Imagine Weekly – Issue 9 [August 2nd]

Welcome to Issue 9 of Imagine Weekly 👋

Hello everyone,

This week, we have an exciting update featuring Midjourney v6.1 along with several other great new additions to explore.

In this issue you’ll find:

• 📖 TL;DR; Weekly Recap of the Office Hours (or the extended recap)

• 👀 Details on the v6.1 release

• 🎓 How to find similar images in the midjourney web ui

• 🎨 Some new srefs to tinker with

Office Hours TL;DR; Recap 2024-07-31

📸 Midjourney 6.1 Release: Sharper images, better text rendering, enhanced upscalers. (More on this down below)

📊 User Data and Bias: Focus on reducing biases while using user feedback.

🔜 Upcoming Releases: Midjourney 6.2 in a month, last in the 6 series.

🌟 Midjourney 7.0 Development: Enhanced aesthetics, faster performance, smarter prompts.

🛠️ Other Projects: 3D models, video capabilities, storytelling tool, web-based improvements.

🔮 Future Considerations: Debate on 6.x vs. 7.0, higher resolution, video, and 3D priorities.

📅 Immediate Plans: Attempting 6.1 zoom-in painting feature this week.

👀 Details on the Midjourney v6.1 release

🌟 More coherent images, including arms, legs, hands, bodies, plants, and animals.

📸 Significantly improved image quality with reduced pixel artifacts and enhanced textures, including skin.

🔍 Greater precision and detail in small image features, such as eyes, small faces, and distant hands.

🔄 New 2x upscalers that offer superior image and texture quality.

⚡ Approximately 25% faster performance for standard image tasks.

✍️ Enhanced text accuracy when generating words using “quotations” in prompts.

🎨 A new personalization model that offers improved nuance, surprise, and accuracy.

🗂️ Personalization code versioning, allowing the use of any personalization code from previous jobs to apply the corresponding model and data.

⏳ A new --q 2 mode that takes 25% longer but may add more texture at the expense of reduced image coherence.

🌺 Overall, images should appear “generally more beautiful” across the board.

🎓 How to find similar images in the midjourney web ui

I'm a huge fan of the MidJourney web UI. I recently found out that you can search for similar images. Whether you're in the Explore section or the Create section, you can click on an image you're interested in to view its details. In the top right corner, next to the prompt, there's a small magnifying glass icon that you can click.

You will then be redirected to the Explore section, where you'll see a grid of similar images.

That's already a neat feature, but it gets even more powerful. If you pay close attention to the search input, you'll notice the URL of the image. The cool thing is that the search input accepts any image URL, not just those generated by MidJourney. So, you can copy the URL of your favorite image and paste it into the search.

Happy exploring! 🌄

🌈 Related

Always interesting to see how different tools are used in combination to create such results!

Hollywood will never be the same…

...well, for now, we're safe, I guess, looking at the current state. But that won't take long to change, I suppose. Check out this wild video. Most of the results from video-generating AIs probably look like this. At least, that's been my experience when using RunwayML, LumaAI, and similar tools.

🎨 Inspiration, Prompts and Srefs

For today's issue, I've gathered some bold srefs for you to save and tinker with.

See you next week 👋🤖

I hope you enjoyed this issue of Imagine Weekly. If you found it helpful, we'd be thrilled if you could share it with your colleagues and friends. Please feel free to reach out with any suggestions or feedback.

Have a great weekend:

To support me:

😘 Recommend the newsletter to your friends: it really helps!

📬 If you’re not subscribed yet to my newsletter Imagine Weekly, I’d be thrilled to welcome you on board!