petermckj

The-Selfie-Coach

Get instant selfie coaching from Kylie J.

lunar_tools

toolkit for interactive exhibitions

pandas-ai

Chat with your database (SQL, CSV, pandas, polars, mongodb, noSQL, etc). PandasAI makes data analysis conversational using LLMs (GPT 3.5 / 4, Anthropic, VertexAI) and RAG.

LivePortrait

Bring portraits to life!

llm-chatbot-rag

A local LLM chatbot with RAG for PDF input files

ComfyUI_IPAdapter_plus

DGAI

Learn Generative AI with PyTorch (Manning Publications, 2024)

ComfyUI-DragNUWA

Lifespan_Age_Transformation_Synthesis

Lifespan Age Transformation Synthesis code

FADING

insanely-fast-whisper

Retrieval-based-Voice-Conversion-WebUI

Easily train a good VC model with voice data <= 10 mins!

persuasive_jailbreaker

Persuasive Jailbreaker: we can persuade LLMs to jailbreak them!

OpenVoice

Instant voice cloning by MyShell.

comfy_mtb

Animation oriented nodes pack for ComfyUI

video2bvh2.0

https://github.com/Dene33/video_to_bvh but with python 3 and tensorflow2.0

VideoTo3dPoseAndBvh

Convert video to the bvh motion file

video_to_bvh

Convert human motion from video to .bvh

video2bvh

Extracts human motion in video and save it as bvh mocap file.

openpose

OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation

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

VCoder

VCoder: Versatile Vision Encoders for Multimodal Large Language Models, arXiv 2023 / CVPR 2024

AnyDoor

Official implementations for paper: Anydoor: zero-shot object-level image customization

fin-sight

FinSight - Financial Insights at Your Fingertip: FinSight is a cutting-edge AI assistant tailored for portfolio managers, investors, and finance enthusiasts. It streamlines the process of gaining crucial insights and summaries about a company in a user-friendly manner.

litgpt

20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.

LaTeX-OCR

pix2tex: Using a ViT to convert images of equations into LaTeX code.

gpt-engineer

Specify what you want it to build, the AI asks for clarification, and then builds it. Not actively maintained.

quivr

Open-source RAG Framework for building GenAI Second Brains 🧠 Build productivity assistant (RAG) ⚡️🤖 Chat with your docs (PDF, CSV, ...) & apps using Langchain, GPT 3.5 / 4 turbo, Private, Anthropic, VertexAI, Ollama, LLMs, Groq that you can share with users ! Efficient retrieval augmented generation framework

Amphion

Amphion (/æmˈfaɪən/) is a toolkit for Audio, Music, and Speech Generation. Its purpose is to support reproducible research and help junior researchers and engineers get started in the field of audio, music, and speech generation research and development.

AnimateAnyone

Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation