Variable length frame conditioning for infinite length video generation. Can be used to generate videos from text that continue from an existing video or image. It can also generate the initial image using a standard text-to-image model from huggingface. Developed in collaboration with motexture and based on vseq2vseq.
Repo for inference can be found at ContinuitySeq.
- Downloads last month
- -
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support