LIDAR sucks, accuracy wise. If you want accuracy, and hate yourself, then you need an iPhone XR/XS because that was the generation with the most accurate FaceID (for whatever reason). Or go photogrammetry, the LIDAR can help but isn’t the main thing there… this is both free and great. With a Mac you can get the data processed faster, or it can be done (paid) via cloud, or with less accuracy and a bit of patience, on device. It’s not going to be a professional solution, but depending on the task it works and chances are the hardware is already there :)
Stampela
joined 2 years ago
With access to a 3d printer one could print something like this https://www.thingiverse.com/thing:5430213/ (that I did print and works fine) or any other similar design.
Sounds about right. But a multimodal one? Ehh… sticking with Meta, their smallest LLaMa is a 7b, and as such without any multimodal features it’s already going to use most of the Quest’s 8gb and it would be slow enough that people wouldn’t like it. Going smaller is fun, for example I like (in the app I linked) to use a 1.6b model, it’s virtually useless but it sure can summarize text. And to be fair, there are multimodal ones that could run on the Quest (not fast), but going small means lower quality. For example the best one I can run on my phone takes… maybe 20 seconds? To generate this description “ The image shows three high-performance sports cars racing on a track. The first car is a white Lamborghini, the second car is a red Ferrari, and the third car is a white Bugatti. The cars are positioned in a straight line, with the white Lamborghini in the lead, followed by the red Ferrari, and then the white Bugatti. The background is blurred, but it appears to be a race track, indicating that the cars are racing on a track.” and it’s not bad. But
I’m not sure I’d call it trustworthy :D
If you happen to have an iPhone and want to get a sense of how difficult to run are LLM on a mobile device, there’s a free app https://apps.apple.com/app/id6497060890 that allows just that. If your device has at least 8gb of memory then it will even show the most basic version of LLaMa (just text there), and since everything is done on device, you can even try it in airplane mode. Less meaningful would be running it on a computer, for that I suggest https://lmstudio.ai/ that is very easy to use.
Running locally a LLM is quite the task, and the Quest 3 is way underspecced to do what’s being added. It’ll be the usual sending a picture with a request, having the servers process it and then receiving a response… so while I don’t have any doubt they’ll use all data they receive, the device itself isn’t going to do anything aside from sending pictures.
Yep. No artistic skills here, fun shitposts like this one for me are only fueled by some sort of generative AI. In this instance I tried a few different models (initially I got a woman with a red shirt uniform and a bee logo, then a red shirt with yellow and black highlights, a different model gave me a buff, hairy bee in a red shirt uniform… on top of the enterprise, holding a small enterprise in a hand) but had to give up and use Flux even if it’s the most intensive to run. Hardly perfect, but it’s fun and easy to recognize :)