the concept has great potential, but at this stage the generations from either text or image to video have a long way to go before you can produce anything close to cinematic or realistic results. As of now, anything over 4 seconds decays details, hallucinates into disfigured, non realistic shapes and maintains little cohesiveness over time. I love the idea, but for every close to good result, I have to churn through 15-20 dissapointing ones. I will hang in there, but certainly hope they figure out a way to maintain some consistency to the original seed throughout the generation and find a way to limit these grossly unrealistic hallaucinations.
I'm really enjoying the "grossly unrealistic hallaucinations" although I'm still generating a fair ammount of garbage in order to get shots that I like.
It’s gonna be amazing when we can upload an Audio file, like reading from a book, and then it auto generates.
this just blew my mind!
This is just amazing. It shows us what the future looks like.
Please check this problem , image to video , getting disfigured images
was the last picture even animated?
last shot did have a slight zoom in and head twist... but yep hardly "animated".
you should add all camera view types, for the promting , some kind of dropdowns, with camera, lighting , ect
At least the cameraman survived
I think it's amazing, everyone can make his big movie
I love it 🔥
Time is Light !
Interesting. Despite using the same seed number, the man is wearing a different jacket
Thanks.👍
needs more work
Always has been.
the concept has great potential, but at this stage the generations from either text or image to video have a long way to go before you can produce anything close to cinematic or realistic results. As of now, anything over 4 seconds decays details, hallucinates into disfigured, non realistic shapes and maintains little cohesiveness over time. I love the idea, but for every close to good result, I have to churn through 15-20 dissapointing ones. I will hang in there, but certainly hope they figure out a way to maintain some consistency to the original seed throughout the generation and find a way to limit these grossly unrealistic hallaucinations.
I'm really enjoying the "grossly unrealistic hallaucinations" although I'm still generating a fair ammount of garbage in order to get shots that I like.
HOT DIGGITY DAMN