[HN Gopher] Show HN: AI Generated SVG's
       ___________________________________________________________________
        
       Show HN: AI Generated SVG's
        
       Author : tm11zz
       Score  : 104 points
       Date   : 2023-11-24 17:43 UTC (5 hours ago)
        
 (HTM) web link (vectorart.ai)
 (TXT) w3m dump (vectorart.ai)
        
       | nojs wrote:
       | Look cool but would be good to try without signing up
        
         | tm11zz wrote:
         | That's the dream, unfortunately with the costs attached it
         | isn't currently possible.
        
           | cseleborg wrote:
           | Cool service! This, though, may prove to be a weakness of
           | your business model. Having to sign up creates friction (I
           | won't), which may lose you potential paying customers. What
           | else could you be doing to give people a real feel for how
           | well this works? Maybe a gallery of prompts and the
           | respective results?
        
       | fernandopj wrote:
       | When I click to see an imagem from the gallery, it looks like it
       | loaded but then a blank screen appears instead, after what looks
       | like a refresh. Tried on Chrome and Firefox.
        
         | samsquire wrote:
         | This happened to me, maybe it's a bug?
        
         | tm11zz wrote:
         | Fixed, thanks for reporting.
        
       | petercooper wrote:
       | Not free, of course, but when I loaded Adobe Illustrator for the
       | first time in a while the other day I noticed it had gained a
       | feature where it can generatively add elements to vector
       | illustrations. It worked very well in my casual playing around
       | and maintained the style of the existing image too.
        
         | dsmmcken wrote:
         | Demo of this feature from the most recent Adobe Max conference:
         | https://www.youtube.com/live/1tbrJNP5Cjk?si=tZegLn1-kXE1axDq...
         | 
         | The style transfer is really impressive (watch past the
         | underwhelming first example of the airplane).
        
           | petercooper wrote:
           | Thanks, I was travelling at the time and completely missed
           | all of this!
        
       | tasty_freeze wrote:
       | Are these generated by doing normal text to (pixel) image
       | generation, then doing a raster to svg conversion? Or are LLM
       | models actually capable of generating SVG directly?
       | 
       | I can imagine that working for simple things: make a red circle
       | with a blue line under it, because there are many simple examples
       | on the web.
       | 
       | But generating complex SVGs directly from text seems like it
       | wouldn't work at all. The examples on their home page are well
       | into the "too complex to generate by piecing together bits of svg
       | examples seen during training."
        
         | bigyikes wrote:
         | Definitely raster to svg conversion. The giveaway (besides
         | complex SVG generation being too difficult, as you say) is the
         | splotchiness of the images, since the vectorization doesn't
         | work super well with gradients.
        
         | minimaxir wrote:
         | You can prompt ChatGPT to generate SVGs. It unsurprisingly
         | doesn't work well.
         | 
         | I once asked it to create a SVG of Earth and it create a green
         | ellipse on top of a blue circle.
        
           | mewpmewp2 wrote:
           | Maybe it knows earth is flat after all?
        
         | Zetobal wrote:
         | Yes, if you look at the paths it's rather obvious.
        
         | krebby wrote:
         | Yeah unfortunately differentiable SVG rendering is still
         | something that is very difficult to accomplish with diffusion
         | models. I looked into this last year and found VectorFusion
         | [0][1], which appears to be using a similar technique to this
         | app - generate the raster image and then apply a vectorization
         | tracer. This leads to the blobbiness you see, given the way the
         | diffusion model generates the image and the tracer applies to
         | the output.
         | 
         | There have been a few attempts (i.e. this recent one [2][3]) to
         | attempt to fine-tune the parameters of the SVG with image
         | segmentation, before comparing rendered outputs with a CLIP
         | model. This is promising but the search space for vector images
         | is just so huge that so far you really need to start with an
         | existing image as a basis rather than starting from scratch.
         | Interesting area of research!
         | 
         | 0. https://ajayj.com/vectorfusion/ 1.
         | https://arxiv.org/abs/2211.11319 2.
         | https://intchous.github.io/SVGCustomization/ 3.
         | https://arxiv.org/abs/2309.12302
        
       | kevincox wrote:
       | Strange that the free tier has no documented limits. I always
       | like it when I can see what I am working with, especially when
       | refining an image will eat into that number.
        
       | jzebedee wrote:
       | Seems to be hugged to death. Any sign-ups just give me "Email
       | rate limit exceeded".
        
         | tm11zz wrote:
         | Should be fixed now!
        
