Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

More difficult examples:

- wine glass that is full to the edge with wine (ie. not half full)

- wrist watch not showing V (hands at 10 and 2 o'clock)

- 9 step IKEA shelf assembly instruction diagram

- any kind of gymnastics / sport acro



What's the reason to test the "not showing ..."? I've never seen anyone make that kind of request in real life. They ask for what they actually want instead. You'd ask for a clock showing 3:25 rather than "not 10:10".

I mean, it's a fun edge case, but I'm practice - does it matter?


Problem is that watchmakers always set the watches to show V with clock hands when they market their watches. This causes a very strong bias in image generation models, making it very difficult for them to generate watch that shows any other time, even if user requests it.


> I mean, it's a fun edge case, but I'm practice - does it matter?

*in practice, not I'm practice. (I swear I have a point, I'm not being needlessly pedantic.) In English, in images, mistakes stick out. Thus negative prompts are used a lot for iterative image generation. Even when you're working with a human graphics designer, you may not know what exactly you want, but you know that you don't want (some aspect of) the image in front of you.

Ie: "Not that", for varying values of "that".


> Thus negative prompts are used a lot for iterative image generation.

Are they still? The negative keywords were popular in SD era. The negative prompt was popular with later models in advanced tools. But modern iterations look different - the models capable of editing are perfectly fine with processing the previous image with a prompt "remove the elephant" or "make the clock show a different time". Are the negative parts in the initial prompt still actually used in iteration?




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: