MoE-LLaVA combines images and text using an efficient model structure.
― 6 min read
Li Yuan
MagicTime transforms written descriptions into dynamic time-lapse videos with improved realism.
― 6 min read
Introducing a framework that improves image aesthetics evaluation through visual and language integration.
― 4 min read
A new dataset and model enhance video captioning quality for machines.
― 5 min read
DF40 offers a comprehensive approach to improving deepfake detection methods.
― 6 min read
New benchmarks improve how we evaluate generated time-lapse videos.
― 6 min read
A new method enhances video generation quality and efficiency.
― 6 min read
Innovative techniques improve the detection of deepfake videos amidst evolving technology.
― 4 min read
A look at continual learning and innovative methods to retain knowledge in AI models.
― 7 min read
A new method for creating videos that preserve identity and improve visual quality.
― 5 min read
Easily generate high-quality videos with just a few words using Open-Sora Plan.
― 6 min read
Learn how NPP improves AI image generation efficiency and quality.
― 5 min read
RoomPainter creates stunning textures for indoor designs quickly and efficiently.
― 6 min read