Midjourney just introduced the alpha testing phase of its latest Midjourney V6 model. This release is a significant progression from the previous major version, V5.2, which was released six months ago.

The new version boasts improved accuracy, greater coherence, and a range of new, advanced features. Being in its early stages, users should be prepared for frequent updates and refinements as the model continues to evolve.

How to Start with V6 ?

Activate V6 by selecting it in /settings or adding --v 6 to the prompt.

Key Enhancements in V6

• Much more accurate prompt following as well as longer prompts
• Improved coherence, and model knowledge
• Improved image prompting and remix
• Minor text drawing ability (you must write your text in "quotations" and --style raw or lower --stylize values may help)
• Improved upscalers, with both 'subtle' and 'creative' modes (increases resolution by 2x)

Style and Prompting For V6

• Prompting with V6 is significantly different than V5. You will need to 'relearn' how to prompt.
• V6 is MUCH more sensitive to your prompt. Avoid 'junk' like "award winning, photorealistic, 4k, 8k"
• Be explicit about what you want. It may be less vibey but if you are explicit it's now MUCH better at understanding you.
• If you want something more photographic / less opinionated / more literal you should probably default to using --style raw
• Lower values of --stylize (default 100) may have better prompt understanding while higher values (up to 1000) may have better aesthetics

Now, let's explore some examples highlighting the new features.

Text Creation Within AI-generated Images

The Midjourney V6 introduces the advanced capability of precise text creation within AI-generated images. In the following demonstration, I will illustrate how this text integration functions using various examples.

Prompt : Visualize "Carpe Diem" artistically scribbled with a vibrant red sharpie on a small whiteboard, with colorful doodles of stars and suns around the text. — v 6.0 — ar 16:9 — style raw

Prompt : A picture of "Dream Big" written in bold, chunky letters with a black chalk marker on a green chalkboard, adorned with whimsical chalk drawings of clouds and stars. — v 6.0 — ar 16:9 — style raw

Prompt : Create an image of the word "Inspire" neatly printed with a fine-tip gold gel pen on a dark blue sticky note, placed on a light wood desk surface next to a potted succulent. — v 6.0 — ar 16:9 — style raw

Prompt : Depict "Adventure Awaits" in adventurous, flowing script using a white paint marker on a smooth, round, black river rock, with a backdrop of a map and a compass. — v 6.0 — ar 16:9 — style raw

Prompt : The words "Stay Curious" elegantly handwritten with a silver calligraphy pen on a piece of translucent tracing paper, overlaid on a background of a starry night sky. — v 6.0 — ar 16:9 — style raw

Prompt : "Be Bold" boldly lettered in neon pink graffiti style on a gritty urban brick wall, with a faint silhouette of a city skyline in the background. — v 6.0 — ar 16:9 — style raw

Prompt : "Explore More" depicted in adventurous, stencil-style letters sprayed with a green spray paint on a rustic, reclaimed wooden sign, set against a backdrop of dense, green forest foliage. — v 6.0 — ar 16:9 — style raw

We can also try some text of some famous brands.

A summer beach scene with a group of friends laughing around a bonfire, a cooler filled with ice-cold "Coca-Cola" bottles in the foreground, capturing the essence of refreshing fun. — v 6.0 — ar 16:9 — style raw

An urban street food setting showcasing a vibrant "KFC" bucket overflowing with crispy fried chicken, placed on a rustic wooden table with city lights in the background, highlighting a casual, delicious meal. — v 6.0 — ar 16:9 — style raw

A sleek, modern kitchen scene with a person wearing fitness gear, holding a "Nike" water bottle, with a blurred background of healthy foods and gym equipment, focusing on a lifestyle of health and athleticism. — v 6.0 — ar 16:9 — style raw

Comparison with V5.2

Now let us do a comparison of the outputs from Midjourney versions 6 and 5.2, utilizing an identical prompt, to observe the distinctions in their aesthetic qualities.

Bee nest: Macro photography, bee nest, up of the intricate patterns of the nest, pattern. The image should convey

Dandelion seed : Macro photography, dusk, when the light, golden, find a dandelion, seed head intact, lighting scenario like backlighting, shape of the dandelion seed, image should, whimsy

High Key Portraits: Craft a high key portrait of a woman in a white dress, surrounded by a bright, airy environment. The lighting should be bright and soft, highlighting the woman's features and the purity of the setting.

Photojournalistic Portraits: Create a photojournalistic portrait of a firefighter in the midst of a rescue operation, showing determination and bravery. The lighting should be dramatic, highlighting the firefighter's focus and the intensity of the situation.

Create glamorous and stylish portraits, often featuring fashion, beauty, and luxury.

Summary

The introduction of Midjourney V6 represents a significant leap in AI-driven image generation, notably highlighted by its new text generation feature. This advancement allows for seamless blending of text into AI-created images.

In comparison to the earlier V5.2 version, V6 not only improves in terms of prompt accuracy and coherence but also offers a noticeably better aesthetic experience.

As V6 continues to evolve, we can anticipate the addition of more features and further refinements. The future of Midjourney V6 looks promising, with potential for even greater creativity and innovation in AI image generation.