_______ __ _______
| | |.---.-..----.| |--..-----..----. | | |.-----..--.--.--..-----.
| || _ || __|| < | -__|| _| | || -__|| | | ||__ --|
|___|___||___._||____||__|__||_____||__| |__|____||_____||________||_____|
on Gopher (inofficial)
URI Visit Hacker News on the Web
COMMENT PAGE FOR:
URI Show HN: I used OpenAI's new image API for a personalized coloring book service
BugsJustFindMe wrote 16 hours 40 min ago:
People are complaining about using the Ghibli style, but I'm here to
complain about the fact that they turn everything into generic
abstractions that look nothing like the people in the original photos.
Generic-cartoon-vaguely-reminiscent-of-your-family-but-not-really is a
product that I'm surprised someone would be proud of.
parpfish wrote 15 hours 43 min ago:
I wonder what would happen if you ghiblified images of the slop I
cooked for dinner. Ghibli food always looks so good
firesteelrain wrote 17 hours 14 min ago:
Why canât people just appreciate some thing cool rather than turn
every HN comment section into a controversy? I had never heard of this
Ghibli controversy.
dkh wrote 14 hours 37 min ago:
When you learn of a situation that a lot of people care about and
feel very strongly about, it would be wiser and more respectable to
not immediately dismiss it. Since you admit to only finding out about
the situation five minutes ago, you might not have a firm enough
understanding of the nuance to reduce everyone involved to haters
without valid concerns. If you dig into the subject a little more,
the answer to your question will become apparent, even if you
disagree it.
firesteelrain wrote 14 hours 24 min ago:
I donât agree or disagree with it. Itâs the constant outrage. I
donât understand how people can be constantly unhappy
dkh wrote 13 hours 4 min ago:
You donât know if anyone upset about this is a generally and
constantly unhappy person, they are upset about this. Are there
no topics in this world that you have a very strong opinion on,
that you would express given the situation? Could you not be a
generally happy person and express those opinions, at the same
time?
Also, I mean, I know a lot of people donât care about the whole
âA.I. vs. artistsâ thing, but it should absolutely not be
difficult to understand why many do. We are talking about a
fast-growing technology and industry that will perhaps decimate
jobs and entire professions, that will definitely reduce the
value of certain things to zero, and while that will be good for
some things, it is concerning for many that one of the first
things being seriously threatened is artâsomething generally
thought to be a deeply human ability, and a profession already
notoriously difficult to earn a living at. For a lot of people
this is existential. This guyâs little coloring book project is
not the problem, but itâs still a small facet of the larger
issue, and being concerned about that issue is very valid, and
anyone with perspective and a modicum of empathy should be able
to understand it.
firesteelrain wrote 13 hours 0 min ago:
Thanks for the perspective. Makes sense
nextworddev wrote 20 hours 39 min ago:
Everything is a copy of a copy of a copy ofâ¦
nesk_ wrote 23 hours 40 min ago:
Love it! Finally a product that properly leverages AI :)
darajava wrote 23 hours 32 min ago:
Thanks!
simianparrot wrote 23 hours 45 min ago:
Every example is the Studio Ghibli style. Tasteless and no respect for
the studio and its legacy.
I donât 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
dollarsâ¦
drdaeman wrote 14 hours 39 min ago:
> I donât understand how you can do this and not feel horrible
about it.
I don't understand why you think one should feel horrible about
generating images in some visual styles. What's the problem?
Demonstrably, it's not something that's generally considered
protected - it's not in the laws, and I've got this impression that
the request of "$artist/$studio-style art" was generally considered
socially acceptable. AFAIK it's also a part of academic courses,
where artists practice various styles.
Patron requests, homages, pastiches - all this stuff existed for a
long while and was generally accepted (or so I think), the only
difference is that a machine does it now, incredibly fast and cheap.
People used to hire artists for this kind of stuff since times
immemorial. Nowadays, if a machine can do a passable job, then why
waste human's most valuable resource (time) for it.
It would be interesting is to hear Studio Ghibli's opinion on the
matter. Not someone who thinks they might be wronged somehow (no
offense meant, I do not intend to invalidate your opinion) or someone
who rather thinks they might be even benefiting from this - I'm sure
it's likely to be a multiple-edged sword, as life is rarely simple -
but their own actual thoughts on the subject. I wonder if they
already published something...
kelseyfrog wrote 14 hours 13 min ago:
Good news - we have commentary on that. Hayao Miyazaki calls
artificial intelligence animation "An Insult To Life Itself" [1].
It's one of his more well-known quotes.
1.
URI [1]: https://www.indiewire.com/features/general/hayao-miyazaki-...
drdaeman wrote 12 hours 50 min ago:
Thank you.
I have watched the video but, sadly, it seems to be on a merely
tangentially related subject (some zombie ragdoll movement), that
caused an understandable disgust (as explained in the video).
Then there was a comment about the desire to create a machine
that can draw pictures - and Iâm really not sure how thatâs
connected to anything that happened in the video.
The only thing I was able to extract from it is general
disapproval, but thatâs about all I can be sure of. Better than
nothing but not something I was hoping for.
