ChatGPT understands text and images, and it is not using the diffusion method like other AI image generators, so that is why it is so much better and more accurate.
But never forget, that ChatGPT has a image model that powerful INTEGRATED into a multimodal AI system. And still it shines compared to a lot other stand-alone models. That's the impressive part for me, that you get the whole package with ChatGPT - I think that the idea of a holistic AI system is the future.
I’ve Been doing some experiments taking MJ prompts and and using ChatGPT to translate the prompts to work in other models and platforms. Using the same prompt (something I’ve tested for years now) doesn’t really work well. Results often are drastically different. Taking the Midjourney prompt along with a few sample results I have chatGPT also do an in depth analysis of the styles and techniques. I then have it create prompts for Reve, Leonardo Ai, NIM Ai and ChatGPT. The prompts are often very different since the tokens that each model understands is often very different. Results can differ depending on the subject. Photography styles work best doing this. I find most other platforms don’t handle illustrations as well as MJ / Niji , or at least in my tests to date. The idea of “ Hey learn this prompt” is meaningless since each platform understands language in a slightly different way which to be honest is annoying. Having to learn the quirks of each platform/ model is too much. But using ChatGPT as a translator helps and makes the process more accurate.
Nice video. Many videos deal with "consistent character", but a video testing "consistent background" in Midjourney, ChatGPT, Leonardo, and ComfyUI would be very interesting.
Damn, Midjourney has been training everyday with people generating stuff with their daily keywords. And it wasn't enough.
yes please do a comparoson of different image generators , specially character consistency
Also one good test is to try to make giants and giants interacting with normal size people. Such fantastical things MJ STILL fails at that after all this time. ChatGPT nails it easily
Excellent video. I'm now a new subscriber. It's kind of amazing to me that chatGPT has come so far, so fast, in image creation that it's already being compared to MidJourney and doing pretty well in the matchup.
yeah, please test all the other image generators! Great comparison.
Man, thanks SOOO much for doing these videos. Updates poppin' up like weeds!
Thanks for posting. Great video.
a comparison video with a conclusion, how fun
I'm happy to know that Chatgpt overcome the Midjourney, because we just only pay 1 subscribtion to get the best text and AI image
Thanx a lot! 👍💚
The key is to combine them.
Thank you my future man
thank you! looking forward to the video including all models!
Super helpful! Thanks for the side by side comparison!
Really loving ChatGPT for just how damn good it is, but putting them side by side here with midjourney you really see it does suck at style and feels way too basic, it's a chore to try and get it to not generate in it's default sort of grungy basic look. Also it's inpainting and editor I find basically useless, it still regenerates the whole image at a worse quality, you're usually better off just regenerating from scratch with a new prompt. I think this 12:16 is just such a great example of it getting the prompt right but just applying its same basic style to everything in a uninspired way, where midjourney looks so much better in terms or style, I would say there's a clear winner here.
@jehhuty