431–440 of 570 posts
Earlier quoted context omitted.
Indeed, it's the advertisers who are paying for AI to watch videos....
And paying for my sofa to watch a unskippable 50s ad while I make a coffee.
>>models create, empowering artists to bring their creative vision Interesting logic the new era brings: something else creates, and you only "bring your vision to life", but what it means is left for readers questioning, your "vision" here is your text prompt? Were at a crossroads where the tools are powerful enough to make the process optional. That raises uncomfortable questions: if you don’t have to create anymor…
we can see what happened to opera/theater/hand drawn art as conclusive answer. humans move on to the newer more easier to create/consume thing in general (digital music/tv/digital art) and a small percentage of people treat the older mode of creation as high art coz it's more difficult and expensive to learn / implement.
What is true is that cheapening the cost of creative production will yield a wider variety of expression: we will see what people prefer to consume.
Can we talk about the elephant in the room, porn and i mean the weird and dangerous one? that moment in history of AI is going to happen and when it did shit will hit the fan.
tbh, wasnt that impressed maybe its cause social media has been heavily marketing out all these things in bulkkk and moreover, at this point, it just feels one company copying what the other released, even the names feel not original?
Like most AI image or video generation tools, they produce results that look good at first glance, but the more you watch, the more flaws and sloppiness you notice, and they really lack storytelling
I don’t get how someone can look at these videos and think “wow there’s lots of flaws and it’s sloppy and no storytelling” rather than “holy smokes this stuff is improving fast!” In 2 years we have moved from AI video being mostly a pipe dream to some incredible clips! It’s not what this is like now, but what will it be like in 10 years!
Earlier quoted context omitted.
Why videos are important for robotics?
If you can generate realistic video stream, responding to player movements and interactions, you can train your robot using that video stream. It's much more scalable, compared to building physical environments and performing real-world training. Of course the alternative is to use game engines, but it's possible that AI would generate more realistic video stream for the same money spent. Those recent AI-generated vi…
Earlier quoted context omitted.
Google Flow is remarkable as video editing UX, but Imagen 4 doesn't really stand out amongst its image gen peers. I want to interrupt all of this hype over Imagen 4 to talk about the totally slept on Tencent Hunyuan Image 2.0 that stealthily launched last Friday. It's absolutely remarkable and features: - millisecond generation times - real time image-to-image drawing capabilities - visual instructivity (eg. you can…
This is amazing, can’t see how I’ve missed it. Thank you!
If Tencent wants to keep Google from winning the game, they should open source their models. From my perspective right now, it looks like Google is going to win this entire game, and open source AI might be the only way to stop that from being a runaway victory.
An indie film with poor production values, even bad acting can grip you, make you laugh and make you cry. The consistency of quality is key - even if it is poor. The directing is the red thread throughout the scenes. Anything with different quality levels interrupts your flow and breaks your experience. The problem with AI video content at this stage is that the clips are very good 'in themselves', just as LLM result…
You might want to look up NeuralViz on YouTube. 180k subscribers. They've been building out an entire cinematic universe using AI video tools. And it's by far the funniest show I've watched in years. So the claim that "let you engage beyond an individual clip will not be possible for a long time" isn't true. People are already doing it. https://www.youtube.com/@NeuralViz
The format of the shows are mostly clip-based - man on the street, news hour, etc - and obviously the jokes are all written by someone with a good sense of humour.
Not to discount that this is, as you say, an example of someone using AI to successfully create characters and stories that resonate with people. it's just still very much because of a creative human's talent and good taste that it's working.
Earlier quoted context omitted.
The winning image entry for "The Yarrctic Circle" by OpenAI 4o doesn't actually wields a cutlass. It's very aesthetically pleasing, even though it's so wrong in all fundamental aspects (perspective is nonsensical and anatomy is messed up, with one leg 150% longer than the other, ...). It's a very interesting resource to map some of the limits of existing models.
In my own testing between the two this is what I’ve noticed. Imagen will follow the instructions, and 4o will often not, but produces aesthetically more pleasing images. I don’t know which is more important, but I would say that people mostly won’t pay for fun but disposable images, and I think people will pay for art but there will be an increased emphasis on the human artist. However users might pay for reliable to…
An indie film with poor production values, even bad acting can grip you, make you laugh and make you cry. The consistency of quality is key - even if it is poor. The directing is the red thread throughout the scenes. Anything with different quality levels interrupts your flow and breaks your experience. The problem with AI video content at this stage is that the clips are very good 'in themselves', just as LLM result…
You might want to look up NeuralViz on YouTube. 180k subscribers. They've been building out an entire cinematic universe using AI video tools. And it's by far the funniest show I've watched in years. So the claim that "let you engage beyond an individual clip will not be possible for a long time" isn't true. People are already doing it. https://www.youtube.com/@NeuralViz