Phidias: A Generative Model for Creating 3D Content from Text, Image, and 3D Conditions with Reference-Augmented Diffusion

3DTopia-XL: High-Quality 3D PBR Asset Generation via Primitive Diffusion

Python package to corrupt arbitrary images.

High-resolution models for human tasks.

Goliath Dataset and Official PyTorch Implementation of RelightableHands, Relightable Gaussian Codec Avatars, and Driving-Signal Aware Full-Body Avatars.

Controllable video and image Generation, SVD, Animate Anyone, ControlNet, ControlNeXt, LoRA

The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑‍🔬

🥕A curated collection of Virtual Reality Resources.

Official inference repo for FLUX.1 models

The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use th…

Understand Human Behavior to Align True Needs

Papers, datasets, and resources related to 2D cartoon video research. Contributions welcome.

TextGrad: Automatic ''Differentiation'' via Text -- using large language models to backpropagate textual gradients.

OpenVLA: An open-source vision-language-action model for robotic manipulation.

A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)

Some simple Blender scripts for rendering paper figures

Focus on prompting and generating

MiniCPM-V 2.6: A GPT-4V Level MLLM for Single Image, Multi Image and Video on Your Phone

A generative speech model for daily dialogue.

A Python framework for high performance GPU simulation and graphics

🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning

[SIGGRAPH 2024] ThemeStation: Generating Theme-Aware 3D Assets from Few Exemplars

Official implementations for paper: Dynamic Typography: Bringing Text to Life via Video Diffusion Prior

[NeurIPS 2024] GaussianCube: A Structured and Explicit Radiance Representation for 3D Generative Modeling

KErnel OPerationS, on CPUs and GPUs, with autodiff and without memory overflows

[CVPR 2024] Official PyTorch implementation of SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction and High-Quality Mesh Rendering

An open-source impl. of Large Reconstruction Models

An Open-source Toolkit for LLM Development

The simplest, fastest repository for training/finetuning medium-sized GPTs.

[ECCV 2024 Oral] LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation.