Stars
A fast asyncio MySQL/MariaDB driver with replication protocol support
[CVPR 2025] MMAudio: Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis
An extremely fast Python type checker and language server, written in Rust.
FantasyTalking: Realistic Talking Portrait Generation via Coherent Motion Synthesis
Phantom: Subject-Consistent Video Generation via Cross-Modal Alignment
极快的B站直播录制、自动切片、自动渲染弹幕以及字幕并投稿至B站，综合多种模态模型，兼容超低配置机器。Extremely fast live recording, automatic slicing, rendering, uploading and Integrating MLLMs. Compatible with low configurations machines.
A simple, easy to use PowerShell script to remove pre-installed apps from Windows, disable telemetry, remove Bing from Windows search as well as perform various other changes to declutter and impro…
A SOTA open-source image editing model, which aims to provide comparable performance against the closed-source models like GPT-4o and Gemini 2 Flash.
✨ 易上手的多平台 LLM 聊天机器人及开发框架 ✨ 平台支持 QQ、QQ频道、Telegram、微信、企微、飞书 | MCP 服务器、OpenAI、DeepSeek、Gemini、硅基流动、月之暗面、Ollama、OneAPI、Dify 等。附带 WebUI。
Official implementation in ComfyUI of CVPR 2025 paper "HyperLoRA: Parameter-Efficient Adaptive Generation for Portrait Synthesis"
SkyReels-V2: Infinite-length Film Generative model
PosterMaker [CVPR 2025] https://poster-maker.github.io/
QQ官方机器人 Java/JVM/kotlin SDK QQ bot sdk qq机器人sdk
🔥 Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos
StoryMaker: Towards consistent characters in text-to-image generation
Skywork-R1V2:Multimodal Hybrid Reinforcement Learning for Reasoning (Best open-source multimodal reasoning model)
Easily train a good VC model with voice data <= 10 mins!