Lists (1)
Stars
一个 聚合的网盘搜索工具。它可以聚合多个优质资源站和公开频道,一次搜索即可覆盖阿里云盘、夸克、百度网盘、115、迅雷等热门网盘资源。它提供智能排序、分类型展示、极速部署等功能,并且是免费开源、零广告、轻量部署的。
3FUI 是 ffmpeg 在 Windows 上的轻度专业交互外壳，收录大量参数，界面美观，交互友好。此项目面向国内使用环境，让普通人也能够轻松压制视频和转换格式。
TurboDiffusion: 100–200× Acceleration for Video Diffusion Models
Web app to extract metadata from .torrent file, magnet URI or info hash.
A high-performance Go API service that retrieves torrent metadata from magnet links using DHT/peer networks, implements intelligent caching, and participates in the BitTorrent ecosystem as a good p…
A dataset for Audio-Visual Sound Event Detection in Movies
A simple vscode extension download website.
A watermark removal tool specifically designed for Sora2. 一个用于Sora2去水印的工具
The fastest and highest-quality deep learning powered Sora2 watermark cleaner.
[ICCV'25 Best Paper Finalist] ReCamMaster: Camera-Controlled Generative Rendering from A Single Video
LongLive: Real-time Interactive Long Video Generation
[ICCV 2025 Highlight] OminiControl: Minimal and Universal Control for Diffusion Transformer
Python binding to Skia Graphics Library
geomagical / lama-with-refiner
Forked from advimman/lama🦙 LaMa Image Inpainting, Resolution-robust Large Mask Inpainting with Fourier Convolutions, WACV 2022
Our implementation of Text Style Brush architecture.
Code for generating synthetic text images as described in "Synthetic Data for Text Localisation in Natural Images", Ankush Gupta, Andrea Vedaldi, Andrew Zisserman, CVPR 2016.
Image inpainting tool powered by SOTA AI Model. Remove any unwanted object, defect, people from your pictures or erase and replace(powered by stable diffusion) any thing on your pictures.
Translate manga/image 一键翻译各类图片内文字 https://cotrans.touhou.ai/ (no longer working)
Qwen-Image is a powerful image generation foundation model capable of complex text rendering and precise image editing.
SSA + FastSAM/Semantic Fast Segment Anything , or Fast Semantic Segment Anything
[IEEE TPAMI] Hi-SAM: Marrying Segment Anything Model for Hierarchical Text Segmentation
AI-Powered Watermark Remover using Florence-2 and LaMA: Remove watermarks from images and videos, including AI-generated content from Sora, Runway, and others. Features a modern PyWebview GUI.