jarrenae

I'm excited to see the next versions of Stable Diffusion. I think we'll probably see this improve significantly over the next year.

haha well I hadn't considered this, but you've actually stumbled upon something interesting. Duly noted!

We're using a synonym API that's separate from the image summoning. Basically our filtering happens after the synonym API, but before the image summoning API.

100% Agreed on this one. I was really hoping we'd have that feature ready before launching today. Hopefully we'll have an early version up in the next week or so.

Yeah, unfortunately uncanny valley is spot on for most generated faces with this version of Stable Diffusion.

I've seen some people tackle the problem by running faces through a secondary AI that makes faces look "better" [1] though in this case "better" just means "pretty" by recent western standards, so that has its own set of shortcomings.

I'd be interested to hear what you think about the inanimate object searches?

[1] https://replicate.com/tencentarc/gfpgan

Thanks a lot! Of course Stable Diffusion is doing most of the heavy lifting here, but we're working hard to make the UI way more user-friendly and provide real lasting utility.

If you have any suggestions, I'm all ears.

I'm interested to hear why you think so? If theres's something specifically wrong with what we've built that we could possibly improve, I'd appreciate the feedback.

Interesting. Over time we'll be working to improve more specific searches to prevent unusual errors. Right now we're just loosely comparing letters in searches.

And yeah, our servers are working overtime, but what's fun is that as more images are generated, there's less of a need to "bulk generate" because many searches show existing results.

Also we'll have to add reporting for specific search terms. We do have a NSFW filter on by default, but there are often things that skirt around the rules while are hard to filter for.

You're absolutely right. We'll likely have a fix rolled out for this and a few other things on Monday.

Seances aren't easy things to get working with ones and zeros.

For more vague terms, this probably won't do too well for a while, but this definitely isn't going to "replace" anything else completely in the near future. It's really intended to be a new tool to add to the toolbox.

That's sort of the reason we started building this. I think there will absolutely always be room for paid, high quality stock photos, but "content" at the speed of thought is here, and I'm excited to see how the space evolves.

I can't wait either. We're going to add follow-up solutions to upres, expand, and improve facial features. Additionally, we're aiming to improve search terminology on the back end to start providing more relevant results for exactly those sorts of searches.

In V2 we're planning to add a voting system and additional filtering/tagging to solve for a lot of these unusual/nightmareish summoned images.

I for one am sorry for your cockroach salad jump-scare, but of course, you know summoning from beyond is tricky business.

We're going to add voting to help empower users to sort between better/worse summoned images. And an API tool for devs to leverage is planned as well.

Exactly. We'll improve button location in another iteration.

Agreed. Mobile we have an added "Search" button appear, but that's on my list of improvements to make.

Agreed. That's already one of the things I have on the list for v2, "make image summoning more obvious/loading" and also we'll improve the button location for "Summoning new images" because it's likely that users won't want to scroll to the bottom just to generate new images.

I've actually been working on a stock photos site built around Stable Diffusion for some of these exact reasons. https://ghostlystock.com/ is the first version, but we're adding a bunch of useful features to make it more useful for people to find legitimately useful stock images.

Hi HN! I made this little project because I wanted a way to easily search for things in specific years, so I’d be able to search web history, or backdated articles or stuff like that. Search A Year lets you just search for anything, but can target current, or historical years. I’ve found it helpful when searching for recent answers to questions about the best products to buy, or for finding older results.

Also, fwiw, we built OldestSearch.com a few months ago, and it had some novelty and HN seemed to like it, but it made me think it’d be interesting to build something similar with a bit more utility.

Yeah, I've been trying to figure out what the issue is there. Seems like ironically it is "randomly" not randomizing.

We definitely made sure to credit - each story is hyperlinked below as you swipe through each one.

I'll be honest, some of the satire posts are very easy to call out because they "sell" the fact that they're satire directly in the title.

Well that's pretty conclusive. Thanks for the video, I'll have to take a look and see what's wrong.

It's built to be completely random, which means upon refresh it would likely still load differently but there's no check to prevent something like that from happening.

Sort of a fun example of https://en.wikipedia.org/wiki/Randomness at play.

I'm glad people seemed to enjoy this.

if (distracted < 15000ms) { electrocute = 300ms; }

Very interesting. If you don't mind providing some more info, it'd really help us figure this out so others don't run into that problem.

What OS and browser were you using? What version? Did you happen to have any extensions running that disabled JS?

We considered removing the prompt, but I've found that it's interesting to intellectually know what to do with a familiar action, but be unable to do it to some small degree.

The reaction difference would theoretically be amplified over time, and if you were to take the test for 30+ minutes a few times a week, the impact would (again, theoretically) be greater.

That's a good point. I'll probably do that and add it to the site!

A recent comment by dang mentioned that some users request specific usernames that are already taken (https://news.ycombinator.com/item?id=32133471 ), and there was a bit of pushback and confusion about it.

I'd agree, the impact is minimal, but if you're an avid reader of the site, it's easy to start recognizing usernames if you're that sort of person. Situational for sure.