Official code for "Style Aligned Image Generation via Shared Attention"Style Aligned Image Generation via Shared Attention Project Page Paper Setup This code was tested with Python 3.11, Pytorch 2.1 and Diffusers 0.16. Examples See style_aligned_sdxl notebook for generating style aligned images using SDXL. See style_aligned_w_controlnet notebook for generating style aligned and depth conditioned images using SDXL with ControlNet-Depth. style_aligned_w_multidiffusion can be used for ge…
Cross-platform iMessage POCpypush pypush is a POC demo of my recent iMessage reverse-engineering. It can currently register as a new device on an Apple ID, set up encryption keys, and send and receive iMessages! pypush is completely platform-independent, and does not require a Mac or other Apple device to use! Installation It's pretty self explanatory: git clone https://github.com/JJTech0130/pypush pip3 install -r requirements.txt python3 ./demo.py Troubleshooting If you have any issues, …
Sequential Modeling Enables Scalable Learning for Large Vision Models Welcome to the official repository for our paper: "Sequential Modeling Enables Scalable Learning for Large Vision Models." Visit our project webpage Abstract: We introduce a novel sequential modeling approach which enables learning a Large Vision Model (LVM) without making use of any linguistic data. To do this, we define a common format, ``visual sentences", in which we can represent raw images and videos as well…
Mamba Mamba: Linear-Time Sequence Modeling with Selective State Spaces Albert Gu*, Tri Dao* Paper: https://arxiv.org/abs/2312.00752 About Mamba is a new state space model architecture showing promising performance on information-dense data such as language modeling, where previous subquadratic models fall short of Transformers. It is based on the line of progress on structured state space models, with an efficient hardware-aware design and implementation in the spirit of FlashAttention. Inst…
MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model Zhongcong Xu · Jianfeng Zhang · Jun Hao Liew · Hanshu Yan · Jia-Wei Liu · Chenxu Zhang · Jiashi Feng · Mike Zheng Shou National University of Singapore | ByteDance …
Fay是一个完整的开源项目，包含Fay控制器及数字人模型，可灵活组合出不同的应用场景：虚拟主播、现场推销货、商品导购、语音助理、远程语音助理、数字人互动、数字人面试官及心理测评、贾维斯、Her。 开源项目，非产品试用！！！English Fay数字人 AI Agent版 带货完整版 助理完整版 “优秀的产品都值得用数字人从新做一遍” 10月，Fay数字人 AI Agent版与官方demo(实验箱)同时开源！ 目前进展 一、APP载入UE数字人： 1、像素流服务搭建及优化： 已经完成，上线时会同步开放代码 2、UE音频流插件： 正在调试修复Bug. 3、改进BS唇型： 进行中. 二、智慧农业箱硬件改造： 完成并已经稳定运行，上线时会公布硬件设计图. 三、IOTM3.0及Raspberry逻辑修改： 完成并已经稳定运行，上线时会同步开放代码. 四、农业LLM： 已经搭建农业知识图谱。 开始测试gpt4的设备控制的推理能力:已经完成硬件控制规则的自动初始化及控制逻辑的自动修正测试. 五、Fay控制器适应新版： 未…
Neovim file explorer: edit your filesystem like a bufferoil.nvim A vim-vinegar like file explorer that lets you edit your filesystem like a normal Neovim buffer. oil.demo.mp4 Requirements Installation Quick start Options Adapters API FAQ Requirements Neovim 0.8+ (optional) nvim-web-devicons for file icons Installation oil.nvim supports all the usual plugin managers lazy.nvim { 'stevearc/oil.nvim', opts = {}, -- Optional dependencies …
Git Query language is a SQL like language to perform queries on .git files with supports of most of SQL features such as grouping, ordering and aggregations functionsGQL - Git Query Language GQL is a query language with a syntax very similar to SQL with a tiny engine to perform queries on .git files instance of database files, the engine executes the query on the fly without the need to create database files or convert .git files into any other format, note that al…