HN user
I too run an AI Art Generator based on VQGAN+CLIP - https://creator.nightcafe.studio/text-to-image-art
NightCafe has a feed of artworks, and I too was getting a lot of NSFW or very distasteful prompts. I just used an npm package to detect 'naughty words' to auto-flag any distasteful ones as 'needs moderating', where I can then manually approve or reject them.
Yeah we do use a print on demand service, and the main reason we use Shopify at all is because the printer (Printful) has a good Shopify app that handles all the product syncing and fulfillment automatically.
Shopify lets you choose which payment options you'll let customers check out with. Examples are Stripe, PayPal, Shopify Payments, Google Pay, etc. A Shopify account is enough to get started, you won't need to dabble with any APIs.
However, if you're wanting to sell digital products, it may not be the best option for you. I've had to do a bit of extra work to get it to work for my situation.
I basically use the API to create a checkout specific to the user's order, then listen to the webhook to fulfill the credits. Gateways are Shopify and PayPal. Shopify payments are in my bank account in a couple of days.
It's not very profitable, about a 10% margin after doing a lot of work to get costs down and sales up.
Ran it a bit longer for you - https://creator.nightcafe.studio/creation/OAG7LUkRVNHunrsiGD...
Yeah you can still buy prints but they're not manually retouched. You'll get product mockups and a buy option for your first 5 creations.
Yeah it would, but aside from the cost there are other benefits to cloud computation. It can be done in the background (i.e. it's ok to close your tab) and you can run multiple at once.
Style transfer on NightCafe has a bulk-create mode that has been used in the past to create 500+ creations at once and they all finished in 10 mins.
That one turned out well!
Yes I do, it's a bit of a hangover from the original business model of buying prints. Stripe would potentially be better for credits.
That's a good one!
Most of my regular users are artists who either use it for inspiration or use it to mix into their digital art. (NightCafe has been around for a while as a style transfer app).
It's rare that people buy prints. Most money comes from people buying credits.
It's not, but I can see why the "Graffiti sunset" would make you think that. It does seem to be two different images combined.
I won't claim to have a good knowledge of the inner workings, but basically CLIP will give a score for how well the image matches your prompt, and that's used as a loss function for the GAN.
On the Colab notebooks you can specify multiple prompts with different weights, in which case I assume it has multiple loss functions that it's trying to optimise for.
I'm more of a web app guy than a deep tech guy. Some of what I wrote can probably be corrected by someone with a better knowledge of the ML.
It doesn't support that yet, but it will soon.
I will build an interface for it rather than a prompt syntax. My target audience is a bit less technical than the average Google Colab user.
The Colab notebooks actually have a "target image" parameter. I haven't added it to NightCafe Creator yet, and haven't even experimented much with it on Colab, but it's definitely on my to-do list.
However, adding keywords like "watercolour painting", "van gogh painting" etc goes a long way to getting more precise results.
One big difference between style transfer and GAN art is that style transfer never changes the shape of things. E.g. you can't put in a woman's face and a cubist painting and get out a rearranged version of the face (as cubists do). It will have all the hallmarks of cubism, but it's still recognisable as the original photo.
With GAN art though, you can put that photo in as a start image, say "Cubist painting of a woman's face", and the GAN will actually rearrange the face like a cubist would.
I ran it a bit longer for you - https://creator.nightcafe.studio/creation/2MGvqi6ZBZ3mZSFB66...
Yep, NightCafe has struggled for years with the expense of running algorithms on GPUs. It started out free, but as soon as you start to get any kind of volume, costs balloon.
I almost gave up on NightCafe when I was trying to make money from selling prints to people. Then, one user generated 3,000 creations in a week, which cost him nothing and me $300. I decided to spend the weekend implementing a credit system to prevent abuse, and was surprised to find that more people were willing to pay for credits than I expected.
It's still not much and I've had to spend a lot of effort on reducing costs in various ways just to be able to break even. But I love working on this app and have high hopes that _one day_ it will become profitable enough for me to work on it full time.
Interesting. For me it's worked out well, but it would be worth doing a proper comparison. I'll add that to my to-do list.
You're right, adding modifier keywords like "impasto" or "cubist" have a big effect. There are also some powerful community-discovered keywords that have a huge impact on your results, like "Trending on Artstation" and "Unreal Engine".
My best tips for good results - use a phrase describing objects you'd commonly see in pictures and art, like "House on a hill" or "Futuristic city", add some modifiers, then start with the smallest resolution and runtime. Try a few variations of phrase and modifiers, and see what looks promising. Then pick the best one(s) and use the "Evolve" button to run them for longer and increase the resolution.
I use Coreweave Cloud for NightCafe Creator (essentially the same service as you, but more mature). Check it out.
I've been running an AI Art Generator for a few years called NightCafe Creator and we do most of what you suggested here. We run on a managed Kubernetes provider called Coreweave Cloud, that provides nodes with good GPUs for a good price.
From experience I can tell you that fewer people will buy prints than you'd expect (that was my original business idea) BUT more people will pay just to create the art than you'd expect.
I just launched VQGAN+CLIP on NightCafe Creator on Show HN (https://news.ycombinator.com/item?id=28081130) and a commenter directed me here. I'm impressed that the OP here has managed to get this done in such a short time (since VQGAN+CLIP is still quite new).
Since you left such thoughtful feedback here, I'd be keen to get your thoughts on my own version.
Thanks
I hadn't seen either of these. Thanks!
Looks like they're both new apps, so they've done well to get everything up and running so quickly! I already had a lot of the groundwork laid for NightCafe Creator, so it was much easier for me to get this done. There's a lot involved, especially if you're going to charge for use (which is a must if you expect to have any sort of volume in the long run).
I've been working on NightCafe for a few years now and have submitted to Show HN in the past, but since VQGAN+CLIP is a new technology and, to my knowledge, no-one else has built an app around it yet, I thought I'd submit again!
Advantages over using Google Colab:
- It's >2x faster (runs on NVIDIA RTX A5000 GPUs). E.g. 800 iterations at 600x600px in 8 mins vs 19 mins on Colab.
- Can do higher resolution (894x894px > 700x700px).
- Run multiple jobs in parallel.
- Works from any device.
- Obviously it's much easier to use for anyone non-technical.
- It's easy to "evolve" creations. I.e. tweak the prompt, increase the resolution, and/or just run them for longer.
- You don't need to keep the tab open to see the result.
It's free for basic use, but does cost money for extended use. Unfortunately I don't have the same access to GPUs as Google does.
Try it out. Would love to get the thoughts of the HN community!
I've been using this technique in production on my app NightCafe Creator[1] for 9+ months with great success, so I decided to turn it into a package.
It's far easier to integrate than the current go-to virtualization options, which often require you to re-architect a lot of how your list works.
I'm in the same space as the founder of NightCafe Creator [1]. It's been running at a (substantial) loss for the last year until September which was my first break even month. I'm hoping to turn it around and have made great strides so far. The biggest expense (95%) is GPU compute time. It runs on Algorithmia which was super convenient to get up and running with, but is now very expensive. Switching compute providers is a big opportunity. Unfortunately I suck at devops.
#4 is now implemented. Thanks again for the suggestion.
Thanks for giving it a go!
iPhones do this sometimes. Thanks for letting me know - I will add this to my to-do list.
Thanks for trying it out!
@airdeck thanks for being the #1 Creator and early adopter!
Faces often don't work well unless they're really tightly framed / close up. I think it's because if the eyes turn out a bit weird, it's very off-putting.
I've thought a bit about marketing to Instagrammers, I think neural style for short videos would be a good service to offer. Not sure where it fits on my roadmap yet though.