Given you would need to pay actors and a production team to do this conventionally, $250/m is massively undercutting the cost of a human created equivalent.
Even if this produces shit half the time, there's enough greedy marketing agency owners out there that will be thinking they can save tens of thousands a month in salary by gutting their video production teams
Lol, you think this is for the poors, this is so one business man in an office in Tahiti can generate infinite videos and finally monopolize the welth of the content creators into the billionaire class
It was fast, for sure, but tv shows in two years are very unlikely. If we could get at least more consistent results and better character control, that would already be a lot
AI has been able to make pictures with the right amount of fingers for about four years. It involved cherry picking and sometimes inpainting. The biggest thing that’s changed is resolution and prompt adherence.
Even the best models sometimes (frequently) give people extra fingers.
A standard Hallmark movie, but it keeps getting increasingly unhinged and disjointed. Could be a masterpiece… or more likely just trash as you’d expect.
4
Google unveils new video generation model with audio | Spyke
I don't want to live on this planet anymore man. Holy fuck we're just watching creativity die.
That looks cool, but maybe not $250 a month cool.
Given you would need to pay actors and a production team to do this conventionally, $250/m is massively undercutting the cost of a human created equivalent.
Even if this produces shit half the time, there's enough greedy marketing agency owners out there that will be thinking they can save tens of thousands a month in salary by gutting their video production teams
Lol, you think this is for the poors, this is so one business man in an office in Tahiti can generate infinite videos and finally monopolize the welth of the content creators into the billionaire class
the primary use case
Seems to be the most lucrative also.
Cherrypicked and even these have issues.
It is progress I guess.
Less than two years ago AI couldn't make an image of a person with the right amount of fingers.
Now we are here. In two years AI video could produce a TV show or movie.
It was fast, for sure, but tv shows in two years are very unlikely. If we could get at least more consistent results and better character control, that would already be a lot
AI has been able to make pictures with the right amount of fingers for about four years. It involved cherry picking and sometimes inpainting. The biggest thing that’s changed is resolution and prompt adherence.
Even the best models sometimes (frequently) give people extra fingers.
It will be funny when someone maps this to the scenes/characters they are training it on.
Let's see how crappy upcoming Hallmark home video xmas movies will be
Oh, wait
A standard Hallmark movie, but it keeps getting increasingly unhinged and disjointed. Could be a masterpiece… or more likely just trash as you’d expect.