Portfolio Tracker: Track your investments and asset allocation

Cosmos-Transfer1 is a world-to-world transfer model designed to bridge the perceptual divide between simulated and real-world environments.

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

Survey Paper of foundation models for robotics

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

This repo contains the code for our paper An Image is Worth 32 Tokens for Reconstruction and Generation

OmniTokenizer: one model and one weight for image-video joint tokenization.

A simple and efficient Mamba implementation in PyTorch and MLX.

Open source implementation and models of One-step Diffusion with Distribution Matching Distillation

PixArt-Σ: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation

Open-sourced codes for MiniGPT-4 and MiniGPT-v2 (https://minigpt-4.github.io, https://minigpt-v2.github.io/)

[CVPR 2022--Oral] Restormer: Efficient Transformer for High-Resolution Image Restoration. SOTA for motion deblurring, image deraining, denoising (Gaussian/real data), and defocus deblurring.

MiniSora: A community aims to explore the implementation path and future development direction of Sora.

Open-Sora: Democratizing Efficient Video Production for All

Official implementation for Mini-Gemini

AniPortrait: Audio-Driven Synthesis of Photorealistic Portrait Animation

Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model

Official DeiT repository

Let us control diffusion models!

Simple, minimal implementation of the Mamba SSM in one pytorch file. More efficient than using for loops, but probably less efficient than using associative scans

Code for "Cameras as Rays"

A minimal, but effective implementation of CLIP (Contrastive Language-Image Pretraining) in PyTorch

Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"

3D Gaussian Splatting, reimagined: Unleashing unmatched speed with C++ and CUDA from the ground up!

[ICLR 2023 Oral] Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model

Posterior Sampling using Latent Diffusion

A mini-library for training consistency models.