Starred repositories
Qwen2.5-Omni is an end-to-end multimodal model by Qwen team at Alibaba Cloud, capable of understanding text, audio, vision, video, and performing real-time speech generation.
SD-Trainer. LoRA & Dreambooth training scripts & GUI use kohya-ss's trainer, for diffusion model.
Danbooru / NovelAI 标签超市
Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.
1 min voice data can also be used to train a good TTS model! (few shot voice cloning)
zero-shot voice conversion & singing voice conversion, with real-time support
🍦 Speech-AI-Forge is a project developed around TTS generation model, implementing an API Server and a Gradio-based WebUI.
🍒 Cherry Studio is a desktop client that supports for multiple LLM providers.
Use your locally running AI models to assist you in your web browsing
Get up and running with Llama 3.3, DeepSeek-R1, Phi-4, Gemma 3, Mistral Small 3.1 and other large language models.
📚 Freely available programming books
通过分析AssetBundle自动计算并将多张立绘和差分表情组合成一个完整的立绘图片
Azur Lane bot (CN/EN/JP/TW) 碧蓝航线脚本 | 无缝委托科研，全自动大世界
aria2 is a lightweight multi-protocol & multi-source, cross platform download utility operated in command-line. It supports HTTP/HTTPS, FTP, SFTP, BitTorrent and Metalink.
Desktop environment in the browser
A feature-rich command-line audio/video downloader
哔哩哔哩-API收集整理【不断更新中....】
Read-only mirror of Wireshark's Git repository at https://gitlab.com/wireshark/wireshark.
A tool for download asmr media from asmr.one(Thanks for the asmr.one)
Stable Diffusion web UI
Bluetooth Forward and Future Secrecy Attacks and Defenses (BLUFFS) [CVE 2023-24023]
Tools and instructions for importing custom models into a certain anime game
AssetStudio is a tool for exploring, extracting and exporting assets and assetbundles.