       | Zetobal wrote:
       | The best pixel to vector is still vectormagic. They are on it
       | since at least 2009 and have a native desktop app. I am not
       | affiliated but just a bit flabbergasted that they are still so
       | far ahead.
       | 
       | https://vectormagic.com/
        
         | jokethrowaway wrote:
         | Have you tried? https://www.visioncortex.org/vtracer/
         | 
         | Not affiliated, but I've used them for a project and I was
         | impressed
        
       | mkreis wrote:
       | > By using the Services, you grant to VectorArt.ai, its
       | successors, and assigns a perpetual, worldwide, non-exclusive,
       | sublicensable, no-charge, royalty-free, irrevocable copyright
       | license to use, copy, reproduce, process, adapt, modify, publish,
       | transmit, prepare Derivative Works of, publicly display, publicly
       | perform, sublicense, and/or distribute text prompts and images
       | you input into the Services, or Assets produced by the Service at
       | your direction.
       | 
       | -> even to images I upload? This is a no go. As a paid
       | subscriber, I would expect to a) not automatically give a license
       | for everything I UPLOAD B) not automatically give a license for
       | content I created myself
        
         | jahewson wrote:
         | Yeah this is excessive in the extreme. Wave goodbye to your
         | copyright if you upload images to this service.
         | 
         | The other thing is that they want you to pay to use the
         | generated images commercially - but (as far as we know) purely
         | AI generated images are not subject to copyright, so such
         | licensing restrictions can't exist.
        
           | alexchamberlain wrote:
           | > purely AI generated images are not subject to copyright, so
           | such licensing restrictions can't exist.
           | 
           | This doesn't feel right, similar to how it doesn't feel right
           | that the companies are hoovering up copyrighted data. The
           | company has invested in creating a cool product here, and
           | it's reasonable for them to be able to license that work when
           | used commercially.
        
             | free_bip wrote:
             | They created a product and they definitely have copyright
             | over that product.
             | 
             | However, what the product is creating, the output, is an AI
             | generated Image... Which because it wasn't human authored,
             | is automatically put into the public domain the moment it's
             | created.
             | 
             | The product is copyrighted, the output is not.
        
               | tensor wrote:
               | I really don't think this has been legally established,
               | especially not in the case that AI is being used in
               | conjunction with a copyright base image that it uses as a
               | scaffold. It's incredibly hard to see the result as
               | anything but a derived work of the original and being
               | copyright by the author of the original in a similar way
               | to applying a digital filter would.
               | 
               | The courts will sort out the boundaries of copyright
               | here, but I'll eat my shorts if it's as extreme as the
               | "all things that come out of AI are public domain" crowd
               | thinks.
        
               | swatcoder wrote:
               | The gist of guidance from the US Copyright Office is that
               | it's relative to what was put in.
               | 
               | If your input was a six word prompt of everyday langhage
               | and the widely available magic box decompressed that into
               | a cool picture, nobody produced anything copyrightable.
               | And most of us wouldn't want that to be different. You'd
               | just have squatters racing to claim copyright over every
               | Midjourney prompt they can generate.
               | 
               | But if someone put what's clearly a demonstrably
               | significant amount of commercial direction or artisanal
               | effort into producing a original work while using
               | generative tools, that direction/effort is what earns
               | your copyright. The same would likely apply when using
               | the tech to further "work" some already-copyrighted
               | material of your own.
               | 
               | You're right that most of this stuff hasn't been tested
               | by the courts when the tools are called "AI", but many of
               | the underlying questions have decades and decades of
               | precedent behind them (music sampling, collage and
               | assemblage in visual art, monkeys taking snapshots, etc).
               | Regulators do and lawyers will be making their cases
               | about AI copyright in reference to those earlier,
               | analogous, cases.
        
               | jahewson wrote:
               | Yes, the "copyright base image that it uses as a
               | scaffold" case is special and I agree that we've not seen
               | the conclusion there yet. Though, it must be said that
               | I'd expect to the extent that such copyright exists it's
               | going to belong to the original image author, not the
               | model creator/user.
        
             | jahewson wrote:
             | I actually agree that it feels weird but you can't license
             | something you don't own and copyright law supersedes
             | contract law.
        
           | 4death4 wrote:
           | The images themselves may not be subject to copyright, but
           | you can still enter into a contract that says you won't use
           | generated images without paying for them.
        
             | jahewson wrote:
             | You can't because copyright law supersedes contract law and
             | copyright law states that such rights are exclusive - thus
             | contract law cannot be used to usurp or invent a copying
             | restriction. Licensing is the exclusive right of the
             | copyright owner and when no copyright exists there can be
             | no license (or de facto equivalent).
        
               | 4death4 wrote:
               | It's not a copyright restriction. It's a restriction on
               | using the service.
        
         | tm11zz wrote:
         | Thanks for surfacing this. I'll work to improve this to reflect
         | reality - your prompts and images are private and owned by you.
        
