Matt Wolfe compares GPT 4o and Midjourney for image generation. Midjourney makes beautiful images but often misunderstands requests, while GPT 4o better interprets what you actually want. Wolfe used GPT 4o to edit a YouTube thumbnail repeatedly: changing his facial expression, swapping text to "WTF", adding Padres imagery, and generating versions in GTA 5, Rick and Morty, South Park, and Minecraft styles.
It's crazy how it seems like really understand images midjourney can make really beautiful stuff, but it doesn't seem to really understand what you're asking it, right? Like, but 4o does actually seem to get what you're talking about.
I was actually using it where I made thumbnails for my YouTube video. The thumbnail at the top here that you can see was actually one that my designer made, but I took the one that the designer made and then I started, like, step by step tweaking it to get something more out of it. So I wanted it to, like, change my facial expression and put WTF in it instead of worth it. And you can see it made pretty much the same thumbnail, but just change the text and change the face a little bit. Right? I threw in some images of, like, the Padres because baseball season starting and I told to make this image in GTA 5 style. I told it to make it in Rick and Morty style. And then I was sending these, these to some of my friends who are not Padre fans to sort of troll them a little bit. Put an image of myself, south park version, Minecraft version. I've been nerding out over this. Like, I've been pretty much my whole day so far today has been spent playing with this stupid tool.
AI News: Dots, GPT-6.1 Sol, Sonnet 5.5, Gemini 4, and everything you need to know
