Deformable-ConvNets is a computer vision framework and a collection of neural network components designed to implement deformable convolutional neural networks. It provides adaptive convolutional layers and pooling implementations that modify their receptive fields based on input features to better capture the geometry of objects within images. The project enables the use of learnable sampling offsets and modulation masks to align convolutional grids with target object shapes. It includes specialized tools for visualizing learned offsets in convolutions and pooling layers, allowing for the an
Videocrafter is a latent diffusion model designed for AI video synthesis. It functions as both a text-to-video and image-to-video generation system, synthesizing high-quality video sequences from descriptive text prompts or static image inputs. The model utilizes a diffusion-based neural network to transform inputs into animated content, ensuring visual consistency and temporal coherence throughout the generated sequences. This allows for the creation of custom video clips and the animation of static images into fluid motion.
VideoSys: An easy and efficient system for video generation
Principalele funcționalități ale nus-hpc-ai-lab/videosys sunt: Computer Vision Frameworks, Diffusion Acceleration, Video Generation.
Alternativele open-source pentru nus-hpc-ai-lab/videosys includ: msracver/deformable-convnets — Deformable-ConvNets is a computer vision framework and a collection of neural network components designed to implement… ailab-cvc/videocrafter — Videocrafter is a latent diffusion model designed for AI video synthesis. It functions as both a text-to-video and… aim-uofa/gendef. ali-vilab/vace — VACE is a set of software tools and frameworks for reference-guided video generation, diffusion-based editing, and… alibaba/animate-anything. ai-forever/kandinskyvideo.