| ▲ | jjcm 4 hours ago |
| > There are other aesthetics my brain associates with AI, like beige/cream colors, orange accents, and serif typefaces Something to consider regarding the narrow space AI-created designs align on: LLMs are trained to write consistent code. This makes sense for something like a billing or a backend function - you want that code to be consistent. The problem though is that LLMs write code to represent designs as well, which means you get consistent designs. You end up aligning on a generic mean because of it, which is often why you see these repeated aesthetics. It was something I saw when I was working on AI tooling over at Figma. It was very hard to get creative, unique outputs out of LLMs. One thing I'd recommend if you're trying to avoid this is try a diffusion model as a starting point. Gpt-image-2 is a VERY capable designer, and Opus and Fable are fantastic at converting images to webpages. Starting with images will let you sidestep a lot of the uniformity of output that LLMs have. I'm heavily biased here as this is what I left figma to build (https://news.ycombinator.com/item?id=48995754), but even starting with gpt-image-2 to give you a general sense of the look/feel will heavily differentiate you on the design front. Here are some examples of image->webpage outputs I've been playing with: https://html.non.io/tarot/ https://html.non.io/neonRamen/ |
|
| ▲ | websight 3 hours ago | parent | next [-] |
| I don't think these look "bad" exactly, but they do look like AI, and I don't think that's just because I know they are. |
| |
| ▲ | Retr0id 2 hours ago | parent [-] | | I don't think I'd clock the ramen one as AI, if not for the main image being AI generated. | | |
| ▲ | somenameforme 37 minutes ago | parent | next [-] | | The one thing that strikes me as LLMesque is the occasional use of random and seemingly inappropriate symbols. For instance the lightning bolt and then the arrow/square by the order ahead label by the start an order button. It's also placed in a slightly odd location. The symbols at the top are also kind of weird. I think it's the LLM trying to allude to the cyberpunk theme, but it does a poor job of it in a way that even a low skill human probably wouldn't - because you just wouldn't think to put a part of a rectangle up there beside a checkerboard pyramid thing. And that contrasts to an extreme degree against the rest of the scene which flows extremely well, maintains perfectly color coordination, and so on. I think it's kind of like how self driving cars can drive phenomenally well but then have occasional failure modes like randomly driving head first into a concrete divider. It's not like that's bad driving in the sense of missing a nuance, but something that's just completely conspicuously outside the rest of its demonstrated abilities. | | |
| ▲ | majormajor 29 minutes ago | parent [-] | | Yeah polish + consistency but also with busy-ness is a hallmark from what I've seen. It can be tamed, but takes effort. That said, the provided examples definitely are a clear step up from the "default" you'd get. Like how some bootstrap-templated sites did it much better than others, while the best made it nearly invisible. |
| |
| ▲ | lynndotpy 40 minutes ago | parent | prev | next [-] | | I'd clock this as an AI website with no question whatsoever. Everything comes in punchy threes. I don't need to know what "早い・旨い・熱い" means in order to smell it for what it is. | |
| ▲ | gentoo an hour ago | parent | prev [-] | | They both read as hyper-polished pastiches of existing, well-established aesthetics. The cyberpunk one in particular employs just about every genre trope I can think of. There's no sense of stylistic ingenuity or choice - e.g. deliberately breaking from convention or leaving things out. |
|
|
|
| ▲ | chadash 3 hours ago | parent | prev | next [-] |
| I like your product and I’m gonna try it because I’m growing to hate the “Claude generated website aesthetic” but $0.13 is way too cheap. |
| |
| ▲ | jjcm 3 hours ago | parent | next [-] | | Ha! Totally fair. 13 cents is 0% margin, which is what I'm targeting for individual plans. I literally just got my SOC2 compliance complete an hour ago, and I'm gonna roll out team plans/enterprise plans next week (unified billing + shared brands). For teams I'm gonna charge a flat 25% margin on API costs, and for enterprise I'll have a 50% margin + minimum spend. I think I'm going to keep the individual plans at 0% though. Realistically until my own diffusion models I'm training are the main model I'm using for generation, I'm just an API wrapper + harness. At the individual level I want to be competitive with going directly to the api and coding your own harness. I am curious though - what would you pay per image? | | |
