Earlier quoted context omitted.
FYI dang they kinda ripped off our product down to copying the UI (Hedra.com). Our model is about 12x faster and supports 4 minute long videos…
[flagged]
Why did you make a brand new account to comment this?
Show HN: Infinity – Realistic AI characters that can speak
211–220 of 320 posts
Re: Show HN: Infinity – Realistic AI characters that can speak
#212Earlier quoted context omitted.
Fwiw, you’ve got one video on your homepage and everything else is locked behind a signup button. I know that signup requirement is an article of faith amongst some startup types, but it’s not a surprise to me shareable examples lead to sharing.
We have a sign-up because we ensure users accept our terms of service and acceptable use policy before creating their first video, which affirms they understand how their data is used (legally required in most US states) and will not use our technology to cause harm.
You can have that without a sign up.
Re: Show HN: Infinity – Realistic AI characters that can speak
#213Say I’m a politician who gets caught on camera doing or saying something shady. Will your service do anything to prevent me from claiming the incriminating video was just faked using your technology? Maybe logging perceptual hashes of every output could prove that a video didn’t come from you?
I think you're fine because these videos don't look or sound the least bit realistic
Re: Show HN: Infinity – Realistic AI characters that can speak
#214Very cool, thanks for the play.
https://6ammc3n5zzf5ljnz.public.blob.vercel-storage.com/inf2...
Managed to get it working with my doggo.
Re: Show HN: Infinity – Realistic AI characters that can speak
#215super nice. why does it degrade quality of image so much, makes it looks obviously AI-generated rapidly.
Re: Show HN: Infinity – Realistic AI characters that can speak
#216[flagged]
Neither your nor their model is remotely close to actually fooling anymore, so celebs could only be used for (very funny) obvious satire. I see no risk of harm here.
Also, two boxes for uploading the only two inputs to a model is not a new idea. One could say you stole it from Gradio (but even that's silly).
Re: Show HN: Infinity – Realistic AI characters that can speak
#217Given that I don't agree with many of Yann LeCun's stances on AI, I enjoyed making this: https://6ammc3n5zzf5ljnz.public.blob.vercel-storage.com/inf2... Hello I'm an AI-generated version of Yann LeCoon. As an unbiased expert, I'm not worried about AI. ... If somehow an AI gets out of control ... it will be my good AI against your bad AI. ... After all, what does history show us about technology-fueled conflicts among…
it’s hard to disagree with him with any empirical basis when all
of his statements seem empirically sound and all of his opponent’s AI Doomer statements seem like evidenceless FUD
I couldn’t help noticing that all the AI Doomer folks are pure materialists who think that consciousness and will can be completely encoded in cause-and-effect atomic relationships. The real problem is that that belief is BS until proven true. And as long as there are more good actors than bad, and AI remains just a sophisticated tool, the good effects will always outweigh the bad effects.
Re: Show HN: Infinity – Realistic AI characters that can speak
#218Given that I don't agree with many of Yann LeCun's stances on AI, I enjoyed making this: https://6ammc3n5zzf5ljnz.public.blob.vercel-storage.com/inf2... Hello I'm an AI-generated version of Yann LeCoon. As an unbiased expert, I'm not worried about AI. ... If somehow an AI gets out of control ... it will be my good AI against your bad AI. ... After all, what does history show us about technology-fueled conflicts among…
it’s hard to disagree with him with any empirical basis when all of his statements seem empirically sound and all of his opponent’s AI Doomer statements seem like evidenceless FUD I couldn’t help noticing that all the AI Doomer folks are pure materialists who think that consciousness and will can be completely encoded in cause-and-effect atomic relationships. The real problem is that that belief is BS until proven tr…
Hello, thank you for sharing your thoughts on this topic. I'm currently writing a blog post where the thesis is that the root disagreement between "AI doomers" and others is actually primarily a disagreement about materialism, and I've been looking for evidence of this disagreement in the wild. Thanks for sharing your opinion.
Re: Show HN: Infinity – Realistic AI characters that can speak
#219I'd love to enable Keltar, the green guy in the ceramic cup, to do this www.molecularReality/QuestionDesk
Re: Show HN: Infinity – Realistic AI characters that can speak
#220For such models, is it possible to fine-tune models with multiple images of the main actor? Sorry, if this question sounds dumb, but I am comparing it with regular image models, where the more images you have, the better output images you generate for the model.
It is possible to fine-tune the model with videos of a specific actor, but not images. You need videos to train the model. We actually did this in early overfitting experiments (to confirm our code worked!), and it worked surprisingly well. This is exciting to us, because it means we can have actor-specific models that learn the idiosyncratic gestures of particular person.
This is actually great, waiting for your API integration or replicate integration to get my hands dirty :)