What the f*ck Python? 😱

🦜🔗 Build context-aware reasoning applications

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

The official Python library for the OpenAI API

A Comprehensive Benchmark for Robust Multi-image Understanding

Benchmarking Multi-Image Understanding in Vision and Language Models

[arXiv 2025] MMSI-Bench: A Benchmark for Multi-Image Spatial Intelligence

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

ArtiMuse: Fine-Grained Image Aesthetics Assessment with Joint Scoring and Expert-Level Understanding（书生 · 妙析多模态美学理解大模型）

A high-throughput and memory-efficient inference and serving engine for LLMs

Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 500+ LLMs (Qwen3, Qwen3-MoE, Llama4, GLM4.5, InternLM3, DeepSeek-R1, ...) and 200+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, Llava, GLM4v, Ph…

In-depth tutorials on LLMs, RAGs and real-world AI agent applications.

LLMs-from-scratch项目中文翻译

Qwen-Image is a powerful image generation foundation model capable of complex text rendering and precise image editing.

Search Airbnb using your AI Agent

An AI agent development platform with all-in-one visual tools, simplifying agent creation, debugging, and deployment like never before. Coze your way to AI Agent creation.

📕 小红书创作者MCP工具包 - 支持与AI客户端集成的内容创作和发布工具

Label Studio is a multi-type data labeling and annotation tool with standardized output format

Open Source DeepWiki: AI-Powered Wiki Generator for GitHub/Gitlab/Bitbucket Repositories. Join the discord: https://discord.gg/gMwThUMeme

Dual-modal YOLO Object Detection Framework

DEYOLO: Dual-Feature-Enhancement YOLO for Cross-Modality Object Detection

Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.

Python tool for converting files and office documents to Markdown.

Create Live Photos from a photo+video pair compatible with Apple Photos

Visualize YOLOv11 classification features with t-SNE. Extract logits or softmax outputs and create customizable scatter plots.

[CVPR 2025] EchoMimicV2: Towards Striking, Simplified, and Semi-Body Human Animation

Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.

Robust Video Matting in PyTorch, TensorFlow, TensorFlow.js, ONNX, CoreML!

AIGCPanel 是一个简单易用的一站式AI数字人系统，支持视频合成、声音合成、声音克隆，简化本地模型管理、一键导入和使用AI模型。