Imagine Weekly – Issue 24 [November 18th]

Author

Daniel Reiser
November 18, 2024

Welcome to Issue 24 of Imagine Weekly 👋

Hi everyone, and welcome back. Hope you all are well and not sick. I am still haunted by the flu and this time it’s really stubborn. So sorry for the slight delay of this weeks issue. As this newsletter is not about me, let’s put my health aside and dig right in.

Midjourney is on the verge of significant advancements, as revealed during their recent office hours. The team is focused on enhancing user experience and personalization with projects like v7 training and the v6 video model training, which aim to transform user interaction with the platform. New features such as mood boards, multiple profiles, and demographic profiles are in development, alongside insightful blog posts on demographic and psychometric profiling. In storytelling, new tools are being tested with guides and moderators, with plans for community release soon. Although 3D projects are paused, they will eventually be integrated into the video models, adding a new dimension to the Midjourney experience.

🤖📋 Have you checked out Midjourney Parameter cheat sheet, it’s free. Head over to Midjourney Cheat Sheets and give it a try. This is still an early release and work in progress. I’ll introduce more features over time. If you want to see something specific, feel free to reach out [email protected].

In this issue you’ll find:

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

  • 🛠️ Tools to explore

  • 🎨 Some new srefs to tinker with

📅 Office Hours TL;DR; Recap 2024-11-13

🚀 Ongoing Projects: Midjourney is advancing v7 and v6 video model training, with new personalization features and storytelling tools in the pipeline.

🎨 Consistency and Personalization: Improvements in character references and image batch planning are underway for a more personalized experience.

🎥 Video Model and Personalization Tests: The v7 video model introduces "image -> video" scaling, with research on demographic influences on aesthetics.

🔧 v7 Improvements and Launch Preparations: A new prompting style and multilingual support are coming with v7, with a gradual feature rollout.

📈 Feature Deployment Optimization: Despite challenges, Midjourney plans to offer monthly subscriptions and an image editor with v7.

👥 Ongoing Model Development and Team Priorities: The team seeks web developers to enhance model development and user experience.

🌟 Community Engagement: User feedback is crucial, with discussions on new features like an image editor and mobile interface.

🙏 Conclusion and Closing Message: Midjourney thanks the community and plans a beta release of v7 with community-driven adjustments.

🔧 Model Improvements: Enhancements in personalization, image, and video quality on the horizon. If you want to get more info, read the extended recap.

It's amazing how far we've come. Midjourney was released in February 2022 and has evolved into something that was beyond our imagination at the time.

Marcus B. on LinkedIn: Midjourney Evolution | 10 comments

Midjourney Evolution. Midjourney was released in Feb 2022. The rate of change in such a short time is incredible, visually explored with the following prompt:… | 10 comments on LinkedIn

www.linkedin.com/posts/marcus-byrne_midjourney-evolution-ugcPost-7262948782433021952-f_tc?utm_source=share&utm_medium=member_desktop

An increasing number of brands are choosing to incorporate AI into their advertising campaigns. Even Coca-Cola is utilizing AI in their iconic Christmas ad campaigns. Another example is MANGO—take a look at these incredible images. You'd never guess they were created using AI if it wasn't mentioned.

There are many artists out there, leveraging Midjourney to create amazing pieces. This interview with Sy Goldstein.

Inside Sy Goldstein’s Alternate Reality | Dream Prompts

Explore the captivating world of Sy Goldstein, an AI artist reimagining 1980s New York through surreal, almost-human characters. Discover how his unique blend of nostalgia and digital portraiture, inspired by classic street photography, has sparked a dedicated following and reignited his creative passion.

dreamprompts.ai/featured-artists/sy-goldstein

Text to image, image to video, video to video—there are so many possibilities for generating content with AI. Let's take it a step further: image to reality.

🛠️ Tools

If you haven’t already, check out Tripo. You can go from 2D to 3D meshes in no time. It even has an API so creating a compfy workflow is something great to explore.

Luke Hurd on LinkedIn: ComfyUi+Tripo makes 2D->3D mesh AI gen a snap. You can use a single image… | 110 comments

ComfyUi+Tripo makes 2D->3D mesh AI gen a snap. You can use a single image (the coffee table, in this example) or multiple images of an object for more detail… | 110 comments on LinkedIn

www.linkedin.com/posts/lukehurd_comfyuitripo-makes-2d-3d-mesh-ai-gen-a-activity-7262934960125206529-pyrE?utm_source=share&utm_medium=member_desktop

🎨 Inspiration, Prompts and Srefs

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.

To support me:

☕️  I’d be happy about a coffee

Buy Me A Coffee

😘 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!