Upd: oh, I havenât noticed this immediately, but itâs a
9-year old video. I was hoping for something more up-to-date, as
a lot of things had happened since then.
yapyap wrote 17 hours 1 min ago:
100% agree, what the AI âtechbrosâ have been doing has been
distasteful and downright disrespectful.
Sam Altman is also a little bitch for taunting people like that
through his business ventures. First that Her actressâ voice and
now this.
MoonGhost wrote 18 hours 21 min ago:
Most people never heard of Studio Ghibli and their style. They just
like how it looks. Whey you have only one such book at home it's not
annoying.
As for the project: it's nice and easy, likely will be replicated
soon.
voxic11 wrote 19 hours 44 min ago:
"Imitation is the sincerest form of flattery that mediocrity can pay
to greatness."
yapyap wrote 17 hours 3 min ago:
âWhoever creates this stuff has no idea what pain is whatsoever.
I am 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 itselfâ
afro88 wrote 15 hours 24 min ago:
Though I agree with the sentiment that Miyazaki must hate OpenAI
commodifying his style, I find it so ironic that people misuse a
quote of his from 2016 to be about AI generally. Another kick in
the nuts for the poor guy.
He was talking about how an AI generated gruesome animation made
him think of his friend awfully struggling with a disability.
That people who create that kind of stuff don't understand pain
and suffering.
The full quote: "Every morning, not in recent days, I see my
friend who has a disability,â he said. âItâs so hard for
him just to do a high five; his arm with stiff muscle canât
reach out to my hand. Now, thinking of him, I canât watch this
stuff and find it interesting.
Whoever creates this stuff has no idea what pain is whatsoever. I
am 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 itselfâ
slantaclaus wrote 20 hours 23 min ago:
Upvoting a bunch of lower comments in an effort to bury this one.
What a dick
DrammBA wrote 18 hours 27 min ago:
> Please don't comment about the voting on comments. It never does
any good, and it makes boring reading.
> When disagreeing, please reply to the argument instead of calling
names.
URI [1]: https://news.ycombinator.com/newsguidelines.html
yosefk wrote 20 hours 33 min 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
darajava wrote 21 hours 7 min ago:
What's so bad about it?
true_religion wrote 22 hours 59 min ago:
I suggest that they use the Disney style. Itâs similarly popular
and well known but no one will stand up to protect it since itâs a
multi billion dollar company that we already know has no respect for
artists or artistic legacy.
vb7132 wrote 23 hours 57 min ago:
This is an awesome. I had a similar one: Convert the dense non-fiction
books into something more readable. eg. SAPIENS vs UNSTOPPABLE US.
But this makes me wonder: What is the barrier to entry for these apps
now? Anyone can do it. There is going to be a barrage of apps/websites
like this?
faeyanpiraat wrote 23 hours 45 min ago:
Why would you do that to Sapiens, it's an enjoyable read
riidom wrote 1 day ago:
Maybe I am thinking a bit meta here. But who is supposed to colorize
these pages? Kids that are in the progress of learning to instead use
AI for everything? It can surely deliver better results quicker, after
all.
Same question would be relevant if you wouldn't have used AI to
generate these outlines, of course.
I just want to point out there is a certain irony of the "cut the
branch you are sitting on"-kind here.
Edit: typo
OPBoot wrote 1 day ago:
Oh, sorry - I'm going to be that person....
Your step 2 is wrong :-)
> Step 2: We convert them into a high-quality physical coloring book
with OpenAIâs brand-new Sora model, then send it out for printing.
You don't convert it into a physical book /before/ sending it for
printing.
darajava wrote 23 hours 50 min ago:
Oh, lol. Nice catch - I'll fix that.
sathishmanohar wrote 1 day ago:
I'm from India. I was looking for a service like this but without
sending me a physical book part.
I'd use this at @ $10 price point if I'm able get downloadable a4
coloring pages from a picture. It would be great. Also this way your
customer base becomes international.
$10 for 20 pictures is a good price point for me. Pretty expensive but
I'd still go for it.
darajava wrote 1 day ago:
I'll implement this today.
Edit: I've implemented this! It's a lot of code changes so I hope I
didn't break anything.
pknerd wrote 1 day ago:
Congrats!
I would like to know the cost of the tokens you are paying for an
image. How many pages coloring book will be created against $24 book?
darajava wrote 1 day ago:
Thank you!
OpenAI costs are surprisingly expensive. It's about $7 to generate a
whole book (24 pages). There are 8-24 images allowed in a book, with
a cover too. So there'll be 48 max pages in a book (incl blank
pages).
pknerd wrote 1 day ago:
Thanks for your prompt and kind response. Yeah, it is expensive
because it is new at the moment. They already mentioned the high
token cost.
avereveard wrote 1 day ago:
They have an api now? amazing! I have been using gemini flash but
results are... less than stellar.
pknerd wrote 1 day ago:
Gemini has released new models, maybe they are better.
