StoryDiffusion is a tool for generating consistent images and videos using self-attention mechanisms.
PyTorch implementation of a generative model for high-fidelity audio generation from text prompts.
自动视频生成器，给定主题，自动生成解说视频。
A powerful tool for creating fine-tuning datasets for Large Language Models (LLMs).
Zero-shot voice conversion and singing voice conversion with real-time support and fine-tuning capabilities.
A high-quality PDF to Markdown tool based on large language model visual recognition.
Open-source platform for visualizing and analyzing reasoning processes of Large Language Models (LLMs).
Integrates Cursor AI with Figma for design communication and modification.
The fast, Pythonic way to build MCP servers and clients.
Allow LLMs to control a browser with Browserbase and Stagehand.
Simple, unified interface to multiple Generative AI providers.
智能闲鱼客服机器人系统，提供7×24小时自动化值守与智能对话功能。
