Hi HN, this is an early version of what we’re imagining as a truly functional stock photo platform using Stable Diffusion.<p>We’re doing our best to hide the customization prompts on the back end so users are able to quickly search for pre-existing generated photos, or create new ones that would ideally work as well.<p>If we keep going with it, in future versions we’d like to add voting, better tags, and more varied prompts, or maybe whatever you recommend!
Some of these are a bit nightmarish!<p><a href="https://replicate.com/api/models/stability-ai/stable-diffusion/files/b17d6f04-8d89-45a4-b2d1-7104c6318591/out-2.png" rel="nofollow">https://replicate.com/api/models/stability-ai/stable-diffusi...</a><p><a href="https://replicate.com/api/models/stability-ai/stable-diffusion/files/0110ae91-4123-4ca8-b697-4be57975fa03/out-0.png" rel="nofollow">https://replicate.com/api/models/stability-ai/stable-diffusi...</a><p><a href="https://replicate.com/api/models/stability-ai/stable-diffusion/files/0bf7ec9f-e867-46b6-ab0b-37eee21db2e7/out-2.png" rel="nofollow">https://replicate.com/api/models/stability-ai/stable-diffusi...</a><p><a href="https://replicate.com/api/models/stability-ai/stable-diffusion/files/8b744be0-02ee-40db-b6ac-0ea07aea885c/out-0.png" rel="nofollow">https://replicate.com/api/models/stability-ai/stable-diffusi...</a><p><a href="https://replicate.com/api/models/stability-ai/stable-diffusion/files/5a952056-48bd-455f-ac24-b986cc8722d9/out-3.png" rel="nofollow">https://replicate.com/api/models/stability-ai/stable-diffusi...</a><p>I love it. But whoever entered "spider salad" and "cockroach salad" previously so it would show up when I searched for "salad" -- I'm mad at you.
Having a button in the search bar that's a blue circle that says Photo, etc, and then not having it start the generation process when clicked feels odd to me. Took me about 30 seconds to realize I had to hit the enter key. Would likely feel weirder on mobile.
UX suggestion: example search already performed on the landing page. You can fake it a bit so it's not actually hitting your search logic (and incurring that cost) every time. Just so when you arrive you see the <i>sort of thing</i> a search might return.<p>[EDIT] Actually instead of dropping straight into the actual search-result UI, how about scrunching the header up a tad more (there's already a bunch of incomplete-looking space under it) and a row of example images with example searches that might bring them up:<p><pre><code> [ Image ] [ Image ] [ Image ]
"Cats playing "The moon, "Statue of
baseball" made of liberty
cheese" driving a car"</code></pre>
None of the text-to-image tools seem to really understand 3D geometry, so I feel safe for now. Look at examples for icosahedron [1] vs dodecahedron [2] vs octahedron [3] None of the images were actually geometrically correct - is that quibbling? Maybe, but sometimes for some audience words actually mean something, not just some vague evocation of the angular aesthetic of something. Has someone delineated the words that will not appear in a stock photography prompt? If there was some feedback like "I'm confident in this" to "I'm guessing here, user beware", it would be a lot more usable.<p>[1] <a href="https://replicate.com/api/models/stability-ai/stable-diffusion/files/57984014-0580-47ee-acc4-da03fe84a8bd/out-2.png" rel="nofollow">https://replicate.com/api/models/stability-ai/stable-diffusi...</a><p>[2] <a href="https://replicate.com/api/models/stability-ai/stable-diffusion/files/a04b3d89-5e74-4adf-beb6-96861a72676a/out-1.png" rel="nofollow">https://replicate.com/api/models/stability-ai/stable-diffusi...</a><p>[3] <a href="https://replicate.com/api/models/stability-ai/stable-diffusion/files/14f94681-185a-43bc-9a45-2e75e0d855c1/out-3.png" rel="nofollow">https://replicate.com/api/models/stability-ai/stable-diffusi...</a>
Not sure I understand how to use this. I searched for "monkey on car" and these are the "categories" I get:<p>"a dead monkey",
"a monkey dancing",
"a dead monkey" (again),
"a ca"
They take too long to generate, but there is no clear indication of that. You should add a spinning mouse or other thing that shows that the server is working. (A robot paining a canvas would be nice, but you need someone that can make nice drawings. A hourglass or a spinning circle are good enough.)
It's fascinating how much AI struggles to mimic signs and text. With as much as we enter text into computers, my instinct was to think this should be really easy for computers, but they don't actually receive and process the abstraction of writing like we do, do they?<p>We use shapes to indicate sounds and sequences to make words, but the computer is ultimately just getting 1 or 0, on or off. It doesn't seem that it does have the associations we use intuitively because of how humans interact with language.