Also, I request you to expand further, why Gemini is not better?
avereveard wrote 14 hours 43 min ago:
instruction following is good most of the time, but hands are still
regularly coming out garbled and there's a small percentage of
failed generation in the mix. style following is also a bit hit and
miss, I'm producing watecolor mostly, but every now and then a
generation is photographic
site is not really ready for this, but if you want to get an idea
go here [1] and search these:
amber
ladybugs
north
I manually remove failed gens, but the proces doens't scale to
where I'd like if I have to manually verify images. and I have to
have a few automatic rejection in the pipeline, like top border not
white or image not squared.
URI [1]: https://d2uua1ig5ocnwt.cloudfront.net/
darajava wrote 1 day ago:
Yes! [1] I was very excited when it came out. Google have Imagen 3
(is that the same as Gemini Flash?), but you need special access to
be able to edit images. I haven't tested it yet but I think it's a
lot cheaper than OpenAI
URI [1]: https://openai.com/index/image-generation-api/
avereveard wrote 14 hours 48 min ago:
imagen 3 is a standard diffusion model the new one is attached to
gemini 2.0 flash experimental. model naming and working is super
confusing there
Huppie wrote 1 day ago:
I've been using (mostly) the OpenAI image generator for quite some time
generating coloring pages, it's pretty decent at it and can generate
just about anything my kids want as long as you word it a bit neutral
to avoid it generating (something it recognizes as) copyrighted
content.
Great idea to turn your own photos into a coloring book generator!
Edit: I wonder how you prevent it from generating copyrighted content
when people upload e.g. 'photos' of Disney content? Or has that not
been a problem yet?
darajava wrote 1 day ago:
Thanks! Hasn't been a problem yet, but if that happens I'd just email
the customer directly and ask for a replacement photo/if it's okay to
leave that one out.
schuettla wrote 1 day ago:
great idea!
how did you realize the actual producing of the book? you connect to
some print on demand api like from printify?
darajava wrote 21 hours 56 min ago:
Yes I use the Lulu API. It's great!
zengineer wrote 1 day ago:
Well done - I like the style of the page and simplicity!
We recently created one too, where you get a printable version:
dibulo.com/editor - the next step will be to bring the templates to
life again.
DrakeDeaton wrote 1 day ago:
Not sure if you're aware, but if you're interested in SEO/AEO
marketing, there's very healthy monthly traffic for long-tail searches
in this area. Some searches getting towards 100K per month.
Love the idea! Good luck.
jdthedisciple wrote 1 day ago:
Where do you get that from?
darajava wrote 1 day ago:
I don't know much about it, feel free to send an email to
dara@clevercoloringbook.com
ugh123 wrote 1 day ago:
Love it!
Idea: option to print "mini books".
I have some kids that still color, and it would be great to keep
something in my pocket to give them quick with a crayon or pen.
darajava wrote 1 day ago:
I was thinking of doing different sizes alright! They might not be
too much cheaper, that's the only problem I can think of there.
ugh123 wrote 1 day ago:
I'd pay for the convenience. Not sure about others!
osigurdson wrote 1 day ago:
I tried copying the one of the photos into ChatGPT and asked it to make
me a coloring book style image out of it. It is definitely not as good
as this site (i.e. I don't think kids would recognize themselves). Good
prompting!
pknerd wrote 1 day ago:
Ask GPT to give you a prompt that would create a color book :-)
I always use LLMs for meta-prompting. They know themselves better
than others :>
ks2048 wrote 1 day ago:
Suggestions:
* one full PDF (including cover) of an example book.
* don't use AI images as examples - it's not obvious if the outline
version will look as good on real images.
darajava wrote 1 day ago:
Thank you, I agree and I'll update the example photos.
I didn't add a PDF but I added some photos of the real end product to
the bottom of the landing page now.
irishmansevilla wrote 1 day ago:
Your contact form is not working . Try using FabForm !
darajava wrote 1 day ago:
Oh nice catch! Fixed, thanks.
ks2048 wrote 1 day ago:
Can you preview the images? I uploaded one image and don't see the
outline-version.
darajava wrote 1 day ago:
No, it's not a real-time process. We have an admin panel to generate
the images, cover and PDF. There is a good bit of human input
involved.
zeroq wrote 1 day ago:
This is fucking amazing!
Everyone and their mother are trying to hop on the band wagon of AI and
make a half assed service just because it may sell just due to the "ai"
tag attached to it - this is different!
Chapeau bas!
It's simple but brilliant. It's a great example of what a good idea is
- with minimal effort he made an epic product focusing not an AI, but
what AI can bring to the table and executing it flawlessly. Hats off!
waynesonfire wrote 1 day ago:
You're uploading your family pictures.. nevermind. Go enjoy your
coloring book.
darajava wrote 1 day ago:
Thanks so much! Really glad you like it.
laborcontract wrote 1 day ago:
i've been doing this with my child and picture books. i take pictures
of pages, convert it to a coloring book, print it, and then we color
her favorite books together.
hamiecod wrote 1 day ago:
How did the launch go? Could you share Revenue stats after the first 24
hours of the launch?
ks2048 wrote 1 day ago:
This is a great idea and looks well done.
