Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

Agent S: an open agentic framework that uses computers like a human

Mobile-Agent: The Powerful GUI Agent Family

[NeurIPS 2025] SpatialLM: Training Large Language Models for Structured Indoor Modeling

[CVPR'25] Official Implementations for Paper - MagicQuill: An Intelligent Interactive Image Editing System

Code and models for ICML 2024 paper, NExT-GPT: Any-to-Any Multimodal Large Language Model

InternLM-XComposer2.5-OmniLive: A Comprehensive Multimodal System for Long-term Streaming Video and Audio Interactions

mPLUG-DocOwl: Modularized Multimodal Large Language Model for Document Understanding

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

🔥 Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos

A family of lightweight multimodal models.

Eagle: Frontier Vision-Language Models with Data-Centric Strategies

[CVPR2024] The code for "Osprey: Pixel Understanding with Visual Instruction Tuning"

OpenEMMA, a permissively licensed open source "reproduction" of Waymo’s EMMA model.

✨✨Woodpecker: Hallucination Correction for Multimodal Large Language Models

[ECCV2024] Grounded Multimodal Large Language Model with Localized Visual Tokenization

[NeurIPS 2025] 4KAgent: Agentic Any Image to 4K Super-Resolution. An intelligent computer vision agent that can magically restore any image to perfect-4K!

NeurIPS 2024 Paper: A Unified Pixel-level Vision LLM for Understanding, Generating, Segmenting, Editing

Custom ComfyUI nodes for Vision Language Models, Large Language Models, Image to Music, Text to Music, Consistent and Random Creative Prompt Generation

Fully Open Framework for Democratized Multimodal Training