Make a Video by Meta VS Sonix

- Meta's Make-A-Video had a very similar approach to this. What could we learn from them? Source: 9 months ago

I suspect that the model used for this video wasn't either of the tools listed in the text-to-video section there, however- it looks like the studio that made it probably got access to a model that isn't publicly-available yet, like Meta's Make-A-Video or Runway. Source: about 1 year ago

This is what FAIR has been doing with https://makeavideo.studio/ . They have a stable diffusion model trained on image pairs in sequence. If this was adopted by the community more broadly as a basis you'd be able to resolve things like flickering across frames much more robustly. Source: about 1 year ago

Yeah, I feel from looking at https://makeavideo.studio/ and https://imagen.research.google/video/ that it's getting there. Source: about 1 year ago

We're seeing early examples like Google's Imagen and Meta's Make a Video – which look to be general, and might make sense when creating clips. Source: over 1 year ago

There's dozens of tools out there for this these days. I'd recommend sonix.ai they give you 30 minutes free. Source: 11 months ago

Do you have a budget? If so, there's this tool I've worked with called Sonix that generates transcripts of what you feed into it. It's not super accurate, but it's good enough. One of the features is that you can "highlight" chunks of text, and have it spit out an XML that will have a sequence containing only the highlighted text. Source: about 1 year ago

Sonix was the one I used because it had 30 free minutes and the video was only 10-11 minutes long. It seems to have done a really decent job, but not sure if that's because the source audio is pretty clear. Source: about 1 year ago

Sonix.ai does many languages and is quite good. Source: about 1 year ago

I am struggling with this as well, but one good tool for me has been sonix.ai, which can transcribe pretty well (posted a little while ago about it). Source: about 2 years ago