Midjourney released a surprise new update this week and it's a much bigger deal than its numbering would suggest. Version 6.1 would hint at a few minor changes but with it, we’ve got more natural looking people, improved text rendering, and even better upscaling.
According to the AI image lab, we should get version 6.2 in the next month or so, which suggests more regular iterative updates may be the norm going forward, rather than making everyone wait until version 7 finishes training and testing.
This approach makes sense as each major new version of a model will require more computing power, time, and data to scale beyond the current generation. Whereas fine-tuning and prompt improvements can make a big difference fairly quickly to current models.
The latest update also comes with better styling and improvements to personalization. To access it you just need to append –v 6.1 to the end of a prompt.
Creating prompts to test Midjourney v6.1
I’ve tried to come up with prompts that test different aspects of the new features, particularly around skin and human features, text rendering and some of the style changes.
1. Holding a butterfly
The first prompt is an examination of how well Midjourney renders both the fingers and the complexities of a butterfly. This should push the texture generation.
Prompt: “Hyperrealistic close-up of a human hand holding a delicate butterfly, intricate details on fingertips and wings, soft natural lighting --v 6.1.”
2. A bright neon sign
The aim here is to test two things, the ability to render text accurately and stylishly within a complex scene, as well as the improved styles such as 8-bit and pixels.
Prompt: "“Welcome to Paradise" neon sign in a bustling cyberpunk cityscape, 8-bit retro aesthetic with enhanced pixel textures --v 6.1.”
3. A majestic lion
This was as much because its cool to see how well Midjourney produces images of a lion, but it also pushes it to render complex textures and lighting.
Prompt: “Majestic lion with a flowing mane standing atop a rocky outcrop, distant savanna landscape, golden hour lighting, ultra-high detail fur textures --v 6.1.”
4. Lush greenery
Here, we're exploring how well Midjourney v6.1 can render complexity. Specific vivid flower details and leaf patterns while also showing a depth of field.
Prompt: “Lush botanical garden with diverse exotic plants, focusing on intricate leaf patterns and vibrant flower details, soft depth of field --v 6.1.”
5. Ballet dancer leaping
This prompt is designed to test how well 6.1 captures fluid motion and dynamic movement. It needs to add a controlled illumination and render hands at a distance.
Prompt: “Full-body portrait of a ballet dancer in mid-leap, capturing fluid motion and muscle definition, soft studio lighting --v 6.1.”
6. Wise Eyes
This prompt puts Midjourney to the test in its promise of improved skin texture rendering, putting the face front-and-center.
Prompt: “Portrait of an elderly wise woman with deep wrinkles and expressive eyes, soft natural lighting emphasizing skin texture and facial features --v 6.1.”
7. Street Photography
Not only does v6.1 have to accurately render multiple people but it also pushes it to render a complex realistic scene. It has to capture individual details on multiple characters.
Prompt: “Candid street photography of a bustling city crosswalk, diverse crowd with varied expressions and poses, focus on individual details in a group context --v 6.1.”
Final thoughts
While some of the improvements might be subtle, there is a noteworthy improvement in texture generation and in upscaling. For each test, I ran the final image through a creative upscale and the improvement was more noticeable than with version 6.
I like that Midjourney is moving to focus on iterative updates as they build towards what I suspect will be a major change with v7, likely creating the start of a better world model.
