baaivision/NOVA
NOVA is an autoregressive model for generating images and videos without vector quantization, achieving continuous-valued generation through a diffusion-based approach.
Not currently ranked — collecting fresh signals.
star history
NOVA (NO-nQuantized Video Autoregressive Model) enables autoregressive image and video generation without discrete vector quantization. Instead, it uses continuous-valued predictions combined with diffusion-based training to generate high-quality visual content. The model handles both text-to-image and text-to-video generation tasks, with inference demos available through HuggingFace spaces.
Frequently asked
- What is baaivision/NOVA?
- NOVA is an autoregressive model for generating images and videos without vector quantization, achieving continuous-valued generation through a diffusion-based approach.
- Is NOVA open source?
- Yes — baaivision/NOVA is open source, released under the Apache-2.0 license.
- What language is NOVA written in?
- baaivision/NOVA is primarily written in Python.
- How popular is NOVA?
- baaivision/NOVA has 656 stars on GitHub.
- Where can I find NOVA?
- baaivision/NOVA is on GitHub at https://github.com/baaivision/NOVA.