开源项目

ChatMusician

Consistory

OpenCodeInterpreter: Integrating Code Generation with Execution and Refinement

ScreenAgent: A Computer Control Agent Driven by Visual Language Large Model (IJCAI-24) - niuzaisheng/ScreenAgent

A Large Language Model for Zero-Shot Video Generation. VideoPoet demonstrates simple modeling method that can convert any autoregressive language model into a high quality video generator.

Official code implementation of General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model - Ucas-HaoranWei/GOT-OCR2.0

Depth Anything

[ACM CCS'24] SafeEar: Content Privacy-Preserving Audio Deepfake Detection - LetterLiGo/SafeEar

DiffusionGPT: LLM-Driven Text-to-Image Generation System

MetaGPT takes a one line requirement as input and outputs user stories / competitive analysis / requirements / data structures / APIs / documents, etc.

Contribute to lamm-mit/PDF2Audio development by creating an account on GitHub.

美图奇想大模型开放平台是美图公司推出的AI服务平台，将美图秀秀、美颜相机、Wink等经市场验证的图像和视频算法赋能开发者与企业数字化建设，为企业及开发者提供领先的人脸人体、图像识别与处理、生成式AI等技术服务及各行业解决方案。

Make-A-Character

MotionCtrl

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

Ai2, a non-profit research institute founded by Paul Allen, is committed to breakthrough AI to solve the world’s biggest problems.

coze-微信AI机器人一键运行包，下载exe双击直接使用。（该项目已停止维护，使用微信机器人请关注我的新项目（技术更合规，使用更简单） ：https://github.com/ImGoodBai/GoodWeBot） - ImGoodBai/onewebot2

Vary: Scaling up the Vision Vocabulary for Large Vision-Language Models

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

Discover amazing ML apps made by the community

A novel Multimodal Large Language Model (MLLM) architecture, designed to structurally align visual and textual embeddings. - AIDC-AI/Ovis

ActAnywhere: Subject-Aware Video Background Generation

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

Void is an open source Cursor alternative. Full privacy. Fully-featured.

Build your own conversational search engine using less than 500 lines of code with Lepton AI.

DESCRIPTION META TAG

MiniMax 成立于 2021 年 12 月，是领先的通用人工智能科技公司，致力于与用户共创智能。MiniMax 自主研发多模态、万亿参数的 MoE 大模型，并基于大模型推出海螺AI、星野等原生应用。MiniMax API 开放平台提供安全、灵活、可靠的 API 服务，助力企业和开发者快速搭建 AI 应用。

汇聚各领域最先进的机器学习模型，提供模型探索体验、推理、训练、部署和应用的一站式服务。

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

Outfit Anyone