Hey HN!
I used to spend hours drawing all kind of things as a kid. Sadly though, those drawings are long gone.
Inspired by this, I created DoodleDreams. A webapp that brings drawings to life using AI and stores them as memories. You can always look back at the drawings, see who made them, and even know the age they were drawn at.
I thought it was a fun way to preserve those memories. What do you think?
Viktor
I believe it focuses more around using masks to build out a "rigging" to animate them.
https://about.fb.com/news/2021/12/using-ai-to-animate-childr...
https://fairanimateddrawings.com
Conversely, sounds like this is just feeding directly into the Kling API though. I'd say pricing is going to be the roughest aspect since they're definitely not cheap.
To add to this - Kling's I2V model (even as of v1.6) is pretty inconsistent when it comes to 2D imagery - even in your cherry picked examples they're unfortunately morphing all over the place. Since you have no control over the model or even the end result outside of minimal positive/negative prompts, I think you'll find prospective customers getting potentially frustrated.
https://sketch.metademolab.com/
You can upload a picture and have it animate it. Not quite the same or as impressive but still might be fun and it's free
they're kids doodles. being a bit wonky is part of the charm, i think its a great use case for where ai animation is at the moment.
If this was wedding photos we'd have a problem :D
I work with things that push to inspire creativity and learning to foster the passion behind creativity and authentic works where otherwise we'd see how 'AI copies our work' and now we can see how AI can bring works to life and make them more fun.
Over-all would you like to see schools adopting your project? I didn't see a contact form but would love to be able to reach out and get more insight. I think this is absolutely wonderful.
While I know tokens and generative AI have costs, I can see the business model.
Since you've made it a web app have you explored the possibility of making it cross platform with something like Cordova? https://cordova.apache.org/
Perhaps setting up a bluesky social and documenting the thought process as you build on would be amazing, I'd love to see more; but would definitely like to be able to reach out in the future. Definitely bookmarked!
There's a short "How it works" section, but could possibly be more detailed. No "potentials" section currently.
Yes, exactly! Sure, schools are welcome to adopt the project. Sorry, added contact details to the page now! Feel free to send an email to: hello@doodledreams.cc
I have not looked into Cordova, will take a look at that now.
Thanks for your feedback!
That Cordova site really needs some kind of disclaimer.
Deleted Comment
One point of critique: Simple, Transparent Pricing -> Currency is tokens. Transparent would be: Currency is animations". Even if 1 token == 1 animation, it gives the feeling as if this would be changed in the future, like 2 tokens == 1 super-animation, which breaks the "simple and transparent".
I made this as I believe it would have made me very excited to see my drawings come alive when I was a kid.
I hope someone can get the same joy out of it as I would have at that age!
Second, are you doing moderation? What is your strategy for porn/illegal content? It often seems like that managing those practicalities kills services like these.
I love this. I've been playing around with drawing-to-animation techniques for a long time (check out this playlist of videos from my lab at CMU from 9 years ago: https://www.youtube.com/watch?v=Uv0qX7N2sJw&list=PLLhv4FQp7z...).
I gave your system a try and it's wonderful. The quality of animations are very different than what you get from rigged rag-dolls.
There are pros and cons to these approaches; the nice thing about masking/cropping/rigging (as our old "Dranimate" system did and Meta's "Animated Drawings" does) is that you prepare once, and then you can animate as many times in as many different ways as you want; you can drive it with mocap data; or with real-time inputs as with the videos of Dranimate above). The bad thing is that the first time preparation takes time.
I can see a lot of magic emerging from the combination of the two. I have recently gotten deep into this again (becauase now we have two little ones that are drawing all the time, and we started a Preschool in coastal norcal so kids are all around and this sort of magic really works on them, IRL).
I would love to connect with you sometime if you are up for chatting. Maybe there is a there there.
https://kling.kuaishou.com/en
Side note: Nice video - setting up the rigging mesh reminds me of the "puppet warp" deformation system in Adobe Photoshop.
@Vic:
Bit of advice, you need to build some kind of a static checker (either in terms of the total compressed size of the video - very small file sizes likely indicate a failed gen, or in terms of a hash as a measure of frame-to-frame changes) - to help set up an automated appeals for customers... having to manage this on a case-by-case basis will destroy any enthusiasm you might have for this project.