拼豆底稿生成器 (Perler Beads Generator)

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

Image inpainting tool powered by SOTA AI Model. Remove any unwanted object, defect, people from your pictures or erase and replace(powered by stable diffusion) any thing on your pictures.

📹 A more flexible framework that can generate videos at any resolution and creates videos from images.

SCAIL: Towards Studio-Grade Character Animation via In-Context Learning of 3D-Consistent Pose Representations (CVPR 2026 Findings)

基于AI的图片/视频硬字幕去除、文本水印去除，无损分辨率生成去字幕、去水印后的图片/视频文件。无需申请第三方API，本地实现。AI-based tool for removing hard-coded subtitles and text-like watermarks from videos or Pictures.

批量去除视频中位置固定的水印

Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.

AIAssistC是一个AI游戏助手，使用OpenCv、DNN、ssd_mobilenet/efficientdet、MFC等技术，截取游戏屏幕进行对象识别，使用虚拟鼠标键盘hook实现自动瞄准/自动开枪等功能，提升玩家的游戏体验。

Directly Aligning the Full Diffusion Trajectory with Fine-Grained Human Preference

StableZero123 is a custom-node implementation for Comfyui that uses the Zero123plus model to generate 3D views using just one image.

[ICLR 2024 Spotlight] SyncDreamer: Generating Multiview-consistent Images from a Single-view Image

Code repository for Zero123++: a Single Image to Consistent Multi-view Diffusion Base Model.

This is the repo for our new project Highly Accurate Dichotomous Image Segmentation

high-accuracy segmentation for anime character

Qwen-Image-Lightning: Speed up Qwen-Image model with distillation

Collection of AI-related utilities. Welcome to submit pull requests /收藏AI相关的实用工具，欢迎提交pull requests

Qwen-Image text to image lora trainer

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

OpenMMLab Detection Toolbox and Benchmark

🎥 Python and OpenCV-based scene cut/transition detection program & library.

This repository contains script to divide a video into key frames.

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

Tiled Diffusion and VAE optimize, licensed under CC BY-NC-SA 4.0

Convolutional Neural Networks to predict the aesthetic and technical quality of images.