What are diffrensces between multi2vec_clip and multi2vec_bind?
Which should I use?
hi @syucchin !!
Welcome back!
Those are different multimodal models.
multi2vec-bind lives here, and is based on Meta ImageBind
While multi2vec-clip here:
and the docs here:
By the way, if you are looking for a cool example to play with multi2vec-bind check this one:
Let me know if this helps!
THanks!