I wonder if printing services (Lulu?) have a automatic API or if it
requires some manual intervention? (And the shipping part?)
darajava wrote 1 day ago:
Thanks! There is a good bit of manual effort involved on our side -
we generate the images, regen any that don't look great, choose the
best cover, and then send the PDF to Lulu. It's dropshipped, we never
see the physical book.
sabslikesobs wrote 1 day ago:
Do you ever handle the physical book, or is this a fully automated
drop-shipping operation?
darajava wrote 1 day ago:
There is a good bit of manual effort involved on our side before we
send the book to print - we generate the images, regen any that don't
look great, choose the best cover, and then send the PDF to Lulu. Yes
it's dropshipped, we never see the physical book.
darkxanthos wrote 1 day ago:
Wow a lot of criticism. I'm considering a similar business. I think
this is too expensive when printing this is so easy these days. But
charging some small about per printable coloring book would be very
attractive.
darajava wrote 1 day ago:
The printing aspect of this wasn't too easy... I wish I could charge
less but as it stands (especially with surprising API costs) I'm
barely making a profit on this.
arnavpraneet wrote 12 hours 58 min ago:
have something similar in the building pipeline, yeah the API costs
caught me off-guard too. I knew it was going to be expensive but
this is still pretty high
transformi wrote 1 day ago:
Why don't you use canny/HED filter :O? (seems pretty overkill for this
job..)
darajava wrote 1 day ago:
Canny filter: [1] Sora: [2] I've had this idea years ago and searched
extensively for a way to turn images into nice line art, but it turns
out there needs to be a good bit of creativity (AI) to do so. Old
school computer science techniques don't cut it.
URI [1]: https://i.imgur.com/Ju7Ggac.png
URI [2]: https://clevercoloringbook.com/samples/3_cartoon.png
jw1224 wrote 1 day ago:
Do you not think the AI output looks far more polished and
print-ready? Canny edges have a lot of noise and don't look at all
clean for coloring book purposes.
MaxLeiter wrote 1 day ago:
For those interested in building something similar, I prompted a story
book generator using v0 and Geminiâs image generation a few weeks
ago:
Demo: [1] The chat:
URI [1]: https://v0-story-maker.vercel.app/
URI [2]: https://v0.dev/chat/ai-story-book-creator-zw7TrmkN2Eb
rahimnathwani wrote 17 hours 45 min ago:
I love the method you used to get image consistency: construct a
conversation history with the model where it explicitly accepts each
image and agrees to use it:
User: Previous page prompt: [Previous Prompt 1]
User: [Image 1]
Assistant: I've received this image and will maintain visual
consistency with it.
User: Previous page prompt: [Previous Prompt 2]
User: [Image 2]
Assistant: I've received this image and will maintain visual
consistency with it.
User: Previous page prompt: [Previous Prompt 3]
User: [Image 3]
Assistant: I've received this image and will maintain visual
consistency with it.
User: Please maintain character appearance, art style, and color
palette consistency with these previous illustrations when creating
the next image.
Assistant: I'll ensure the characters, art style, and colors remain
consistent with the previous illustrations.
User: Generate an illustration for a children's ABC story: [Current
Prompt]. Make it colorful, child-friendly, and in a consistent style
with any previous images. Include diverse characters with different
ethnicities, genders, and abilities. Ensure representation is natural
and authentic.
I'm curious: did you settle on this after trial and error? I mean,
did having the assistant explicitly agree increase consistency,
compared with just asking nicely at the end?
MaxLeiter wrote 17 hours 38 min ago:
I didnât write that - v0 did. You can see it all in the chat
I noticed it wasnât passing the image back and forth so I asked
it to, and it wrote that prompting
rahimnathwani wrote 17 hours 17 min ago:
BTW - thanks for sharing the chat. I'm going to study it for
prompting tips. It's good to learn from other people's iterations
using coding agents, and not just my own.
pknerd wrote 1 day ago:
wow!!!!
Any idea how much it costs to create a book?
r0fl wrote 1 day ago:
The quality of the images is incredible! Great job
How much does the api cost to run? Do you have any safe guards in
place in case bots try to build 1000 stories?
MaxLeiter wrote 1 day ago:
Thatâs all Gemini, I did very little prompting
Iâm just using Geminis rate limits, because its pretty
ridiculously cheap. You can get pretty far on just their free tier
last I checked (when I made this the image model was 100% free)
I wrote about it a little bit here:
URI [1]: https://x.com/max_leiter/status/1906492622551884187
pelagicAustral wrote 1 day ago:
Awesome idea, implementation and design!
darajava wrote 1 day ago:
Thank you!
gitroom wrote 1 day ago:
Nicely done, Ive always wanted something like this for my family pics.
you think AI-generated art will ever feel as special as something
handmade?
darajava wrote 21 hours 56 min ago:
I mean it's pretty close. The handmade element comes from coloring it
in.
Terretta wrote 1 day ago:
Seems like this cat (and various variants in similar settings) was a
top rated image in Sora's explore/images a week ago. Was it yours,
should it be credited, or did you hit edit prompt to get a variant?
