Image generation has come a long way since August 2022
A Hacker News discussion of a blog post comparing early AI image generators with today's models. Commenters ask for side-by-side comparisons, and one shares a benchmark tracking prompt adherence since the SDXL days of 2023, with a progress metric showing how models like Ideogram4 and Moss-Image score over time. Others note they sometimes prefer the rougher early outputs to today's hyper-polished images.
In some ways I prefer looking at these over the hyper-polished 2026 image generators tbh.
- gavmor
Images without prompts and statistics are... meaningless. We don't know if/how these adhere, whether they took a thousand hours or a thousandth of a second.
> “Would you tell me, please, which way I ought to go from here?”
> “That depends a good deal on where you want to get to,” said the Cat.
> “I don’t much care where—” said Alice.
> “Then it doesn’t matter which way you walk,” said the Cat.
(Lewis Carroll)
- pants2
No modern or over-time comparisons?
In some ways I prefer looking at these over the hyper-polished 2026 image generators tbh.
- karim79
Oh my gosh. Makes me want to wake up my comfyUI setup on a RTX 2080 egpu which still works like a charm today even. I think the last time I touched it was about two years ago!
I always found the commercial stuff to be complete rubbish. I was astounded by how I could just spend a couple of hours using open models and open source software to produce better results.