IDK if the site is being hugged to death but I can only load the first video. Even in just one viewing there were noticeable artifacts, so my impression is that Veo is still in the lead here.
Sora 2
11–20 of 916 posts
Re: Sora 2
#12I find it comical that OpenAI with all the power of CharGPT even them are unable to release an app for both iOS and Android at the same time. Wow, good marketing for Codex.
Re: Sora 2
#13Re: Sora 2
#14Just seeing the examples that I assumed are cherry picked, it seems like they're still behind on Google when it comes to video generation, the physics and stylized versions of these shots seem not great. Veo3 was such a huge leap and is still ahead of many of the other large AI labs.
Re: Sora 2
#15Did they make human voices sound robotic on purpose? Is that some kind of Ai fingerprinting? It's way too obvious
It's very hard for simultaneous good audio generation with video generation (simultaneous generation is necessary to maintain lip sync). Veo 3 et al also have flat monochannel audio, but not as bad as these Sora 2 demos.
Re: Sora 2
#16I find it comical that OpenAI with all the power of CharGPT even them are unable to release an app for both iOS and Android at the same time. Wow, good marketing for Codex.
That is more of a statement of the complete dominance of iPhones among gen z.
Re: Sora 2
#17The most interesting thing by far is the ability to include video clips of people and products as a part of the prompt and then create a realistic video with that metadata. On the technical side, I'm guessing they've just trained the model to conditionally generate videos based on predetermined characters -- it's likely more of a data innovation than anything architectural. However, as a user, the feature is very cool and will likely make Sora 2 very useful commercially.
However, I still don't see how OpenAI beats Google in video generation. As this was likely a data innovation, Google can replicate and improve this with their ownership of YouTube. I'd be surprised if they didn't already have something like this internally.
Re: Sora 2
#18Someone remind me the benefits of mass produced fake videos again?
Re: Sora 2
#19Overall, appears rather underwhelming. Long way to go still for video generation. Also, launching this as a social app seems like yet another desperate try to productize and monetize their tech, but this is the position big VC money forces you into.
I've perhaps been away from the scene for a bit, but I'm very impressed. To me this is absolutely "video generation", and I don't get your disdain for productization and monetization; last I checked this wasn't "Basic Research News".
Re: Sora 2
#20The example prompt "intense anime battle between a boy with a sword made of blue fire and an evil demon demon" is super clearly just replicating Blue Exorcist https://en.m.wikipedia.org/wiki/Blue_Exorcist
one of the example prompts is literally:
Prompt: in the style of a studio ghibli anime, a boy and his dog run up a grassy scenic mountain with gorgeous clouds, overlooking a village in the distant background