This is awesome. I see this coming builtin to power point.<p>Cellist eating a donut is super freakish!<p><a href="https://replicate.com/api/models/stability-ai/stable-diffusion/files/d57b5612-d46f-4a57-874b-3389bc0ac72a/out-1.png" rel="nofollow">https://replicate.com/api/models/stability-ai/stable-diffusi...</a>
The suggested search results are amazing in such a ridiculous way.<p>"paper" produced "a man reading a newspaper while riding a walrus"<p>"a wolf reading a newspaper"<p>"Trapped inside infinity"<p>and I got to say, the wawlrus readers look passable at a glance when shrunk to low res<p><a href="https://replicate.com/api/models/stability-ai/stable-diffusion/files/19954865-2b12-499c-bf48-5065b2a1abda/out-2.png" rel="nofollow">https://replicate.com/api/models/stability-ai/stable-diffusi...</a><p><a href="https://replicate.com/api/models/stability-ai/stable-diffusion/files/8146e1f8-fb9a-42f0-a9ad-607dac6cad77/out-1.png" rel="nofollow">https://replicate.com/api/models/stability-ai/stable-diffusi...</a>
It still has trouble understanding sentences, it feels to me that it just generates images based on keywords and not the meaning of my sentence.<p>For example, I tried "attractive woman disgusted by an ugly bystander" and the generated images show a disgusted woman with no "ugly bystander".<p>Similar situation with "man angry at a squirrel seeks revenge" (generated image shows an angry squirrel with no man in the image, when the man was the one supposed to be angry..)
Not sure how to evaluate that. Maybe it's kinda fun, but… I mean, generating crappy images from text isn't exactly new by now. It may be "an early version" (and this is exactly why I struggle to evaluate that — obviously, we shouldn't be too judgemental of "an early version"), but it surely isn't "a truly functional stock photo platform" yet. I mean, by far. "By a light-year" kind of far.
Whoa this is cool and I would def used a more refined version of it. The images with people are a little bit... freaky but objects and animals look fine.<p>I wonder if this exists inside of Squarespace or Wordpress. I imagine the ability to generate quality license free stock photos would be a huge selling point for them.
It's sort of interesting, given the undeniable power that these new AI techniques have, just how limited the <i>output</i> is at the moment. Only 512x512 images.<p>I tried a specific query - "man running from a tiger" - and none of the provided images were even close. Seems to be a common problem.
I really like this idea! Related results work fairly well.
Tons of potential here!<p>Ideas:
Allow voting for prompts.
Allow voting for results.
(But try to prevent the rich get richer effect... <a href="https://medium.com/hacking-and-gonzo/how-hacker-news-ranking-algorithm-works-1d9b0cf2c08d" rel="nofollow">https://medium.com/hacking-and-gonzo/how-hacker-news-ranking...</a>)
Allow requesting more results for a given prompt.<p>bug: When there is an error, make it so "back" goes to before the error, instead of before I went to the website perhaps?
I am so thankful we got out of the stock business when we did.<p>AI generated photos, videos, music and animations are here, and I believe it's only a matter of time before they replace a large percentage of the stock websites/companies.
Omg I cannot wait for human faces to become non-freaky with this technology. People pay real money to sites like Getty or Adobe (the former of which is owned by a corp that you may or may not find politically compatible with your beliefs) to fill their landing pages. And for specific categories, for example "happy asian couple", there's only a few models to choose from so it becomes repetitive fast.
The landscape and city photos are stunning.<p>The ones with people and animals tend to have distorted faces or bodies.<p>But keep up the good work. There’s a definitely a market for this.
How safe is it to use those stock photos? How sure can one be that stable diffusion does not create any copyrighted work? Is the training data all freely licenced or is there a mechanism that does not recreate the training data, otherwise I could see remaining risks.
I was intrigued by the text I had as a subtitle in one run:<p>> Please Contact Us US$1,000 One or more parties reside in a country not supported by Escrow.com. Please contact us to discuss alternate payment options with a Flippa Representative.
This needs a lot of curation. Maybe put some ads and offer a percentage to users willing to give ratings to the quality of the images. I will be happy to spend some time clicking , to earn some money for a beer once in a while.
512x512 is standard for SD generated images, but seems pretty low res when you look at it as a stock photo. Might be good to provide an AI upscaled version of the image for download.
Use the Lexica API and show images from them as well! <a href="https://lexica.art/docs" rel="nofollow">https://lexica.art/docs</a>