Convert free-form academic references into LaTeX BibTeX entries via title-based retrieval with DBLP, Crossref, and Google Scholar fallback, plus a lightweight local web UI.

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.

zero-shot voice conversion & singing voice conversion, with real-time support

Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything

PyTorch implementation of 'Cover-separable Fixed Neural Network Steganography via Deep Generative Models' （ACM MM 2024）

邱锡鹏《神经网络与深度学习》（蒲公英书）理论书 v2 与通识版

PyTorch implementation of “Purified and Unified Steganographic Networks” (CVPR 2024)

PyTorch implementation of the classical image steganalysis networks, compatible with both grayscale and color images, and supporting multiple image sizes.

[CSUR] A Survey on Video Diffusion Models

Official repo for VGen: a holistic video generation ecosystem for video generation building on diffusion models

PyTorch implementation of "Steganography of Steganographic Networks" (AAAI 2023)

PyTorch implementation of image hiding networks

This code converts any decimal number(integer or float) in to binary according to IEEE754 Single precision 32-bit format

This project contains some interesting image processing algorithms that were wrote in python and c++ from scratch.