Ultra-light Harness scaffolding for AI agents, a mini version of claude code

Practical marketing resources to get the first 10 / 100 / 1000 users for your SaaS / App / Startup

This is a repo to track the latest autoregressive visual generation papers.

Roblox Foundation Model for 3D Intelligence

A suite of image and video neural tokenizers

TorchCFM: a Conditional Flow Matching library

Reference implementation of Megalodon 7B model

[NeurIPS 2024 Best Paper Award][GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". A…

EDM2 and Autoguidance -- Official PyTorch implementation

Minimal multi-gpu implementation of EDM2: "Analyzing and Improving the Training Dynamics of Diffusion Models"

An Open-source Toolkit for LLM Development

This project aim to reproduce Sora (Open AI T2V model), we wish the open source community contribute to this project.

U-Mamba: Enhancing Long-range Dependency for Biomedical Image Segmentation

🏙 Interactive performance profiling and debugging tool for PyTorch neural networks.

Code for Fast Training of Diffusion Models with Masked Transformers

A collection of resources and papers on Diffusion Models

Official code for VisProg (CVPR 2023 Best Paper!)

A collection of resources on controllable generation with text-to-image diffusion models.

Infinite Photorealistic Worlds using Procedural Generation

MetaSeg: Packaged version of the Segment Anything repository

Framework agnostic sliced/tiled inference + interactive ui + error analysis plots

[CVPR 2023 Highlight] InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions

[ICLR'23 Spotlight🔥] The first successful BERT/MAE-style pretraining on any convolutional network; Pytorch impl. of "Designing BERT for Convolutional Networks: Sparse and Hierarchical Masked Modeling"

Easily turn large sets of image urls to an image dataset. Can download, resize and package 100M urls in 20h on one machine.

Kernl lets you run PyTorch transformer models several times faster on GPU with a single line of code, and is designed to be easily hackable.

Official implementation of Cold-Diffusion for different transformations in pytorch.

Official PyTorch implementation of BlobGAN: Spatially Disentangled Scene Representations

[ECCV 2022] This is the official implementation of BEVFormer, a camera-only framework for autonomous driving perception, e.g., 3D object detection and semantic map segmentation.