No worries, just wondering how that should work.
darajava wrote 1 day ago:
Wow, yes you're right. I did in fact take that image from the Sora
homepage because I thought it was cute.
I pretty much just assumed they're all in the public domain. I can't
find the image anymore so I've decided to remove it for now. I
generated the other three myself.
avree wrote 1 day ago:
Cool idea and really nice looking site.
Pricing is quite high - 24 pages maximum for $23.99. There are 100-page
coloring books on Amazon for $5.00, and the age group that really would
be using this is not going to remember what was on the page a week from
the day they did it.
Maybe it can work in the nice of "adult coloring books" - I've seen
some social media content where people really go crazy on coloring
books, and being able to get nice physical copy to work off could
appeal there.
darajava wrote 1 day ago:
Thanks! I priced it as low as I could given the costs of printing the
book, Sora's API costs, and the human effort that goes into it (there
are some creative choices to be made too!). The 100 page books you
see on Amazon aren't personalized and probably not the best quality.
I'm also hoping a completed page from one of these books will be a
nice keepsake for the parents as well as being more of an incentive
for a child to exercise some creativity.
subpixel wrote 1 day ago:
Presumably you arenât the parent of a 5-7 year-old child. I might
try this manually and save some money but my kids will absolutely
cherish coloring themselves, their friends, and their parents.
Weâre on vacation now and this is gonna be big when we get back.
mirsadm wrote 1 day ago:
My 5 year old will start coloring, get bored and scribble all over
it.
zengineer wrote 1 day ago:
You may want to give dibulo.com a try. We also launched a photo ->
coloring page, but we will go one step further that you can bring
it to life again.
avree wrote 1 day ago:
Interesting presumption. I know about the 100-page coloring books
because I've bought them. Paying $1 per page at the speed they get
colored would cause me to go bankrupt. I presume you're fabulously
rich, and it doesn't matter.
barbazoo wrote 1 day ago:
For anyone looking for a prompt to do this manually, it seems to be as
simple as this:
> Generate a version of this photo that can be used as a coloring sheet
level09 wrote 1 day ago:
Anyone else feeling this weird vibe in the age of AI? You get a cool
new idea, but then you think about how easy it is for someone else to
replicate it, and you end up not doing it.
dkh wrote 14 hours 32 min ago:
Often multiple times a day, but on top of that concern, also throw
in various ethical concerns and a few questions about if it
actually has value or should exist
arnavpraneet wrote 14 hours 2 min ago:
likewise, at this point I am just giving in and making what I can
to see whether or not it is feasible, to speak nothing to its
value or existence
dkh wrote 13 hours 33 min ago:
Me too except I usually donât get very far into making the
things
darajava wrote 1 day ago:
Close enough! The prompt I use is:
> Make this a page in a colouring book. The drawing is in a simple
Studio Ghibli portrait style. Bleed all the way to the edges.
Background colour is #ffffff and lines are bold and #000000. There is
no shading or crossthatching.
natdempk wrote 1 day ago:
I think one thing that slightly drags this down is the Ghibli style
produces images that donât really look that much like the
original people. If you can find a prompt that is still stylized
while preserving more of the characteristics of faces would go a
long way on the personalization front. Maybe easier said than done.
an0malous wrote 1 day ago:
The OP looks like it runs images through a Ghibli filter first
thehappypm wrote 1 day ago:
Iâve done this a bunch with my son. Itâs not quite that simple
because often times itâll create images that have too much detail,
sometimes itâll actually include colors. But yeah, itâs not
really all that complicated
sen wrote 1 day ago:
Yeah I've been doing this with image-gen AIs pretty much since they
started and it's a lot of fun. Even early Dall-E etc was awesome at
doing stuff like "Create a colouring in sheet with some dinosaurs
having a party" or generic prompts like that, and more recently
giving photos to convert has been loads of fun for the kids.
xnx wrote 1 day ago:
Is there somewhere to download a PDF to print out?
darajava wrote 1 day ago:
No, but perhaps I could add this as a paid option.
kelvinjps10 wrote 1 day ago:
Why not just an option to print the image?
darajava wrote 17 hours 46 min ago:
I've added this option - we send out two print-ready PDFs for the
cover and the coloring sheets.
ks2048 wrote 1 day ago:
Presumably, itâs more profitable to sell a physical book, which
makes sense.
beering wrote 1 day ago:
You can simply open up Chatgpt and generate the image yourself,
faster than itâd take to transact with this third party. The cool
thing is that they are printing a physical book for you.
rafram wrote 1 day ago:
For what itâs worth (and itâs probably not much), it doesnât cost
that much to commission comic book-style art from an actual artist
online. When you do that, the proceeds go to an artist, not to an AI
company that stole from them and a software developer who wrote a
wrapper around their API.
darajava wrote 1 day ago:
I can't imagine how much it would cost to commission an artist to do
a whole coloring book and then organize them and send them to print
but it's a good point. AI is never going to be as good as a real
commissioned artist, but this idea makes having something similar far
more accessible to a lot of people.
patch_collector wrote 1 day ago:
I tried to do exactly that once. I was offering between $20-$40 per
image to make a few coloring pages as a mother's day gift for my
wife. Not complex images either -- just basic coloring pages from
photos of my wife and child, without backgrounds, for my kids to
color in.