| ▲ | chadash 2 hours ago | parent [-] | | Ok, so I signed in to your site and started out. The $0.13 is a bit misleading because by default it generates 4 images per “sketch” so it’s more like $0.50. So I can easily get to $5 in a session, which feels like a good amount. That’s about the amount I would pay to just play around and I like that you start me off with a few credits If I’m using this towards something that makes me money, I’d pay a lot more, but it really depends on context. In general, I’ll spend $5 like it’s nothing, $20 if it’s nothing and it’s for a business expense, and probably $50-100 for a design scheme for my (quite small) business. I don’t know that I’m a representative sample, but I’ll put my money where my mouth is, because I just added an extra $5 to play around more. Btw, it’s a really innovative interface. It’s fun and very different from other tools I’ve seen. I quite like it but it’s also a bit confusing. Feel free to contact me if you want customer feedback (info in profile). |
| |
| ▲ | altmanaltman an hour ago | parent | prev [-] | | It literally is not though, it takes $0.50 for generating 4 images. That's on par for any image model by frontier labs. Probably just covering their costs right now but will keep rising it over time if the tool gets adopted. But it is not too cheap when you consider the sheer amount of variations one will make if they use this in a professional design capacity. The quality of the tool is not what this comment speaks on since i have not tried it yet but it is not "way too cheap" in any real sense given the pricing. | | |
| ▲ | chadash 42 minutes ago | parent [-] | | I think that's fair, but if you add a lot of value on top, a higher price is justified. Would I pay $5 for a great looking homepage, even if I only have to generate 12 images at $0.13 ($1.56 total) to get there? Yes. Sometimes models are vastly underpriced. Fable is an example. I can easily spend hundreds of dollars using it to code. On the other hand, if I'm looking for AI to review a contract for any obvious mistakes, I don't really care if I spend $0.01 vs $1.00, even if the difference is only marginal. I'll pay quite a bit more for something that's just a little bit better. Same thing with design, in many cases. When the absolute dollar amounts are small, I'm happy to pay more for even marginally better quality. | | |
| ▲ | altmanaltman 13 minutes ago | parent [-] | | I understand but you are thinking design and coding maps neatly one to one when it absolutely doesn't. If you don't care if the cost goes up 100x, of course it is too cheap for you. But that is not how everyone looks at costs even for marginal things esp at scale. |
|
|
|
|
| ▲ | keithnz 3 hours ago | parent | prev | next [-] |
| maybe, but you can do wacky things, eg I put together https://scores.lazer-kiwi.workers.dev/ It's a dota2 guild (#1 guild in autralasia) website and I have a bot that extracts the scores and publishes peoples progress on the website with a relatively basic table and stats, as a random side quest all kinds of weird stuff got built in ( you can shoot all kinds of things, if you hover over the number in the # column of the members and it turns into a gold sights, then you can click that and there are all kinds of weird cinematics. Lots of semi crude humor and Kiwi / Aussie rivalry Jokes and internal digs at some of the players. The art is...errr... basic. There's a secret counter down the bottom left so you can tell if you have seen all the weird things or not. Note, on mobile it doesn't include the extras. |
| |
| ▲ | jjcm an hour ago | parent | next [-] | | You have my dota 2 aus guild beat by a couple of places: https://image.non.io/dad602c8-4774-47dc-b671-c515c67a0cf1.we... You definitely can do fun/creative things with LLMs, but they need a lot more steering/handholding. IE if you add an additional page to the lazer kiwi leaderboard, it's likely the first pass will be somewhat more generic than the homepage. One of the other advantages of diffusion is that it does really, really well with style transfer, meaning designing additional pages in the same style ends up pretty easy. As an example, here are designs of a user profile page and a top guilds page, using the look/feel of a screenshot of your homepage: https://image.non.io/5415e0e0-9264-4bad-988e-8d9d3885b518.we... | |
| ▲ | the_sleaze_ an hour ago | parent | prev | next [-] | | Laser kiwi reminds me so much of the old web circa 2008. Awesome. | |
| ▲ | huey77 an hour ago | parent | prev [-] | | Lazer kiwi respect! |
|
|
| ▲ | floam 3 hours ago | parent | prev | next [-] |
| I tried your tool just now, on my iPhone. I am really kind of stuck and frustrated. I cannot get that first box, the one you can type into, that’s on a grid into a state where I can interact with it. Stuff is jumping around after I try to move the canvas around, unexpected stuff. I can’t figure it out. |
| |
| ▲ | jjcm an hour ago | parent [-] | | Oof, apologies. I have not done any work at all on mobile to make this work. |
