Bob 是一款 macOS 平台的翻译和 OCR 软件。

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

HY-World 1.5: A Systematic Framework for Interactive World Modeling with Real-Time Latency and Geometric Consistency

Fast and Universal 3D reconstruction model for versatile tasks

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

A Collection of Google Colab Notebooks for various projects

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。

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。

Implementation of GradLoc from the Tencent Hunyuan blog "Stabilizing RLVR via Token-level Gradient Diagnosis and Layerwise Clipping".

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。

Nodes to run Hunyuan Image 3 locally with BF16 and NF4 quantized options in Comfyui

Advanced Image Stitching & Image Padding Node for ComfyUI

An integrated fine-tuning platform for lightweight vlmOCR models

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

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

通过Cookie信息快速访问腾讯混元大模型

A Gradio-based demo application for comparing state-of-the-art OCR models: DeepSeek-OCR, Dots.OCR, HunyuanOCR, and Nanonets-OCR2-3B.

Large Language Models Python API

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.

🗿 hunyuan3d based 3d model maker on st cloud

VSCode extension to generate Git commit messages using AI (Claude/OpenAI/Azure/混元)

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

🌐 Local AI-powered translator with GUI using Hunyuan-MT models. Private, offline translation for 50+ languages with dual-stage processing (base + Chimera refinement)

定制你的专属ai-FLXTeam-FELIX

AI-powered prompt generator for video (Wan2.1/2.2, Hunyuan), image (SD, FLUX, Midjourney, DALL-E), and creative content. Local LLMs with GPU auto-detection.

AI Text-to-Video Generation Example using Hunyuan Model

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