I reached out to multiple artists, and got one image back (from a
good friend). I gave up on commissioning actual artists, and traced
the images myself on a tablet. I imagine someone with the right
knowledge of where to find artists and the willingness to wait on
their schedule could have done it faster, but I'd have used this
service if it had been around.
thehappypm wrote 1 day ago:
I can get ChatGPT to do this for literally free. Even in the free
tier, I can get a couple images per day.
yieldcrv wrote 1 day ago:
Those transactions never would have happened, and never will happen.
ipaddr wrote 1 day ago:
In fairness no artists are advertising a personal coloring book. The
time, effort and cost would put this out of reach for 99.99 of
people.
No artists are losing income because of this and no industry is being
upended. This is a new product that's available because of a
technology advanced.
Why the focus the artist? Everytime you order in food online you
take away a tip from a host, server, bartender and take away a job
from a person who answers a phone. Why focus on artists when so many
have been affected by technology.
seeEllArr wrote 1 day ago:
The food you order online was not stolen from the server/bartender
without their permission or compensation. Even if the analogy
holds, this is whataboutism, and in the U.S. at least tipping is a
fucked system too.
hightrix wrote 18 hours 6 min ago:
Youâre right that the food itself wasnât stolen, but how many
restaurants actually come up with their own recipes? And how many
use recipes created by master chefs that were âstolenâ and
used by others?
This is how art works and has always worked. Artist should be
using the same AI tools that the general public use but create
things that the general public cannot. Thatâs what artists have
always done.
dkh wrote 13 hours 35 min ago:
Culinary skills at the high-end are typically passed on
directly from chefs to their apprentices, intending to be used,
built on, and passed down again. It doesnât really work the
way being described, which is fine, because thereâs no way to
shape this scenario into a comparable one.
Any attempt to compare the A.I. stuff to some analogous
scenario is deeply flawed if it does not include 1) that A.I.
instances are not humans, but computers run by companies, and
2) the incredible scale at which it can operate.
The actual actions taking place are secondary at best, and the
situation cannot be judged on that alone. It must be debated in
the context of the actions being undertaken by machines, owned
by companies, motivated by profit/market share/growth/whatever,
with little communication or collaboration with the humans who
created the works, and that they can now generate outputs based
on those works at a scale, frequency, level of precision
several orders of magnitude higher than a human can ever
compete with. It cannot be compared to any sort of
person-to-person scenario. The enormous scale this operates at,
by actors that are not human, is the core of the situation.
jfengel wrote 17 hours 48 min ago:
Recipes are the least of what goes into a restaurant. It's not
a secret. In many restaurants the chef will give you the recipe
if you ask nicely. If not, anyone skilled in the art could
reproduce it.
Running a restaurant is a trillion other things. Ordering the
right amount of ingredients. Hiring, training, and keeping
staff. Cleaning the bathrooms. Replacing stolen silverware.
You're not paying for the secret recipe. There isn't one.
You're paying for the insane amount of work that goes into
putting cooked food on a plate.
Images are much more about the specific process that went into
creation. The intellectual part that can be taken is a much
higher fraction of the product.
ipaddr wrote 1 day ago:
If you stop going into the restaurant they stop scheduling
servers. You or the restaurant didn't get permission from the
server who isn't working there anymore.
It's about applying your outrage evenly. Why put artists over a
servers? Why do you drive when not using horses means many
blacksmiths positions disappear. Technology that is accepted by
society changes society. Artists will continue to evolve and
create messages about those changes. No need to worry about
their plight. Worry about translators or other industries that
can't easily provide the same value. Artists are the one group
who will survive and thrive.
ada1981 wrote 1 day ago:
If it's not plant based it is.
Something1234 wrote 1 day ago:
And yet thereâs plenty of adult coloring books made by a human
out there if youâre willing to go to a brick and mortar shop. Got
a super cool one from dick blicks, with a lot of underwater scenes.
Also paper quality is important. I canât imagine getting as far
as I did in mine if it was newspaper
jen729w wrote 1 day ago:
My partner makes one! Go grab a copy if you're in Australia, the
wonderful POP local -- started as POP Canberra -- sells them. [1]
He's 'Bum Man'. A man (actually it's asexual) who is a bum. I
mean c'mon.
URI [1]: https://www.poplocal.com.au/product/bum-man-colouring-bo...
giarc wrote 21 hours 28 min ago:
Looks cool, but they should show more of the pages online. All
I see is the (already coloured) front cover.
saretup wrote 1 day ago:
Thatâs because those are not personalized. The economy of scale
allows for artists to make generic coloring book with high
quality art, but itâs expensive for artists to create (and
customers to buy) custom made coloring books personalized for the
customers photos.
calebio wrote 1 day ago:
Usually when you commission something you're asking the artist to do
art and create something unique with their own artistic flair... not
just line-trace an existing photo.
The intention and cost of something like that is not at all
comparable to what is being offered here.
bix6 wrote 1 day ago:
This is a cool technological feat but what is the cost to humanity
and its artists?
