yumianhuli2's repositories
AniPortrait
AniPortrait: Audio-Driven Synthesis of Photorealistic Portrait Animation
ComfyUI-BRIA_AI-RMBG
Unofficial implementation of BRIA RMBG Model for ComfyUI
EmoTalk_release
This is the official source for our ICCV 2023 paper "EmoTalk: Speech-Driven Emotional Disentanglement for 3D Face Animation"
Emote-hack
using chatgpt (now Claude 3) to reverse engineer code from Emote white paper. WIP
F8Framework
F8 Framework是一个优雅，轻量，符合直觉的基于Unity引擎的Game Framework，组件围绕F8一键启动，框架整体遵循以极少的使用成本开发游戏。
FlashAvatar-code
[CVPR 2024] The official repo for FlashAvatar
GauHuman
Code for our CVPR'2024 paper "GauHuman: Articulated Gaussian Splatting from Monocular Human Videos"
HeyGenClone
A simple and open-source analogue of the HeyGen system
LLMUnity
Create characters in Unity with LLMs!
manga-image-translator
Translate manga/image 一键翻译各类图片内文字 https://cotrans.touhou.ai/
MiniGPT4-video
Official code for MiniGPT4-video
miniPaint
online image editor
mlc-llm
Enable everyone to develop, optimize and deploy AI models natively on everyone's devices.
mPLUG-DocOwl
mPLUG-DocOwl: Modularized Multimodal Large Language Model for Document Understanding
pyannote-video
Face detection, tracking and clustering in videos
qucsdk
Qt编写的自定义控件插件的sdk集合，包括了各个操作系统的动态库文件以及控件的头文件和sdk使用demo。心中有坐标，万物皆painter，欢迎各位咨询、购买、定制控件，QQ：517216493 微信：feiyangqingyun 推荐加微信。公众号：Qt实战/Qt入门和进阶/Qt教程
RapidVideOCR
Extract video hard subtitles and automatically generate corresponding srt files.
Scrapegraph-ai
Python scraper based on AI
sd-dynamic-thresholding
Dynamic Thresholding (CFG Scale Fix) for Stable Diffusion (StableSwarmUI, ComfyUI, and Auto WebUI)
sd-webui-photopea-embed
A simple Stable Diffusion WebUI extension that adds a Photopea tab and integration.
sort
Simple, online, and realtime tracking of multiple objects in a video sequence.
StableTTS
Next-generation TTS model using flow-matching and DiT, inspired by Stable Diffusion 3
SyncTalk
[CVPR 2024] This is the official source for our paper "SyncTalk: The Devil is in the Synchronization for Talking Head Synthesis"
textsToVideo
使用stable diffusion api生成图片,结合python的一系列对媒体操作的库,生成十分简单的小说推文.
Track-Anything
Track-Anything is a flexible and interactive tool for video object tracking and segmentation, based on Segment Anything, XMem, and E2FGVI.
UMA
Unity Multipurpose Avatar
WatermarkRemover
批量去除视频中位置固定的水印