Consistency between video created
#14
by levag - opened
Hello,
I am using the playground to generate videos for a short movie I have writen. I have an issue with the consistency of the characters I am using. It would be great if I can upload a picture of a character and the model create a video based on a text but with the face based on the picture I've uploaded. Is there anything I can do to reach that goal with the current version of your playground?
The best I have found on this is to use the seed from a look you like and use it on the next video. It gets pretty close.
Can anyone suggest me a model text to video ,which is open source can be used for commercial purpose free (under apache 2.0 license )and also can be used on google colab free version .