Award-Winning Open Source Video Editing Software
Blender addons to make the bridge between Blender and geographic data
3D reconstruction software
State-of-the-art 2D and 3D Face Analysis Project
Text-to-3D & Image-to-3D & Mesh Exportation with NeRF + Diffusion
Implementation of Make-A-Video, new SOTA text to video generator
2D and 3D Face alignment library build using pytorch
Build cross-modal and multimodal applications on the cloud
A walk along memory lane
Open Source Differentiable Computer Vision Library
Geometric deep learning extension library for PyTorch
Implementation of Video Diffusion Models
Blender pipeline for photorealistic training image generation
State-of-the-art diffusion models for image and audio generation
The data structure for multimodal data
A python module for scientific analysis of 3D data
Implementation of a U-net complete with efficient attention
Visual localization made easy with hloc
AI Upscaler for Blender using Real-ESRGAN
A library to model multivariate data using copulas
CLIP + FFT/DWT/RGB = text to image/video
Implementation of DeepLabCut
Toolkit for developing and comparing reinforcement learning algorithms
Notebooks, models and techniques for the generation of AI Art
Based on the Disco Diffusion, version of the AI art creation software