Implementation of UltraPixel: Advancing Ultra-High-Resolution Image Synthesis to New Peaks

Vibe check Imagegen models (AuraFlow vs Others)

A collection of original, innovative ideas and algorithms towards Advanced Literate Machinery. This project is maintained by the OCR Team in the Language Technology Lab, Tongyi Lab, Alibaba Group.

Official implementation of Unique3D: High-Quality and Efficient 3D Mesh Generation from a Single Image

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

A high-throughput and memory-efficient inference and serving engine for LLMs

Anole: An Open, Autoregressive and Native Multimodal Models for Interleaved Image-Text Generation

Understand Human Behavior to Align True Needs

The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

Code release for "Segment Anything without Supervision"

A framework for serving and evaluating LLM routers - save LLM costs without compromising quality!

Depth Anything V2. A More Capable Foundation Model for Monocular Depth Estimation

Synthetic Scene Text from 3D Engines

Official implementation of High Fidelity Scene Text Synthesis

Code for generating synthetic text images as described in "Synthetic Data for Text Localisation in Natural Images", Ankush Gupta, Andrea Vedaldi, Andrew Zisserman, CVPR 2016.

Kolors Team

Text-To-Image Generation with Chinese Characters

A unified framework for 3D content generation.

Official repo for the paper "Scaling Synthetic Data Creation with 1,000,000,000 Personas"

Minimalistic large language model 3D-parallelism training

Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.

Manage scalable open LLM inference endpoints in Slurm clusters

Awesome multilingual OCR toolkits based on PaddlePaddle (practical ultra lightweight OCR system, support 80+ languages recognition, provide data annotation and synthesis tools, support training and…

🐚 OpenDevin: Code Less, Make More

[CVPR 2024 Oral] Rethinking Inductive Biases for Surface Normal Estimation

a reimplementation of Holistically-Nested Edge Detection in PyTorch

Python Package reimplementation of Holistically-Nested Edge Detection in PyTorch