Leo's Lightbulbs

Merry xmas to one and all!

Hello everyone and welcome to Leo’s Lightbulbs! I’ll be covering the top news from the past week every Monday morning in your inbox. This newsletter was written completely by hand, without any AI assistance or even AI editing.

So, let’s jump right in! What happened in AI this week?

TL;DR

Leo’s thoughts this week

Midjourney 6 has been the talk of the town this week. Its graphical improvements definitely solidify its lead as best-in-class for graphics, but the /tune feature sees no new improvements. There is also basic text ability but worse than DallE by far. Don’t get me wrong, I still use Midjourney a lot, but what I’m looking for next is the ability to understand a sentence with multiple characters and complex subjects. An example: this week I was generating an Asian woman in Times Square in Midjourney, and it makes all the signs in Chinese. Interestingly, Google’s Imagen2 is best in class at following complex instructions for now, even though the quality of its images is usually subpar.

I’m excited to see what comes next in video generation! Pika’s new video generator release was a pleasant surprise, and I’m still hoping for an announcement any day from Moonvalley, which has had a less well known video generator in beta for some time now. Runway also must be up to something, they’ve been quiet lately and have lots of money.

Have a wonderful week everybody! I check this email address ([email protected]) daily, so don’t hesitate to reply with any thoughts or questions for a chance to get featured next week!

Yours,

Leo💡

Oh, btw, my 🎙️Podcast🎙️ launched! Check it out on Youtube, Spotify and Apple Podcast!🎙️🎙️

Reply

or to participate.