remix logo

Hacker Remix

Show HN: I used OpenAI's new image API for a personalized coloring book service

259 points by darajava 1 day ago | 141 comments

I've had an idea for a long time to generate a cute coloring book based on family photos, send it to a printing service, and then deliver it to people.

Last month, when OpenAI's Sora was released for public use I (foolishly) thought I'd manually drag-and-drop each order’s photos into Sora's UI and copy the resulting images back into my system. This took way too much time (about an hour for each of the few books I made and tested with family and friends). It clearly wasn't possible to release this version because I’d be losing a huge amount of time on every order. So instead, I decided I'd finish off the project as best I could, put it "on ice," and wait for the API release.

The API is now released (quicker than I thought it'd be, too!) and I integrated it last night. I'd love your feedback on any and all aspects.

The market is mostly family-based, but from my testing of the physical book I've found that both adults and kids enjoy coloring them in (it's surprisingly cathartic and creative). If you would like to order one you can get 10% off by tapping the total price line item five times.

simianparrot 3 hours ago

Every example is the Studio Ghibli style. Tasteless and no respect for the studio and its legacy.

I don’t understand how you can do this and not feel horrible about it. But I guess not everyone cares as long as it might earn you a few dollars…

yosefk 11 minutes ago

Style has been copied since time immemorial and was never copyrightable. I think it's better to be the studio everyone copies in their AI slop than the studio nobody copies in terms of publicity, sales and cultural impact. And the mass copying by a handful of models in a reasonably consistent way together with everyone talking about it is probably better for the studio than flesh and blood artists here and there copying it not so consistently / competently without the buzz attributing the style to the studio

true_religion 3 hours ago

I suggest that they use the Disney style. It’s similarly popular and well known but no one will stand up to protect it since it’s a multi billion dollar company that we already know has no respect for artists or artistic legacy.

darajava 45 minutes ago

What's so bad about it?

reneretord 38 minutes ago

[dead]

mdeeks 16 hours ago

This is a cute and simple idea!

I'd like to see what a real physical book looks like before I buy it though. Do you have real pictures of a printed one?

I think our kids would appreciate seeing the original (even if a small thumbnail) along side it. You can't always tell from these AI drawings that it was originally you and your family.

Also, it's REALLY expensive. $30 for a book that my kids will draw on in one or two nights and then never touch again is probably too much.

darajava 8 hours ago

Thanks! I've added a section at the bottom of the site showing some real photos of an actual coloring book I got in the mail. There are thumbnails of all photos uploaded on the back.

$24 + postage is the lowest I could reasonably charge for this. Printing costs are a bit more than half of that, OpenAI charge a surprising amount for image generation, but there is also a good amount of human effort (and creative choices) in generating the book. It's not a fully automated process and I hope that's evident from the quality of the end product.

subpixel 15 hours ago

It’s not cheap, but my kids treasure coloring books for a long time and probably one like this until it falls apart.

zakki 15 hours ago

To the author, I have this idea, for each page, put a sheet of transparent plastic or something like that. So the owner will color the plastic which can be erased. But it may increase the cost anc the color may not stick to the plastic.

sharkjacobs 16 hours ago

from clevercoloringbook.com:

    > Please only upload photos that are in line with OpenAI's Usage Policy.
    > We are not able to include any photos that do not follow their policy in the final printed book.
from openai.com/policies

    > Editing uploaded images or videos that contain real people under the age of 18 is not permitted.
The first two sample pictures on the page contain of adolescent children. Are you concerned about this apparent contradiction?

darajava 8 hours ago

Great point. As per our TOS - users of the site must be over 18 and have the consent of everyone in the image (i.e. their own kids, relations etc).

I put that line about OpenAI's usage policy there for practical reasons. If someone orders something that OpenAI refuses to generate (like a photo of Bart Simpson say), then I can't include it in the printed book. With this project, if someone uploads content that's in any way inappropriate, we'll see it and refuse to fulfill the order (and take other appropriate actions, if needed)

mdeeks 16 hours ago

I'm not the OP, but during the recent Studio Ghiblification craze there were a huge number of photos of families and kids passing along in facebook, twitter, and other social media. It was literally everywhere you looked. OpenAI obviously saw all of that. I don't think they actually care unless it's something bordering on illegal.

ronsor 16 hours ago

I agree. In practice OpenAI is unlikely to care about families uploading their own photos. I think the policy is mostly to stop random people from engaging in creepy activities with the photos of children.

ks2048 11 hours ago

> "that contain real people"

It seems the loophole on this site, is the examples (by my best guess) are AI.

mmastrac 16 hours ago

The comics look pretty Miyazaki-inspired, like all of the comics I've seen lately. I've kinda started to dislike this look because it's _everywhere_ that low-effort comics are these days.

