#
chr2117216003
Follow
Starred repositories
An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
SALMONN: Speech Audio Language Music Open Neural Network
Diffusers wrapper to run Kwai-Kolors model
Lifelike Audio-Driven Portrait Animations through Editable Landmark Conditioning
Multilingual Voice Understanding Model
Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.
Understand Human Behavior to Align True Needs
"Effective Whole-body Pose Estimation with Two-stages Distillation" (ICCV 2023, CV4Metaverse Workshop)
Project page of replacing the human motion in the video with a virtual 3D human
🤢 LipSick: Fast, High Quality, Low Resource Lipsync Tool 🤮
Controllable video and image Generation, SVD, Animate Anyone, ControlNet, LoRA
LivePortrait: Efficient Portrait Animation with Stitching and Retargeting Control
Scripts for fine-tuning Llama2 via SFT and DPO.
Reference implementation for DPO (Direct Preference Optimization)
[NeurIPS 2022 Spotlight] VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training
Code for CVPR 2022 paper "Scene Consistency Representation Learning for Video Scene Segmentation"
Codebase for CVPR2020 A Local-to-Global Approach to Multi-modal Movie Scene Segmentation
Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities
ImageBind One Embedding Space to Bind Them All
🎥 Python and OpenCV-based scene cut/transition detection program & library.
[ICML 2024] MagicPose(also known as MagicDance): Realistic Human Poses and Facial Expressions Retargeting with Identity-aware Diffusion
FreeAskInternet is a completely free, PRIVATE and LOCALLY running search aggregator & answer generate using MULTI LLMs, without GPU needed. The user can ask a question and the system will make a mu…
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.
VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs