An open source AI tool to animate children's drawings | Hacker News Reader

An open source AI tool to animate children's drawings

github.com

318 pointssnork_alt14 comments

Open articleView on HN

Follow the discussion here: https://news.ycombinator.com/item?id=35561203

You could do live-action animated Teen Girl Squad with this ...

Open Source Greg finally gets his day.

Amazing work! Someone is probably already working on porting it to work as an extension on Stable Diffusion webui.

Yeah, haven't tested it but I assume this would work for realistic cartoon/cgi characters?

Maybe the researchers didn't want to freak out anyone who does 2D animation? "Hey everyone, look at this toy we made that would never be used to animate anything but toy doodles. No one's 2D animation jobs are being replaced here - this project would never do that!"

No animator is looking at those examples and being worried. It's interesting for sure but I would put it on the most bottom tier of animation.

The bottom tier of animation is still pretty big. You apparently are too young to remember what a lot of animation was like in the 70s and 80s.

Is it like how typists were the bottom tier of office work?

Look at what AI generated images were like a year or two ago. They were mostly abstract, dream like images that were cool but not usable. They have improved 1000x in a year. Bottom tier animation from cartoon images now, could be seriously impressive in a few short years.

This doesn’t look like AI.

This looks like an algorithm like how hash map is an algorithm.

It’s also being presented at SIGGRAPH which further makes me think it’s just an algorithm to map motion capture data to a 2D image. We can already map motion capture data to a 3D model.

Yeah I didn't read through it earlier. Seems like there are 3 parts from my understanding. You need some motion capture service like Rokoko/DeepMotion to create BVH files describing the movement from a video. The algorithm this guy created animates/renders by taking the BVH and an annotation file from the drawing. But the project did "train a drawn humanoid figure detector and pose estimator and provided scripts to automatically generate annotation files from the model predictions" so that part does have machine learning.

I would love to use this for my old animation website https://www.superanimo.com/ But due to the AI boom I have tons of work to do on my other projects, so I can't sink time into modernizing my crappy animation site.

Very cool, yet all I can think of is DoodleBob.

After sampling/covering every song and re-making every movie to death, we have now taken to mining the minds of children for new ideas to steal.

It's not like they can apply for copyright protection or sue to defend their IP!

I love the future.

reminder to concerned artists: we would have never commissioned you to do this

Reply on news.ycombinator.com