Qwen-Image-Layered: Layered Decomposition for Inherent Editablity

TurboDiffusion: 100–200× Acceleration for Video Diffusion Models

微舆：人人可用的多Agent舆情分析助手，打破信息茧房，还原舆情原貌，预测未来走向，辅助决策！从0实现，不依赖任何框架。

A cross-platform desktop All-in-One assistant tool for Claude Code, Codex & Gemini CLI.

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

[NeurIPS 2025 Spotlight] LeMiCa: Lexicographic Minimax Path Caching for Efficient Diffusion-Based Video Generation

TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. Tensor…

Transformer related optimization, including BERT, GPT

OpenVINO™ is an open source toolkit for optimizing and deploying AI inference

所有小初高、大学PDF教材。

🤗A PyTorch-native and Flexible Inference Engine with Hybrid Cache Acceleration and Parallelism for DiTs.

Command-line program to download image galleries and collections from several image hosting sites

Official inference repo for FLUX.2 models

Light Video Generation Inference Framework

Nano Banana(nanobanana),GPT-5(GPT5),GPT-4o(GPT4o) Image Prompts，Nanobanana Prompts，nanobanana提示词

Nano Banana(nanobanana),GPT-5(GPT5),GPT-4o(GPT4o) Image Prompts，Nanobanana Prompts，nanobanana提示词

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

"AI-Trader: Can AI Beat the Market?" Live Trading Bench: https://ai4trade.ai Tech Report Link: https://arxiv.org/abs/2512.10971

The best ChatGPT that $100 can buy.

[ECCV2024] IDM-VTON : Improving Diffusion Models for Authentic Virtual Try-on in the Wild

主要记录大语言大模型（LLMs） 算法（应用）工程师相关的知识及面试题

Convert PDF to markdown + JSON quickly with high accuracy

My learning notes for ML SYS.

A python tool that uses GPT-4, FFmpeg, and OpenCV to automatically analyze videos, extract the most interesting sections, and crop them for an improved viewing experience.

(CVPR 2024) Bridging the Gap Between End-to-End and Two-Step Text Spotting.

An Open-Sourced LLM-empowered Foundation TTS System