Layer Diffuse custom nodes

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.

real time face swap and one-click video deepfake with only a single image

SD.Next: All-in-one WebUI for AI generative image and video creation

A reactive notebook for Python — run reproducible experiments, query with SQL, execute as a script, deploy as an app, and version with git. Stored as pure Python. All in a modern, AI-native editor.

Streamlined interface for generating images with AI in Krita. Inpaint and outpaint with optional text prompt, no tweaking required.

Effortless data labeling with AI support from Segment Anything and other awesome models.

SAM with text prompt

Improved AnimateDiff for ComfyUI and Advanced Sampling Support

Stable Diffusion built-in to Blender

Openpose editor for ControlNet. Full hand/face support.

A visual no-code/code-free web crawler/spider易采集：一个可视化浏览器自动化测试/数据采集/爬虫软件，可以无代码图形化的设计和执行爬虫任务。别名：ServiceWrapper面向Web应用的智能化服务封装系统。

Get Deinked!!

Remove unwanted objects and restore images without prompts, powered by ControlNet.

one-click face swap

roop extension for StableDiffusion web-ui

A synthetic data generator for text recognition

Text To Video Synthesis Colab

set prompt to divided region

This script allows to automate video stylization task using StableDiffusion and ControlNet.

Implementation of DragGAN: Interactive Point-based Manipulation on the Generative Image Manifold

リアルタイムボイスチェンジャー Realtime Voice Changer

Personalization for Stable Diffusion via Aesthetic Gradients 🎨

The definitive Web UI for local AI, with powerful features and easy setup.

AudioLDM: Generate speech, sound effects, music and beyond, with text.

BoxMOT: Pluggable SOTA multi-object tracking modules modules for segmentation, object detection and pose estimation models