Looks good. I wonder what use case Apple has in mind though, or I suppose this is just what the researchers themselves were interested in, perhaps due to the current zeitgeist. I'm not really sure how it works at big tech companies with regards to research, are there top down mandates?
To add things to videos you create with your phone. TikTok and Insta will probably add this soon, but I suppose Apple is trying to provide this feature on “some level”. That means you don’t have to send your video through a social media platform first to creatively edit it (the platforms being the few tools that let you do generative video).
I guess Apple is big in video production and animation with some ties via Pixar and Disney. Since Jobs started Pixar and it all got tied up in myriad of different ways.
Apple has a video understanding model too. I can't wait to find out what accessibility stuff they'll do with the models. As a blind person, AI has changed my life.
I wonder if there's anything that can help blind people to navigate the world more easily - I guess in the future AR Glasses won't just be for the sighted but allow people without vision to be helped considerably. It really is both amazing and terrifying the future we're heading towards.
I'm only commenting because I absolutely love this thread. It's an insight into something I think most of us are quite (I'm going to say it...) blind to in our normal experiences with daily life, and I find immense value in removing my ignorance about such things.
Hi Devin and other folks, I'm looking for software developers who are blind or hard of sight as there is a tool I'm building that I think might be of interest to them (it's free and open source). If you or anyone you know is interested in trying it please get in touch through my email.
I'm in the middle of updating a new public transit app my team wrote in Flutter and want it to flow better for blind people. Would you rather use AI chat session with realtime information or go through the screens with VoiceOver/TalkBack controls? What about trust and hallucinations?
Hopefully this will make into some useful feature in the ecosystem and not contribute to having just more terrible slop. Apple has saved itself from the destruction of quality and taste that these model enabled, I hope it stays that way.
The license[0] seems quite restrictive, limiting it's use to non commercial research. It doesn't meet the open source definition so it's more appropriate to call it weights available.
As for the license, happily, Model Weights are the product of machine output and not creative works, so not copyrightable under US law. Might depend on where you are from, but I would have no problem using Model Weights however I want to and ignoring pointless licenses.
From the paper, this is a research model aimed at dealing with the runaway error common in diffusion video models - the latent space is (proposed to be) causal and therefore it should have better coherence.
For a 7b model the results look pretty good! If Apple gets a model out here that is competitive with wan or even veo I believe in my heart it will have been trained with images of the finest taste.
I was upset the page didnt have videos immediately available, then I realized I have to click on some of the tabs. One red flag on their github is the license looks to be their own flavor of MIT (though much closer to MS-PL).
It’s not really relevant to this release specifically but it irks me that, in general, an “open weights model” is like an “open source machine code” version of Microsoft Windows. Yes, I guess I have open access to view the thing I am about to execute!
This Apple license is click wrap MIT with the rights, at least, to modify and redistribute the model itself. I suppose I should be grateful for that much openness, at least.
Apple's got to stop running their AI group like a university lab. Get some actual products going that we can all use--you know, with a proper fucking web UI and a backend.
This looks interesting. This project has some novelty as a research and actually delivered a promising PoC but as a product it implies that its training was severely constrained by computing resources, which correlates well with the report that their CFO overruled CEO's decision on ML infra investment.
JG's recent departure and follow up massive reorg to get rid of AI, rumors on Tim's upcoming step down in early 2026... All of these signals indicate that those non-ML folks have won corporate politics to reduce the in-house AI efforts.
I suppose this was a part of serious efforts to deliver in-house models but the directional changes on AI strategy made them to give up. What a shame... At least the approach itself seem interesting and hope others to take a look and use it for building something useful.
32 comments
[ 3.0 ms ] story [ 45.5 ms ] threadThey don’t say for how long.
Do the examples in the repo run inference on Mac?
They should really buy Snapchat.
I know this is a low quality comment, but I'm genuinely happy for you.
Any tips you can give?
Did I miss anything?
[0]https://github.com/apple/ml-starflow/blob/main/LICENSE_MODEL
As for the license, happily, Model Weights are the product of machine output and not creative works, so not copyrightable under US law. Might depend on where you are from, but I would have no problem using Model Weights however I want to and ignoring pointless licenses.
> The checkpoint files are not included in this repository due to size constraints.
So it's not actually open weights yet. Maybe eventually once they actually release the weights it will be. "Soon"
For a 7b model the results look pretty good! If Apple gets a model out here that is competitive with wan or even veo I believe in my heart it will have been trained with images of the finest taste.
This Apple license is click wrap MIT with the rights, at least, to modify and redistribute the model itself. I suppose I should be grateful for that much openness, at least.
JG's recent departure and follow up massive reorg to get rid of AI, rumors on Tim's upcoming step down in early 2026... All of these signals indicate that those non-ML folks have won corporate politics to reduce the in-house AI efforts.
I suppose this was a part of serious efforts to deliver in-house models but the directional changes on AI strategy made them to give up. What a shame... At least the approach itself seem interesting and hope others to take a look and use it for building something useful.