Open-source unified multimodal model

A SOTA open-source image editing model, which aims to provide comparable performance against the closed-source models like GPT-4o and Gemini 2 Flash.

Lets make video diffusion practical!

Efficient optimizers

A quick intro to IPSec on the kernel side with STUN and UDP hole punching

CogView4, CogView3-Plus and CogView3(ECCV 2024)

Cambrian-1 is a family of multimodal LLMs with a vision-centric design.

Repository for Meta Chameleon, a mixed-modal early-fusion foundation model from FAIR.

Your image is almost there!

GPT4V-level open-source multi-modal model based on Llama3-8B

cuDF - GPU DataFrame Library

cuML - RAPIDS Machine Learning Library

[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…

Grok open release

DeepSeek-VL: Towards Real-World Vision-Language Understanding

适配轻小说/Galgame的日中翻译大模型

Hackable and optimized Transformers building blocks, supporting a composable construction.

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

a state-of-the-art-level open visual language model | 多模态预训练模型

The JoyTag Image Tagging Model

Blazing fast concurrent HashMap for Rust.

A convenient and user-friendly anime-style image data processing library that integrates various advanced anime-style image processing models

A fast & densely stored hashmap and hashset based on robin-hood backward shift deletion

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

Xwin-LM: Powerful, Stable, and Reproducible LLM Alignment

Focus on prompting and generating

set prompt to divided region