[ICLR2024] Official repo for paper "PnP Inversion: Boosting Diffusion-based Editing with 3 Lines of Code"

Implementation of Parti, Google's pure attention-based text-to-image neural network, in Pytorch

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

PyTorch implementation of RCG https://arxiv.org/abs/2312.03701

[CVPR 2024] Official implementation, Inversion-Free Image Editing with Natural Language"

LAVIS - A One-stop Library for Language-Vision Intelligence

LLaVA-Plus: Large Language and Vision Assistants that Plug and Learn to Use Skills

VL-GPT: A Generative Pre-trained Transformer for Vision and Language Understanding and Generation

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

Gradio demo used in our Osprey:Pixel Understanding with Visual Instruction Tuning.

Official implementation code of the paper <AnyText: Multilingual Visual Text Generation And Editing>

[CVPR 2024 Highlight] Official repo: SCEdit: Efficient and Controllable Image Diffusion Generation via Skip Connection Editing

The official Pytorch Implementation for ElasticDiffusion: Training-free Arbitrary Size Image Generation through Global-Local Content Separation (CVPR 2024)

Qwen2.5-Omni is an end-to-end multimodal model by Qwen team at Alibaba Cloud, capable of understanding text, audio, vision, video, and performing real-time speech generation.