baaivision/NOVA
[ICLR 2025] Autoregressive Video Generation without Vector Quantization
This project helps content creators, marketers, and digital artists generate high-quality images and videos from simple text descriptions or existing images. You provide a text prompt or an image, and it outputs a corresponding image or a short video. It's designed for anyone needing to quickly create visual assets for campaigns, presentations, or creative projects without needing advanced design skills.
635 stars.
Use this if you need to rapidly produce diverse visual content, from still images to dynamic videos, by just describing what you want.
Not ideal if you require frame-by-frame precision editing or highly specialized visual effects, as this tool focuses on generative content creation.
Stars
635
Forks
22
Language
Python
License
Apache-2.0
Category
Last pushed
Oct 29, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/baaivision/NOVA"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
hao-ai-lab/FastVideo
A unified inference and post-training framework for accelerated video generation.
ModelTC/LightX2V
Light Image Video Generation Inference Framework
thu-ml/TurboDiffusion
TurboDiffusion: 100–200× Acceleration for Video Diffusion Models
PKU-YuanGroup/Helios
Helios: Real Real-Time Long Video Generation Model
PKU-YuanGroup/MagicTime
[TPAMI 2025🔥] MagicTime: Time-lapse Video Generation Models as Metamorphic Simulators