tfjs VS stylegan2-pytorch

TensorFlow.js

Many people seem to be unaware of tensorflow.js, an official JS implementation of TF

https://github.com/tensorflow/tfjs

I'd love to see PyTorch in JS, but I think unless you get it running on the GPU it won't be able to do much.

TensorflowJS GitHub Repository

Also, Tensorflow.js WebGPU backend has been in the works for quite some time: https://github.com/tensorflow/tfjs/tree/master/tfjs-backend-...

It's a pity that tfjs never truly developed any decent ops. E.g. you need lgamma to implement the cap for zero-inflated poisson regression and tfjs simply doesn't have that: https://github.com/tensorflow/tfjs/issues/2011

People have been doing it for long with WebGL, see eg https://github.com/tensorflow/tfjs and https://cloudblogs.microsoft.com/opensource/2021/09/02/onnx-...

thanks, no not unity, going to show it as a demo with threejs + tensorflow on the web. I found a github request to add face orientation https://github.com/tensorflow/tfjs/issues/3835 looks like they assigned someone to add it but doesn't look like its available yet, but there's some posts about the math I can use to get rotations based on some of the landmarks

There already exist a wide variety of neural network inference engines that run in web browsers (e.g. TensorFlow.js and, my personal favorite for use with PyTorch models, ONNX Runtime Web), but pre- and post-processing has always required imperative manipulations on flat buffers rather than a clean ndarray interface.

Full docs and code: https://github.com/tensorflow/tfjs/tree/master/e2e/benchmarks/local-benchmark

export default function ChannelListBottomBar(): JSX.Element { const { client } = useChatContext(); const [micActive, setMicActive] = useState(false); const [audioActive, setAudioActive] = useState(false); return (

{client.user?.image && (

div> )}

{client.user?.name} span> {client.user?.online ? 'Online' : 'Offline'} span> p> button>

setMicActive((currentValue) => !currentValue)} > button> setAudioActive((currentValue) => !currentValue)} > button> button> div> ); }

I wonder if we will ever get a realism model which can produce normal faces like https://thispersondoesnotexist.com instead of like super symmetrical faces of models

this has been in circulation since a while AI images took off, and they certainly weren't convincing before they did. You know the old "try to name one thing in this image" macro? Pretty sure that was AI generated, there was also thispersondoesnotexist.com which was always pretty good but of course it is

Not the workflow for these images, but if you easily want to spice up your gens with a bit more natural look, try using images from thispersondoesnotexist.com with IPAdapter face model.

...then they just use the app on generated images of not real people (potentially based on specific inputs to remind you of a real person).

Also we can generate very realistic faces with AI, https://thispersondoesnotexist.com/ (old example), fully 3D faces are doable at this point. So in another 5-10 years a low profile model like him wouldn't even be hired for this, they would just generate a digital face model. Unionizing will only speed up studios adoption of digital replacements.

It looks like they all use a profile picture made with https://thispersondoesnotexist.com/