Discover The Top AI hackers & Projects

A model-driven approach to building AI agents in just a few lines of code.

基于 Google Gemini AI 的全功能图像处理应用

Easiest way to give context to LLMs; Attachments has the ambition to be the general funnel for any files to be transformed into images+text for large language models context by only adding 2 lines to your python code.

Take your LLM to the optometrist.

Llama.cpp runner/swapper and proxy that emulates LMStudio / Ollama backends

a comprehensive diffusion-based code refinement model

An implementation of GRPO for Unsloth's VLMs training

A Commitizen plugin that leverages OpenAI's GPT-4o to automatically generate clear, concise, and conventional commit messages based on your staged git changes.

Adapting VLMs to Bench2Drive.

ComfyUI-AniSora is now available in ComfyUI, Index-AniSora is the most powerful open-source animated video generation model. It enables one-click creation of video shots across diverse anime styles including series episodes, Chinese original animations, manga adaptations, VTuber content, anime PVs, mad-style parodies(鬼畜动画), and more!

A comprehensive list of awesome research, resources, and tools for leveraging LLMs, VLMs, and VLA models in autonomous driving decision-making and motion planning.

ComfyUI custom node powered by LLaVA VLM for advanced image captioning with customizable styles and memory-efficient inference.

A simplified mlx implementation of the original stable diffusion 1.5 algorithm featuring fine-tuned weight loading and lora loading for Text and Image generation

This repo has specific easy steps for you to be able to train your Llama AI Model offline

DarkGPT Lite is a specialized CLI tool providing unrestricted conversations with AI for cybersecurity research purposes

🔥 The first survey on bridging VLMs and synthetic data, for which I completed the entire process of reading 125 papers and writing the research paper in just 10 days.

A simple, intuitive, Roblox admin script.

Convert SD1.5 Textual Inversion to SDXL

An efficient sampling method for long-CoT LLM with fractured CoT.

Discord chat bot using AI models from Nano-GPT.com. Supports popular AI models such as ChatGPT, Llama, Claude, Gemini, Grok, and many more!

ChatGPT 中文版：国内直连教程（支持GPT-4、4o、o1、o3 和 DeepSeek R1，无需翻墙）【5月持续更新】

개발 및 GPT 프롬프팅을 위한 도구들 모음

我们制作了一个6人版AI狼人杀，目前是用的本地模型（如deepseek-r1:7b），用api会有更佳体验。

基于Qwen Agent框架，融合JAKA机械臂、视觉检测、语音识别与合成、MCP数据库的多模态大模型

VLM specially crafted for geospatial reasoning tasks

Track brand visibility across different LLMs

✨ Ho-Oh: Give your Google Gemini chats a personal touch with custom user avatars

OllamaFreeAPI: Free Distributed API for Ollama LLMs Public gateway to our managed Ollama servers with: - Zero-configuration access to 50+ models - Auto load-balanced across global nodes - Free tier with no API keys required - Built on ollama-python

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction

Habitad for humanity LMS from from zero.

Basic LMS

initializing LLMs using the llama engine and gguf images (𝔦𝔫 𝔭𝔯𝔬𝔤𝔯𝔢𝔰𝔰)

Implement the AI podcast feature of NotebookLM to generate Chinese podcasts in a clear and concise manner.

Full documentation for setup Azure_API_OLLAMA_DeepSeek-R1

ChatGPT 中文版：免费国内直连指南（支持GPT-4.1、4o、o1、o3 和 DeepSeek R1、Claude 3.7 Sonnet，无需翻墙）【5月最新更新】

ChatGPT 中文版：国内免费直连指南（支持GPT-4.1、GPT-4o画图，无需翻墙）【5月更新】

Minimal chat interface, All tasks can be done from the keyboard