[krainboltgreene]

> The gap of being distinguishable from manually drawn images is still closing

People have been trumpeting this since day one of Stable Diffusion releasing, but I'm seeing the same output quality as that day and I've been keeping up.

[tavavex]

Just because the pace of progress isn't exponential (like what some people would want to believe) doesn't mean it isn't happening. I remember getting an early invite to DALL-E 1 all the way back, and while I don't use it anymore, the modern improvements made seem very substantial. From plain comparisons of different versions where the same inputs produce substantially better outputs, to the mere fact that the latest version can actually generate decent, often discernible text at all (something that people joked would be impossible from AI to achieve) shows that some progress is being made.

The reason why it's not as visible with Stable Diffusion is because a lot of the technologies around it circle the same few foundational SD models - people build on top of them, add new ways of interacting with them, but ultimately, the same thing underlies them all. Community support is seen as more important than cutting-edge tech, which is why something like Stable Diffusion XL hasn't even seen universal adoption yet.

[krainboltgreene]

I'm telling you the progress isn't happening based on my own consistent observations of various releases across multiple platforms. The only people who don't seem to agree with me are those who have the art literacy of a highschooler and think "discernible text" is a improvement.

As an aside, no one said AI couldn't achieve drawn generated text, that's been possible for years prior to stable diffusion.