Some of these replies seem rather dismissive to the artistsâ
plight.
ronsor wrote 1 day ago:
They're dismissive because we've had the same moral panics before
with the introduction of photography, then sound recordings, and
then digital art tools, and then vector art, and then 3D, and also
the Internet to an extent, and...
You can see where this is going, right? In the end, humanity and
even artists will be fine overall, even if the world changes.
bix6 wrote 21 hours 17 min ago:
This feels different to me. This isnât the camera going from
film to digital. This is the camera taking over the photo
creation process, and developing them, and selling them. Whatâs
the point of the human?
thesparks wrote 17 hours 43 min ago:
It feels different because you are living through the change.
What happened before is something you read about and already
know the outcome. Future generations will say the same.
blibble wrote 1 day ago:
how will artists be fine when Google can steal all their work,
then use that to compete with them and ultimately replace them
for the cost of showing ads?
ipaddr wrote 1 day ago:
Cost is nothing because this service isn't offered currently. No
income lost and might spark an interest in coloring books which
grows the artist's income.
Artists have been around and existed in more repressive societies
throughout time. The best art is usually produced from the
greatest struggle. Artists will engage and create art in this new
world. The cost of not providing a new surface for artists to
explore is what kills art.
bix6 wrote 21 hours 20 min ago:
How does buying an AI generated coloring book lead to more sales
for the artist that doesnât offer AI generated coloring books?
nxm wrote 1 day ago:
âlearn to codeâ
bix6 wrote 1 day ago:
Just code the food!
jstummbillig wrote 1 day ago:
If it does not cost that much, that is obviously because the artist
is too cheap. If you find that to be a preferable equilibrium, that's
a choice I guess, but I find it fairly ironic in light of the
purported motivation.
richardw wrote 1 day ago:
My opinion isnât fully formed but I currently think either all
content producers have a claim (potentially workable as eg a
discount), or only those who contribute should get access to AIâs.
And by all I mean the AI companies owe a huge debt to all humans who
wrote or designed or drew anything. The vast majority of the benefit
of this technology relies on volume: the billions of pages and lines
of code we wrote for other humans, but have now been repurposed. This
technology relies on bulk, which was mainly unprofessional or freely
given content, by those who intended it for other humans. It was not
100% built only on the output of the few who charge for their
exquisite words or designs, even if their output is higher quality.
Alternatively, let the AI companies go for it but everyone who uses
any kind of AI should understand that theyâre standing on the
shoulders of the millions of developers and nonprofessional writers
whose work has now been repurposed. Not the few artists and
journalists. So those artists and journalists should both refuse to
contribute to, and use, AI.
* Iâve written very little of this useful content, but would be
happy to pay my share to those that have built what we have. I also
turn off training on my content, but I pay a lot for models. Feel
free to help me think through this with comments of your own.
jfengel wrote 17 hours 46 min ago:
I am following a similar mental path. I feel like the AI companies
should be paying some sort of tariff on their output, going towards
everyone on the planet who contributed anything at all. I don't
think you can account for it more finely than that.
richardw wrote 14 hours 59 min ago:
Yup, it feel similar to mining. The models are a transformation
of the underlying content. The content is owned by âusâ. A
mining company can come in and transform rock into iron but it
owes something to the grantors of the mining rights.
There is certainly a contribution in improving how the body of
work is represented but we treat the âAIâ as the smarts, when
really itâs a lens on the collective knowledge we have built.
You can make the lens better, bit not claim ownership of the body
of work. Right now thatâs whatâs happening, with a few edge
cases for artists and publishers.
paulcole wrote 1 day ago:
If this personâs service was to pay human artists $24 for a 23 page
custom coloring book youâd be crying on here about them not paying
human artists enough.
Almost nobody is paying $100 or more for a custom 5-page coloring
book.
This service isnât taking work from human artists.
op00to wrote 1 day ago:
Didnât the artist âstealâ from artists that came before them by
looking at and taking inspiration from their photos? Especially ones
that would do such artistic genres as commercial coloring book art?
jmathai wrote 1 day ago:
Yes. But they are people, perhaps with families to feed. Not
computers.
Cool idea. I can see keeping colored pages of these by my kids up
on the fridge a lot longer than whatâs on there now!
op00to wrote 17 hours 25 min ago:
So itâs ok to steal as long as you are feeding a family with
it? :) I get what youâre saying, anyway and itâs an important
distinction.
I guess what you see as âstealingâ I see as inspiration. I
also believe that there will be artists who use these new
artistic image generation models in ways that are new and
interesting just like the first person who used spray paint for
graffiti was ripped off by everyone else.
It delighted my kids to see themselves depicted in coloring
sheets in situation where they are currently interested. There is
no world where I would have paid an artist to make these photos,
and we would have just colored on blank paper.
