[NeurIPS 2024 Oral][GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". An *ultra-sim…

每个人都能用的数字人

Document to Markdown OCR library with Llama 3.2 vision

[NeurIPS 2024🔥] DreamClear: High-Capacity Real-World Image Restoration with Privacy-Safe Dataset Curation

Official implementation of the paper "TANGO: Co-Speech Gesture Video Reenactment with Hierarchical Audio-Motion Embedding and Diffusion Interpolation"

A suite of image and video neural tokenizers

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

This repository gives the official implementation of Realistic and Efficient Face Swapping: A Unified Approach with Diffusion Models (WACV 2025)

[IJCAI'24] Beyond Alignment: Blind Video Face Restoration via Parsing-Guided Temporal-Coherent Transformer

The official CLIP training codebase of Inf-CL: "Breaking the Memory Barrier: Near Infinite Batch Size Scaling for Contrastive Loss". A super memory-efficiency CLIP training scheme.

Janus-Series: Unified Multimodal Understanding and Generation Models

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

基于AI的图片/视频硬字幕去除、文本水印去除，无损分辨率生成去字幕、去水印后的图片/视频文件。无需申请第三方API，本地实现。AI-based tool for removing hard-coded subtitles and text-like watermarks from videos or Pictures.

NIST_FRVT Top 1🏆 Face Recognition, Liveness Detection(Face Anti-Spoof), Face Attribute Analysis Linux Server SDK Demo ☑️ Face Recognition ☑️ Face Matching ☑️ Face Liveness Detection ☑️ Face Identif…

一个超轻量级、可以在移动端实时运行的数字人模型

This is a HeadSwap project not only face

本项目旨在分享大模型相关技术原理以及实战经验（大模型工程化、大模型应用落地）

Structured Text Generation

[3DV'25] 3D Reconstruction with Spatial Memory

EchoMimic: Lifelike Audio-Driven Portrait Animations through Editable Landmark Conditioning

OmniGen: Unified Image Generation. https://arxiv.org/pdf/2409.11340

研报，行业研报，研究报告，每天定时更新，可关注公众号查看研报

1000+ DevOps Bash Scripts - AWS, GCP, Kubernetes, Docker, CI/CD, APIs, SQL, PostgreSQL, MySQL, Hive, Impala, Kafka, Hadoop, Jenkins, GitHub, GitLab, BitBucket, Azure DevOps, TeamCity, Spotify, MP3,…

Hallo: Hierarchical Audio-Driven Visual Synthesis for Portrait Image Animation

This React component is used to render Markdown into a beautiful poster image, with support for copying as an image. Md to Poster/Image/Quote/Card/Instagram/Twitter/Facebook...

Real time interactive streaming digital human

Official code implementation of General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model

⚡️HivisionIDPhotos: a lightweight and efficient AI ID photos tools. 一个轻量级的AI证件照制作算法。

Qwen2-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.