           | graypegg wrote:
           | Reality is whatever is in your terms of use agreement. Who
           | wrote it?
        
             | waihtis wrote:
             | AI, of course
        
               | graypegg wrote:
               | Haha, I wonder if we're ever going to see a litigation
               | over a EULA, where the service provider is trying to
               | nullify some duty based on the fact they used AI to write
               | the agreement which swapped Provider and User in a
               | sentence.
               | 
               | Great era to be EULA hunting!
        
               | yjftsjthsd-h wrote:
               | I'm sure it will happen. However, I'm also fairly
               | confident that whoever is the first to try it will be
               | ripped to shreds by the judge:)
        
         | amluto wrote:
         | How would VectorArt.ai even believe that their user has the
         | rights to do so? If (for example) I upload some stock photo off
         | the Internet, I absolutely do not have the right to grant such
         | a license.
        
           | colejohnson66 wrote:
           | They don't. It's a CYA in case they're sued. If/when that
           | happens, they can point the finger at you the uploader.
        
         | leptons wrote:
         | Yet this is essentially the same kind of license Facebook has
         | when you upload any image to Facebook. And billions of people
         | still upload content to them every day.
        
       | esafak wrote:
       | I would buy credits if they let you, instead of a subscription.
       | Just how many vector images do people need to create?
        
       | james2doyle wrote:
       | It seems like we still can't use Bard in Canada yet. Pretty
       | annoying. I haven't been able to find an explanation of why it is
       | not available
        
         | politelemon wrote:
         | Best I could find:
         | 
         | When asked what regulations Google is considering when it comes
         | to bringing Bard to Canada, Sebastian cited the Online News
         | Act, which would force tech giants and other companies to pay
         | Canadian news producers for links posted to their platforms
         | 
         | "We'll bring (Bard) here to Canada very soon as we manage
         | through all the regulatory issues," Sebastian said.
         | 
         | https://www.bnnbloomberg.ca/google-exec-says-regulatory-conc...
        
       | TekMol wrote:
       | It's a sign-up page for a commercial service, not a show HN.
       | 
       | https://news.ycombinator.com/showhn.html
        
         | Kiro wrote:
         | I think "sign-up pages" here needs some clarification from the
         | mods (maybe referring to wait lists?). If everything that
         | requires sign-up is banned then why this section further down:
         | 
         | > Please make it easy for users to try your thing out, ideally
         | without barriers such as signups or emails. You'll get more
         | feedback that way.
        
           | petee wrote:
           | I think its pretty clear, Show HN is for readily showing a
           | project, not getting email addresses. Any service should be
           | able to create a demo account.
           | 
           | The quote is them just asking nicely and clearly to make it
           | accessible.
        
       | supermatt wrote:
       | Not actually AI generated SVGs, but it generates an AI raster
       | image and then "converts" it.
        
       | yieldcrv wrote:
       | this could be great, I've tried getting chatgpt4 to output svg,
       | it will but struggles on complexity
       | 
       | it can perceive what is being requested but you need to break
       | down each part in a g statement just like with coding
        
       | okamiueru wrote:
       | So, if anyone has a weekend to spare, setting up a competitor by
       | running stable diffusion with a LORA for vectorized output with
       | vtracer on the image output... should about do it. Seems at least
       | one of these services pop up every day, and it's usually the same
       | thing wrapped in different packaging.
        
       | andybak wrote:
       | Spam. Check their post history
        
       | blacksmith_tb wrote:
       | It's interesting to see the prompts on specific examples, like
       | https://vectorart.ai/3e5ead1b-60be-40f8-ae6f-25e14ca4e9a0 I guess
       | "vectorized" is doing some heavy lifting there for converting to
       | SVG. It's always funny to me to see random text generated,
       | especially when it's either close to right (like this example) or
       | just mangled shapes that were derived from the Roman or Cyrillic
       | alphabet, but which still have some flavor of the original font,
       | just with zero meaning.
        
       | layer8 wrote:
       | So, this is just traditional image vectorization on top of
       | existing AI-based bitmap image generation. It would be more
       | interesting if this was actually AI-based vector image
       | generation.
       | 
       | They also don't say if they are self-hosting the image generation
       | or rely on an external AI service, which may have an impact on
       | data protection.
        
       | zdwolfe wrote:
       | Seems to not be working. I tried the same prompt twice. My trial
       | credits were used but there was no image generated, nor do they
       | appear in My Images.
        
       | system2 wrote:
       | This is an account just to promote the website. I don't think it
       | fits HN.
        
       ___________________________________________________________________
       (page generated 2023-11-24 23:01 UTC)