Maybe worth trying to train a better style for this. This is probably something where you could put a little effort in up-front (ie: using a model that's for segmentation to get outlines, using some classic image-processing for boundary detection) and then have AI touch it up a little more lightly and a less of the "default" style.

Also, do you have AI images for the "real world" samples on the left? They have a certain "I don't exactly know what, but it's creeping me out" vibe.

ronsor 16 hours ago

It doesn't look particularly Miyazaki style to me; it's just a generic cartoon style.

I think the Ghiblipocalypse has gotten people on edge.

asteroidburger 8 hours ago

The author has since listed the prompt elsewhere in the comments. It includes, "The drawing is in a simple Studio Ghibli portrait style."

https://news.ycombinator.com/item?id=43801189

0_____0 8 hours ago

OP confirmed that their prompt includes a directive for Ghiblification. Given that Miyazaki is known to hate GenAI I really can't condone... I mean there's nothing anyone can do about it but it's just kind of sad.

Springtime 8 hours ago

> Given that Miyazaki is known to hate GenAI I really can't condone

Not that I wouldn't similarly expect it from Miyazaki in terms of general generative art but the actual source of all the articles/memes about his quote point to a 2016 video where he's being demo'd a disturbing 3D simulation of an oily looking human figure crawling on the ground by its head while the dev explains to Miyazaki and others that 'it feels no pain so it learned to move by its head' and it could be used for horror games.

It's then that Miyazaki expresses the 'insult to life itself' quote and explains the devs have no idea what human pain is. Makes one wonder how the devs thought the reaction would be any different tbh.

Edit: reading that he clarified in an interview[1] a couple years later that his distaste was due to believing the dev was aiming at humorizing such body contortions of realistic humans which he took issue with.

[1] https://realsound.jp/tech/2018/10/post-270755.html

wordofx 4 hours ago

Yeah can we stop spreading this misinformation. His quote was in reference to grotesque nature of something he saw.

> Miyazaki was shown an AI-generated character. The character was a scary monster that used its head as a leg because it couldn’t feel pain. The person presenting it said its movements could be used in making a zombie video game.

To which he stated:

> Every morning, not in recent days, I see my friend who has a disability. It’s so hard for him just to do a high five; his arm with stiff muscle can’t reach out to my hand. Now, thinking of him, I can’t watch this stuff and find it interesting. Whoever creates this stuff has no idea what pain is. I’m utterly disgusted. If you really want to make creepy stuff, you can go ahead and do it. I would never wish to incorporate this technology into my work at all. I strongly feel that this is an insult to life itself.

fouc 12 hours ago

there's 4 sample pages, and the one with the cat is the only one that is not Ghibli-style.

Here's some generic cartoon styles to look at: https://i.pinimg.com/originals/5f/04/ef/5f04ef77ce3beb272a61...

throwup238 9 hours ago

That's probably the only info-graphic I've ever seen that's worth a damn.

darajava 9 hours ago

This is so interesting - I could add some of these as options.

cjaybo 2 hours ago

Jesus Christ

Klonoar 11 hours ago

It absolutely resembles the current Miyazaka-esque OpenAI image trend that’s been going on.

rafram 16 hours ago

This has zero resemblance to Miyazaki’s style. (And I say that as someone who isn’t a fan of this idea at all.)

mmastrac 16 hours ago

Hard disagree. Sample #2 is totally the Miyazaki-vibe that is everywhere in OpenAI-generated comics. https://clevercoloringbook.com/samples/2_cartoon.png

The cartoon owl at the top has a different vibe and would probably work for the comics as well.

uvesten 7 hours ago

After seeing this example, I think this is the elevator pitch: ”We take your personal highlights and make them as generic and impersonal as possible.”

xdfgh1112 12 hours ago

It's nothing like Ghibli, you are overthinking this.

ks2048 11 hours ago

I'm gonna agree with the above comment - #2 looks like a Japanese-style cartoon (for better or worse).

dgellow 8 hours ago

OP confirmed their prompt explicitly asks for a studio ghibli style