A steampunk platypus, a cyberpunk goose, and a dieselpunk duck walk into a club...
I don't have a ton to add here other than I'll probably stay away from Reve for a while, but I must comment on this:
"Fun fact: In my head, I hum the words “Text-to-Image Model Showdown” to the chorus of “Teenage Mutant Ninja Turtles”—and now it’s in your head, too!"
First, good for you! This is important work, and I'm glad somebody is doing it. However, now I'm concerned: what comes next?
I'm envisioning something like:
Text-to-Image Model Showdown
GPT 4 will win again
But that's kind of lame. It goes w/the rhythm, but it's also kind of self-defeating. Thoughts?
Reve Will Live Forever...In Your Nightmares!
It really should've been obvious.
These are always fun.
Or, in Reve’s case, traumatizing.
I hate to complain, but I think you've inadvertently favoured 4o by not letting the others enhance the prompt, while 4o does this quietly behind the scenes. I want a rematch!
All right, I'll bite!
I just let Reve enhance the last prompt behind the scenes. Here's the enhanced prompt it wrote up:
https://i.imgur.com/mYXZiNw.png
Here are the four resulting images:
https://i.imgur.com/qBOfEnO.png
I'm not sure "slightly less nightmarish" is a major improvement here!
Thanks Daniel, great article. I've been out of the AI loop for a bit and it's certainly impressive to see how far things have come.
Native image models vs. diffusion image models?
GPT-4o is within the paid version of ChatGPT, yes?
They even give free accounts something like three free images a day, last I heard!
Thanks, will take another look!
I don't have a ton to add here other than I'll probably stay away from Reve for a while, but I must comment on this:
"Fun fact: In my head, I hum the words “Text-to-Image Model Showdown” to the chorus of “Teenage Mutant Ninja Turtles”—and now it’s in your head, too!"
First, good for you! This is important work, and I'm glad somebody is doing it. However, now I'm concerned: what comes next?
I'm envisioning something like:
Text-to-Image Model Showdown
Text-to-Image Model Showdown
Text-to-Image Model Showdown
GPT 4 will win again
But that's kind of lame. It goes w/the rhythm, but it's also kind of self-defeating. Thoughts?
Text-to-Image Model Showdown
Text-to-Image Model Showdown
Text-to-Image Model Showdown
Reve Will Live Forever...In Your Nightmares!
It really should've been obvious.
These are always fun.
Or, in Reve’s case, traumatizing.
I hate to complain, but I think you've inadvertently favoured 4o by not letting the others enhance the prompt, while 4o does this quietly behind the scenes. I want a rematch!
All right, I'll bite!
I just let Reve enhance the last prompt behind the scenes. Here's the enhanced prompt it wrote up:
https://i.imgur.com/mYXZiNw.png
Here are the four resulting images:
https://i.imgur.com/qBOfEnO.png
I'm not sure "slightly less nightmarish" is a major improvement here!
Thanks Daniel, great article. I've been out of the AI loop for a bit and it's certainly impressive to see how far things have come.
Native image models vs. diffusion image models?
GPT-4o is within the paid version of ChatGPT, yes?
They even give free accounts something like three free images a day, last I heard!
Thanks, will take another look!