Pittsburgh Arts, Regional Theatre, New Work, Producing, Copyright, Labor Unions,
New Products, Coping Skills, J-O-Bs...
Theatre industry news, University & School of Drama Announcements, plus occasional course support for
Carnegie Mellon School of Drama Faculty, Staff, Students, and Alumni.
CMU School of Drama
Thursday, February 15, 2024
Apple is developing an AI tool for animating images using text prompts
The Verge: Researchers at Apple have unveiled Keyframer, a prototype generative AI animation tool that enables users to add motion to 2D images by describing how they should be animated.
4 comments:
Julia Adilman
said...
I feel like this would be such a revolutionary invention, especially for graphic designers, video editors, and all around media content creators. It is crazy how much AI can do for us and how much faster it can complete jobs. I can not imagine how much time it could save for people that just make image graphics and little animations on a daily basis. I do wonder about what its limits are and what kinds of things this tool has difficulties with. I also find it quite interesting that Apple is the one who is conducting all of this research on this AI animation tool. I don’t think that I would have initially expected that. I wonder if and how they will incorporate this Keyframer tool with their products in the future. I do worry about these kinds of tools taking away jobs in the future, but I think that there is a way for AI to just enhance people’s work and make it even more interesting and allow time for designers and artists to play around with other things.
I feel like this technology, at least in the state it is currently in, seems like a pretty good thing. I often have very mixed feelings about AI technology because it can be far too successful at destroying the jobs of many creatives and also can steal content and ideas from others. Being able to describe animations and then having them coded for seems like it could be pretty beneficial. As the article said, this technology is not yet advanced enough to animate a movie for example, but it can do smaller, more simplistic things. I think this will make it so the jobs of animators can be sped up and they will have to spend less time with more trivial tasks. Additionally, it could allow animators and designers to visualize ideas more quickly and not waste time coding in dozens of ideas themselves. Of course, this tech could take on harmful forms, so like all other AI tech, should be watched closely.
I'm really excited to see where Apple is going to go wih advances in artifical intelligence in 2024. I've noticed that Apple is typically a later adopter of any new technology, as they're trying to find ways to integrate it into their ecosystem, for better or for worse. This means that Apple, while creating new technology later, can typically produce a more finished final product that many consumers will want to buy. Take the example of the vision pro: when Meta unveiled their grand plans for an AR/VR future, many companies adopted quickly, but Apple stayed back, until the launch of the vision pro. I think they're doing something similar with these small AI announcements, where they work towards incremental change and then launch something all at once.
I think the thing that must be remembered when working with animation is that it is a lot harder to train a computer model to properly follow the rules of animation, as it something that is hard to quantify in code, as well as something that needs intuition to work. However, the article did mention that the model just does simple web based animations which could be useful. I don't understand the push for everything to be AI, especially when a lot of these process just cannot reach the same level as human artists making things (music creation and animation being major sticking points, as well as making compelling writing). I think AI can be a useful tool, however, relying on it for everything may be a bit overzealous. I could just be cynical, but I don't think we should be trying to use these LLMs to cut out human artists.
:format(webp)/cdn.vox-cdn.com/uploads/chorus_asset/file/25285786/Keyframer_Apple_hed.jpg)
4 comments:
I feel like this would be such a revolutionary invention, especially for graphic designers, video editors, and all around media content creators. It is crazy how much AI can do for us and how much faster it can complete jobs. I can not imagine how much time it could save for people that just make image graphics and little animations on a daily basis. I do wonder about what its limits are and what kinds of things this tool has difficulties with. I also find it quite interesting that Apple is the one who is conducting all of this research on this AI animation tool. I don’t think that I would have initially expected that. I wonder if and how they will incorporate this Keyframer tool with their products in the future. I do worry about these kinds of tools taking away jobs in the future, but I think that there is a way for AI to just enhance people’s work and make it even more interesting and allow time for designers and artists to play around with other things.
I feel like this technology, at least in the state it is currently in, seems like a pretty good thing. I often have very mixed feelings about AI technology because it can be far too successful at destroying the jobs of many creatives and also can steal content and ideas from others. Being able to describe animations and then having them coded for seems like it could be pretty beneficial. As the article said, this technology is not yet advanced enough to animate a movie for example, but it can do smaller, more simplistic things. I think this will make it so the jobs of animators can be sped up and they will have to spend less time with more trivial tasks. Additionally, it could allow animators and designers to visualize ideas more quickly and not waste time coding in dozens of ideas themselves. Of course, this tech could take on harmful forms, so like all other AI tech, should be watched closely.
I'm really excited to see where Apple is going to go wih advances in artifical intelligence in 2024. I've noticed that Apple is typically a later adopter of any new technology, as they're trying to find ways to integrate it into their ecosystem, for better or for worse. This means that Apple, while creating new technology later, can typically produce a more finished final product that many consumers will want to buy. Take the example of the vision pro: when Meta unveiled their grand plans for an AR/VR future, many companies adopted quickly, but Apple stayed back, until the launch of the vision pro. I think they're doing something similar with these small AI announcements, where they work towards incremental change and then launch something all at once.
I think the thing that must be remembered when working with animation is that it is a lot harder to train a computer model to properly follow the rules of animation, as it something that is hard to quantify in code, as well as something that needs intuition to work. However, the article did mention that the model just does simple web based animations which could be useful. I don't understand the push for everything to be AI, especially when a lot of these process just cannot reach the same level as human artists making things (music creation and animation being major sticking points, as well as making compelling writing). I think AI can be a useful tool, however, relying on it for everything may be a bit overzealous. I could just be cynical, but I don't think we should be trying to use these LLMs to cut out human artists.
Post a Comment