Bob 是一款 macOS 平台的翻译和 OCR 软件。

一款JavaSDK用于快速接入AI大模型应用，整合多平台大模型，如OpenAi、智谱Zhipu(ChatGLM)、深度求索DeepSeek、月之暗面Moonshot(Kimi)、腾讯混元Hunyuan、零一万物(01)等等，提供统一的输入输出(对齐OpenAi)消除差异化，优化函数调用(Tool Call)，优化RAG调用、支持向量数据库(Pinecone)、内置联网增强，并且支持JDK1.8，为用户提供快速整合AI的能力。

PromptEnhancer is a prompt-rewriting tool, refining prompts into clearer, structured versions for better image generation.

YuanBao-Free-API 是一个允许您通过 OpenAI 兼容接口访问腾讯元宝的服务。

Model compression toolkit engineered for enhanced usability, comprehensiveness, and efficiency.

H1111 --- GUI for Video Models

AI Hub 是一个为了接入包括ChatGPT、Baichuan、Zhipu、混元、MiniMax、Moonshot等多种大型语言模型而设计的服务。它旨在积累和管理各种有效的模型调用提示（prompt），并对这些大型语言模型进行持续的测试和评估。

Text Encoders finally matter 🤖🎥 - scale CLIP & LLM influence! + a Nerdy Transformer Shuffle node

集成 百度文心一言，阿里通义千问，腾讯混元助手 和 讯飞星火认知 等大模型的 API，并且适配 OpenAI 的输入与输出。

Advanced Image Stitching Node for ComfyUI

a website for accessing many models through api（deepseek、Qwen、Hunyuan etc.）

simple diffusers based implementation of Hunyuan-DiT, in Forge webUI for Stable Diffusion. Works with 8GB VRAM.

通过Cookie信息快速访问腾讯混元大模型

Large Language Models Python API

AKasha Whisper提供了一个统一的、用户友好的 API，用于集成多个 AI 模型并与之交互

本项目旨在构造一个手机、平台等端侧设备本地运行多模态大模型能力的生态，包括运行环境、端侧大模型和前后端APP等，并追踪当前端侧大模型开源模型。This project aims to build an ecosystem for running multimodal large models locally on devices such as mobile phones and tablets. It encompasses the runtime environment, edge-device large models, and front-end and back-end applications.

SkyReels V1: The first and most advanced open-source human-centric video foundation model. Adapted to run on Google Colab.

Python code to help creation of datasets for Wan2.1. Should be compatible with all diffusion-pipe datasets.

Chat to different AI webpage in one single page|一个页面同时与多个AI通信，支持混元、千问、ChatGLM。

Open-source Hunyuan-0.5B offers efficient instruction-following with 0.5B parameters for multilingual tasks. 🐙 Accessible via Hugging Face, ModelScope, and AngelSlim for researchers and developers, with concise docs.