101–110 of 1001 posts
This is going to make the latest election really interesting (and scary). Is anyone working to ensure a faked video of Biden that looks plausible but is AI generated doesn't get significant traction at a critical moment of the election?
This is insane. Even though there are open-source models, I think this is too dangerous to release to the public. If someone would've uploaded that Tokyo video to youtube, and told me it was a drone.. I would've believed them. All "proof" we have can be contested or fabricated.
The key word there is "someone". The only way forward is to care a lot more about our sources. Trust is about to become really valuable.
They'll simply see an inflammatory tweet from their leader on Twitter.
This is insane. Even though there are open-source models, I think this is too dangerous to release to the public. If someone would've uploaded that Tokyo video to youtube, and told me it was a drone.. I would've believed them. All "proof" we have can be contested or fabricated.
> All "proof" we have can be contested or fabricated. This has been the case for a while now already, it's better that we just rip off the bandaid and everyone should become a skeptic. Standards for evidence will need to rise.
This is leaps and bounds beyond anything out there, including both public models like SVD 1.1 and Pika Labs' / Runway's models. Incredible.
Don't get overly excited until you can actually use the technology.
This is leaps and bounds beyond anything out there, including both public models like SVD 1.1 and Pika Labs' / Runway's models. Incredible.
Let's hold our breath. Those are specifically crafted hand-picked good videos, where there wasn't any requirement but "write a generic prompt and pick something that looks good", with no particular requirements. Which is very different from the actual process where you have a very specific idea and want the machine to make it happen. DALL-E presentation also looked cool and everyone was stoked about it. Now that we k…
Not loving that there are more details on safety than details of the actual model, benchmarks, or capabilities. > That’s why we believe that learning from real-world use is a critical component of creating and releasing increasingly safe AI systems over time. "We believe safety relies on real-world use and that's why we will not be allowing real-world use until we have figured out safety."
This is leaps and bounds beyond anything out there, including both public models like SVD 1.1 and Pika Labs' / Runway's models. Incredible.
Let's hold our breath. Those are specifically crafted hand-picked good videos, where there wasn't any requirement but "write a generic prompt and pick something that looks good", with no particular requirements. Which is very different from the actual process where you have a very specific idea and want the machine to make it happen. DALL-E presentation also looked cool and everyone was stoked about it. Now that we k…
They're literally taking requests and doing them in 15 minutes.
This is leaps and bounds beyond anything out there, including both public models like SVD 1.1 and Pika Labs' / Runway's models. Incredible.
It's very good. Unclear how far ahead of Lumiere it is ( https://lumiere-video.github.io/ ) or if its more of a difference in prompting/setttings.
Worth noting that Google also has Phenaki [0] and VideoPoet [1] and Imagen Video [2]
[0] https://sites.research.google/phenaki/
The signs are non-sensical but this is probably expected.