Imagine Weekly – Issue 32 [January 21th]

Author

Daniel Reiser
January 21, 2025

Welcome to Issue 32 of Imagine Weekly 👋

The Midjourney team is hard at work refining the much-anticipated V7 model, which promises to bring enhanced multilingual support, improved coherence, and better character references. However, the journey hasn't been without its hurdles. Data quality issues in the new dataset have caused delays, pushing the launch from January to February. The team is committed to ensuring that the V7 model meets high standards, even if some aspects of image quality and aesthetics may need further refinement beyond this release.

How do you like Imagine Weekly? Is there anything I can do differently? Anything you want to see more or less of? Just shoot me an email [email protected] ✉️

In this issue you’ll find:

  • 📖 Office Hours TL;DR

  • 🛠️ Tools to explore

  • 🎨 Some new srefs to tinker with

📖 TL;DR

🚀 V7 Model: Launch delayed to February for data quality improvements; aims for better multilingual support and character references.

🎥 Video: Exploring high-quality vs. fast, cheaper options; considering in-house vs. external APIs.

🖼️ 3D: Promising tests; potential feature launch soon; long-term integration with open-world simulations.

🔄 V6.2: Interim release for larger batch sizes and improved personalization.

👥 Character References: V7 to improve consistency; potential for "omni-reference" capability.

💰 Cost & Community: Budget limits on expensive models; goal to remain community-supported.

⚖️ Model Tiers: Exploring fast vs. slow models; community desires affordability.

🔮 Future Vision: Rapid improvements expected; considering advanced features and balancing projects.

🗣️ Feedback: Focus on character creation, consistency, and collaboration tools; updates to Explore page underway.

Didier Quarroz 郭荻 on LinkedIn: One of the aspects I like most about MidJourney is that you can do very…

One of the aspects I like most about MidJourney is that you can do very photorealistic visuals but also very unique styles. Especially blends tend to create…

www.linkedin.com/posts/guodi_one-of-the-aspects-i-like-most-about-midjourney-activity-7285934096394989568-48ni

🛠️ Tools

Hector Rodriguez on LinkedIn: Today I tried and I failed. I do a lot of that with tool testing. I…

Today I tried and I failed. I do a lot of that with tool testing. I tried to see if I could do image-to-3D for packaging concepts, but Krea's 3D shows too…

www.linkedin.com/posts/hrodriguez1_today-i-tried-and-i-failed-i-do-a-lot-of-activity-7287386432057290752-4eli

Sachin Kamath↗️ on LinkedIn: #aivideo #aitools #aianimation | 20 comments

This is so INSANE! Hunyuan AI’s new video-to-video model can replace actors in any film scene—and it doesn’t stop there. It captures even the subtlest facial… | 20 comments on LinkedIn

www.linkedin.com/posts/sachinkamathai_aivideo-aitools-aianimation-activity-7287136800555327488-9Dys

🎨 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!