
Now that I've created two photorealistic images, it's time to test the sixth iteration of the Midjourney model with an illustration prompt. I decided to keep my prompt short here. I refrained from using any keywords at the end of my prompt and focused only on providing clear instructions.
The result is amazing. The first thing I paid attention to were the hands. I know that text-to-image models sometimes have a hard time generating hands properly, but this wasn't the case here. Both hands are illustrated well. I also like the fact that the young sorceress is reading a spellbook while practicing this spell. The environment fits the theme of the image.
/imagine interior design showing a spacious home decorated in the art deco design style, the walls feature a burgundy color palette while the furniture features a pastel color palette, vintage and classy --style raw
It's become pretty popular for people to use Midjourney to create ideas for interior design. Some often generate their dream homes while others use this to easily imagine what their home could be like before they renovate.
I have an entire article dedicated to Midjourney prompts for interior design. The examples in that article were created using a previous iteration of the Midjourney model, but you can use the prompts with v6 as well.
The image I created with Midjourney v6 is almost perfect. Every object in this room blends well together. I wouldn't mind living in an apartment that looks like this.
/imagine digital painting in a glitch art style showing a far-future where people have unlocked the secrets of the great pyramid with advanced technology and used it to send a concentrated beam of energy shooting up from the top of the pyramid --style 250 --ar 16:9
My goal with this prompt was to test the coherence of the Midjourney v6 model. It's safe to say that it passed the test. I purposely included many details here to see if the model would follow the instructions. I ran this prompt six times, which resulted in creating 24 variations of the image.
Around half of the images that were created featured the concentrated beam of energy at the top of the pyramid, which is quite impressive. When using the previous iterations of the Midjourney model, it would've been much more difficult to get a result that follows all the instructions in my prompt.
/imagine macro photography, delicate spiderwebs adorned with dewdrops on a misty morning --ar 16:9 --style raw
This is the only prompt in this article that I've used before. I originally wrote it while I was writing an article on Midjourney prompts for nature. I was impressed with how v5 generated an image from the prompt, so I wanted to see what the v6 model would do differently.
Honestly, you could upload this image on social media and nobody would figure out that it was created with artificial intelligence. Once again, I used the 'style raw' option to get this type of photorealistic result.
/imagine tense scene from a thriller movie, an anxious middle aged man is sitting in a poorly lit diner with a half-eaten sandwich on the table and a cup of coffee as he's waiting for his nemesis to arrive --style raw --ar 16:9
This is another prompt that I wrote to test the coherence of the model. I wanted to include small details that I wanted featured in the image, and Midjourney v6 did not disappoint. I'm impressed by the fact that there's both a half-eaten sandwich and a cup of coffee on the table.
The main character also looks great, while the overall aesthetic of the image certainly makes it feel like a scene from a thriller movie.
Final Thoughts
Midjourney v6 was a highly anticipated upgrade. Users have been patiently waiting for months to get a chance to experiment with this model, and the moment has finally arrived. The sixth iteration of the Midjourney model is more powerful than ever before.
The quality and level of detail featured in the images made with Midjourney v6 is nothing short of amazing. I haven't personally been this excited for Midjourney in a while. It's almost as if I'm using a completely different text-to-image tool developed by a new company.
It's worth noting that there have been massive changes to the Midjourney model with this iteration. The most notable is the model's enhanced ability to understand instructions, thus removing the need to clutter prompts with random keywords. The model has become insanely sensitive to the words used in a prompt, so you should use them wisely.
Another impressive feature is the introduction of the minor text drawing ability. You can now put words in quotation marks within your prompt to have the text featured in an image.
