Live data from Hacker News

Show HN: New AI edits images based on text instructions

github.com

61–70 of 241 posts

Re: Show HN: New AI edits images based on text instructions

#61

Earlier quoted context omitted.

Haven't we been here before? - see self driving cars.

I've certainly seen this argument before.. Yes, it's true that not all technology evolves as fast as predicted (by some, at some point), but first of all I still believe we will see self driving cars in the future and secondly, it's one anti-example in a forest of examples of tech that evolves beyond anyone's expectations. I don't find it very convincing.

Autonomous driving as it currently exists came unexpected for most people. Now many look at it with the power of hindsight but back in the day the majority never thought we'd have cars (partly) driving on their own within a few years. The case of AI art seems the exact same to me, now that many are working on it there's lots of progress but it's still nowhere near what an experienced human can do. And that seems to be the general rule, not an exception.

We might need to create real intelligence for that to become true. A machine that can think and is aware of its purpose.

Re: Show HN: New AI edits images based on text instructions

#64
post #62

How does this work? When I run it on a machine with a GPU (pytorch, CUDA etc installed) I still see it downloading files for each prompt. Is the image being generated on the cloud somewhere or on my local machine? Why the downloads?

Shouldn't be downloads per prompt. Processing happens on your machine. It does download models as needed. A network call per prompt would be a bug.

Re: Show HN: New AI edits images based on text instructions

#65
post #42
post #28

It's a little premature, fine, but I want to start liquidating my rhetorical swaps here: I've been saying since last summer (sometimes on HN, sometimes elsewhere) that "prompt engineering" is BS and that in a world where AI gets better and better, expecting to develop lasting competency in an area of AI-adjacent performance (a.k.a. telling an AI what to do in exactly the right way to get the right result) is akin to…

Been doing a lot with prompts lately. What people are calling "prompt engineering" I'd call "knowing what to even ask for and also asking for it in a clear manner". That was a valuable skill before computers and will continue to be one as AI progresses. I've been pretty disappointed to introduce ChatGPT to people in jobs where it would be a game changer and they just don't know what to do with it. They ask it for not…

> I'd call "knowing what to even ask for and also asking for it in a clear manner".

It was a very important skill for searching. Nowadays, with Google "I know what you want better than you" search, it’s not that useful anymore (not useless, I get better search results by not using google and knowing what I want, just less required).

Re: Show HN: New AI edits images based on text instructions

#67

It's very interesting, thanks! I've noticed (on the Spock example) that "make him smile" didn't produce a very... "comely" result (he basically becomes a vampire). I was thinking of deploying something like that in one of our app features, but I'm scared of making our Users look like vampires :-) Is it your experience that the model struggles more with faces than with other changes?

Yes if you're not careful it can ruin the face. You can play with the strength factor to see if something can be worked out. Bigger faces are safer.

Re: Show HN: New AI edits images based on text instructions

#69
post #50

Many thanks to the OP, can't wait to try this out! I have a question I'm hoping to slide in here: I remember there were also solutions for doing things like "take this character and now make it do various things". Does anyone remember what the general term for that was, and some solutions (pretty sure I've seen this on here, apparently forgot to bookmark). PS: I'm not trying to make a comic book, I'm trying to help a…

dreambooth perhaps?

Re: Show HN: New AI edits images based on text instructions

#70
post #28

It's a little premature, fine, but I want to start liquidating my rhetorical swaps here: I've been saying since last summer (sometimes on HN, sometimes elsewhere) that "prompt engineering" is BS and that in a world where AI gets better and better, expecting to develop lasting competency in an area of AI-adjacent performance (a.k.a. telling an AI what to do in exactly the right way to get the right result) is akin to…

Prompt engineering already exists, it's called management.
Post reply on HN