Bob 是一款 macOS 平台的翻译和 OCR 软件。

[CVPR 2026] 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

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

[ICML 2026] WorldMirror: Fast and Universal 3D reconstruction model for versatile tasks

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。

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。

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

H1111 --- GUI for Video Models

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

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

HY-Embodied-0.5-X: An Enhanced Embodied Foundation Model for Real-World Agents

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。

An integrated fine-tuning platform for lightweight vlmOCR models

Advanced Image Stitching & Image Padding Node for ComfyUI

Improved ReferenceLatent for ComfyUI — per-image strength, timestep gating, MediaPipe auto-masks, 1-4 image inputs. Works with Flux, Klein, Lumina, Wan, Hunyuan, Qwen-Image.

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.）