Again, I get that real peopleâs content was devoured by these
big companies, but at the same time I am much more concerned
about bigger issues and would rather focus on getting ahead of AI
rather than fighting it.
warkdarrior wrote 1 day ago:
Maybe, but then I have to negotiate with the artist, handle their
refusal to draw art of my choosing, and wait for their (possibly
unpredictable) schedule. AIs mostly avoid these problems.
abaymado wrote 1 day ago:
I like GPT wrapper's that let me personalize/customize existing real
world things, and this a good example of that. I like it.
darajava wrote 1 day ago:
Thank you!
vunderba wrote 1 day ago:
You'll want to really drive home the niche (through your feature set)
that it's for family photos, because the generic photo to AI vectorized
coloring book service has been done to death.
darajava wrote 1 day ago:
Can you show me an example? I think before 2-3 days ago this wasn't
really possible without the output images looking really bad.
themanmaran wrote 1 day ago:
Nice and simple! I'm excited for all the fun micro businesses that get
enabled by the new image API.
Things like your coloring book, instant sticker/tshirt/swag creation,
video game assets, etc.
Also love the "tap 5 times for a discount" feature.
darajava wrote 1 day ago:
Thank you! I was happy with the discount thing alright but it's not
useful for tracking referrals unfortunately.
mdeeks wrote 1 day 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 wrote 1 day 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.
zakki wrote 1 day 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.
subpixel wrote 1 day ago:
Itâs not cheap, but my kids treasure coloring books for a long time
and probably one like this until it falls apart.
sharkjacobs wrote 1 day 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?
voxic11 wrote 19 hours 36 min ago:
My reading of the policy is that if the real person is above the age
of 18 then they can consent to the editing of images which depict
themselves under the age of 18. So I could upload and edit a
childhood photo of myself because I am a real person above the age of
18 and I am the person "contained" in the image. But I couldn't do
the same for my niece who is a real person under the age of 18.
darajava wrote 1 day 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)
ks2048 wrote 1 day ago:
> "that contain real people"
It seems the loophole on this site, is the examples (by my best
guess) are AI.
mdeeks wrote 1 day 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 wrote 1 day 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.
mmastrac wrote 1 day 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.
rafram wrote 1 day ago:
This has zero resemblance to Miyazakiâs style. (And I say that as
someone who isnât a fan of this idea at all.)
mmastrac wrote 1 day ago:
Hard disagree. Sample #2 is totally the Miyazaki-vibe that is
everywhere in OpenAI-generated comics. [1] The cartoon owl at the
top has a different vibe and would probably work for the comics as
well.
URI [1]: https://clevercoloringbook.com/samples/2_cartoon.png
uvesten wrote 1 day ago:
After seeing this example, I think this is the elevator pitch:
âWe take your personal highlights and make them as generic and
impersonal as possible.â
xdfgh1112 wrote 1 day ago:
It's nothing like Ghibli, you are overthinking this.
mmcwilliams wrote 17 hours 36 min ago:
You think that the model is not properly producing the style it
was prompted for in the below prompt? I don't see other artists
or styles mentioned.
> Make this a page in a colouring book. The drawing is in a
simple Studio Ghibli portrait style. Bleed all the way to the
edges. Background colour is #ffffff and lines are bold and
#000000. There is no shading or crossthatching.
ks2048 wrote 1 day ago:
I'm gonna agree with the above comment - #2 looks like a
Japanese-style cartoon (for better or worse).
dgellow wrote 1 day ago:
OP confirmed their prompt explicitly asks for a studio ghibli
style
ronsor wrote 1 day 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.
0_____0 wrote 1 day 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.
HideousKojima wrote 17 hours 36 min ago:
>Given that Miyazaki is known to hate GenAI I really can't
condone...
Miyazaki also said (in response to the Charlie Hebdo murders):
"For me, I think it's a mistake to make caricatures of what
different cultures worship. It's a good idea to stop doing that."
I still love the man and his work, but he's not some infallible
authority on what is and isn't appropriate in art.
wordofx wrote 1 day 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 couldnât
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. Itâs so hard for him just to do a high five; his
arm with stiff muscle canât reach out to my hand. Now, thinking
of him, I canât watch this stuff and find it interesting.
Whoever creates this stuff has no idea what pain is. Iâm
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.
Springtime wrote 1 day 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.
URI [1]: https://realsound.jp/tech/2018/10/post-270755.html
0_____0 wrote 18 hours 46 min ago:
Hm! Thanks for the fact check. I really do want to know what
Miyazaki actually thinks of the Ghiblification thing at
present.
asteroidburger wrote 1 day ago:
The author has since listed the prompt elsewhere in the comments.
It includes, "The drawing is in a simple Studio Ghibli portrait
style."
URI [1]: https://news.ycombinator.com/item?id=43801189
Klonoar wrote 1 day ago:
It absolutely resembles the current Miyazaka-esque OpenAI image
trend thatâs been going on.
fouc wrote 1 day 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:
URI [1]: https://i.pinimg.com/originals/5f/04/ef/5f04ef77ce3beb272a...
darajava wrote 1 day ago:
This is so interesting - I could add some of these as options.
cjaybo wrote 22 hours 28 min ago:
Jesus Christ
throwup238 wrote 1 day ago:
That's probably the only info-graphic I've ever seen that's worth
a damn.
DIR <- back to front page