thrilliance

DiffBody

ControlNet

Let us control diffusion models!

stable-diffusion-webui-ux

Stable Diffusion web UI UX

SingleFileDB

A single file implementation of key-value database for Python 3.

ControlNet-v1-1-nightly

Nightly release of ControlNet 1.1

stable-diffusion-webui-forge

LoRA_Easy_Training_Scripts

A UI made in Pyside6 to make training LoRA/LoCon and other LoRA type models in sd-scripts easy

Arturia_Beatstep_for_Video_Editor

I'm not, by any means, a programmer, I'm a video editor and I saw this one video on youtube where an Arturia Beatstep was used for video editing and color grading and decided to give it a shot programming some scripts to control Adobe Premiere Pro and Davinci Resolve.

video-audio-swap

Swap the audio of a music video with another track using beat detection

MusicVideoSync

Python app to sync Video Files to the beat of a song

BabyFace

Baby monitoring device that uses MIT's "Eulerian Video Magnification" to detect heart beat based on facial colour changes.

cock-heroine

A tool for recording and editing beat patterns for cock hero videos

Heart-beat-frequency-extracted-from-videos-

Based on extracting heart beat using Eulerian Video Magnification technique for amplifying temporal changes in video

fastdup

fastdup is a powerful free tool designed to rapidly extract valuable insights from your image & video datasets. Assisting you to increase your dataset images & labels quality and reduce your data operations costs at an unparalleled scale.

imagehash

Fast image similarity search with hash tables (Golang). Version 1

ultralytics

NEW - YOLOv8 🚀 in PyTorch > ONNX > OpenVINO > CoreML > TFLite

MocapNET

We present MocapNET, a real-time method that estimates the 3D human pose directly in the popular Bio Vision Hierarchy (BVH) format, given estimations of the 2D body joints originating from monocular color images. Our contributions include: (a) A novel and compact 2D pose NSRM representation. (b) A human body orientation classifier and an ensemble of orientation-tuned neural networks that regress the 3D human pose by also allowing for the decomposition of the body to an upper and lower kinematic hierarchy. This permits the recovery of the human pose even in the case of significant occlusions. (c) An efficient Inverse Kinematics solver that refines the neural-network-based solution providing 3D human pose estimations that are consistent with the limb sizes of a target person (if known). All the above yield a 33% accuracy improvement on the Human 3.6 Million (H3.6M) dataset compared to the baseline method (MocapNET) while maintaining real-time performance

Measure-Me

Measure Me: An app ‘concept’ to extract measurements from images

stashtag

stashmarkers

visage-ml

InstantID

InstantID : Zero-shot Identity-Preserving Generation in Seconds 🔥

Tdarr

Tdarr - Distributed transcode automation using FFmpeg/HandBrake + Audio/Video library analytics + video health checking (Windows, macOS, Linux & Docker)

MultiLabelImageClassificationPytorch

vivict

An easy to use in-browser tool for subjective comparison of the visual quality of different encodings of the same video source.

stashapp-tools

Tools to interface with stashapps API

FreeU

FreeU: Free Lunch in Diffusion U-Net (CVPR2024 Oral)

gradio

Build and share delightful machine learning apps, all in Python. 🌟 Star to support our work!

StyleGAN-Human

StyleGAN-Human: A Data-Centric Odyssey of Human Generation

Awesome-Avatars

List of recent advances for human avatars, including generation, reconstruction, and editing, etc.