|
|
| ▲ | internet2000 3 hours ago | parent | prev | next [-] |
| The ramen one looks extremely AI. It's mostly the atrocious copywriting, and wonky responsiveness, but even overlooking those things you can tell. On the Tarot one, the 3D card in the bottom is both very elaborate and also pointless. No human would've put effort into making that. Not bad per se! But AI. |
| |
|
| ▲ | sebmellen 4 hours ago | parent | prev | next [-] |
| How do you prompt your diffusion models? I see that you are a founder in this space :) |
| |
| ▲ | jjcm 3 hours ago | parent [-] | | A few layers to it. When you prompt on my product I expand out that prompt into a semantic json blob that represents the style, theme, color palette, and subjects on the screen. I then feed that blob into the diffusion model itself. The reason I feed in the json blob is it lets me better preserve subjects across multiple screens (ie you probably want to carry over the header exactly as it is in one image to another image). The example sites above though were pretty simple. I think they were something like "A tarot card website with an inky, painted artistic style, with rich illustrations on a card featured on the left, and a button to draw cards on the right" and for the other it was something like, "A cyberpunk inspired ramen cart website" |
|
|
| ▲ | hijp 3 hours ago | parent | prev | next [-] |
| For Tarot, did you generate base-color, roughness and normal maps? How do you make sure something like the roughness map doesn't deviate slightly from the base-color? |
| |
| ▲ | jjcm 3 hours ago | parent [-] | | Yea. I have a very speed run version of how I made that one here: https://x.com/pwnies/status/2076755344471289898 But basically diffui's build step provides an API to create normal/roughness/depth maps from images. It's essentially an interface to fal.ai's Patina model, which does a really good job at creating those. The one thing that's missing with it though is metalness maps (Patina can theoretically output them, but they only have a ~10% success rate I've found). I'm trying to train my own diffusion model now to help generate those so the reflectivity isn't fully uniform. I just posted very, VERY early results here - right now my model has around a ~25% succes rate: https://x.com/pwnies/status/2082980850120163756 |
|
|
| ▲ | motoroco 3 hours ago | parent | prev | next [-] |
| I wanted to try out your service but I don't have any accounts with Google or Microsoft properties (incl Github), so I can't sign up |
|
| ▲ | p-e-w 4 hours ago | parent | prev | next [-] |
| > The problem though is that LLMs write code to represent designs as well, which means you get consistent designs. You end up aligning on a generic mean because of it, which is often why you see these repeated aesthetics. The funny thing is that looking like everyone else was once considered the definition of good UI design, because it helps users understand a new interface. Then mobile apps came and suddenly UI design was about “expressing your brand” or whatever. |
| |
| ▲ | jjcm 3 hours ago | parent [-] | | I think it's important to separate patterns from aesthetics. Patterns help us understand a new interface for sure, but aligned aethetics start to look mundane. That's why I was specifically calling out the color usage and typefaces. I actually think the other things that Jim mentioned, such as the async task gradient / standard sidebar for agents are good things. |
|
|
| ▲ | senderista 3 hours ago | parent | prev | next [-] |
| I was expecting Papyrus for the tarot page :) |
|
| ▲ | wahnfrieden 2 hours ago | parent | prev | next [-] |
| Context priming all the more important for design work over raw model vanilla experience |
|
| ▲ | azan_ 3 hours ago | parent | prev [-] |
| Honestly these examples absolutely DO look like generic AI slop, no offense. |
| |
| ▲ | a1o 3 hours ago | parent | next [-] | | I think that if the images were replaced by human made (you can take photos of real things if you don’t want to draw or hire an actual artist) perhaps the design could be more passable | |
| ▲ | matheusmoreira 3 hours ago | parent | prev [-] | | I think the neon ramen example looks pretty awesome. | | |
| ▲ | vips7L 37 minutes ago | parent | next [-] | | To me it looks exactly like a cluttered LLM generated one. | |
| ▲ | jjcm 3 hours ago | parent | prev | next [-] | | ty ty, though I do agree with azan that the imagery inside of it looks generated (as it is). That was really a test of whether or not newer models could implement box shapes that aren't provided by CSS. Opus 5 was one of the first that really nailed that - it's been a long standing test I've had for img->html. | |
| ▲ | shimman 3 hours ago | parent | prev [-] | | It's a copy of cyberpunk 2077 aesthetic (which if you search on google you'll see many css + component libraries trying to recreate it). |
|
|
