John D. Pope's repositories
Emote-hack
using chatgpt (now Claude 3) to reverse engineer code from Emote white paper. (abandoned)
MusicControlNet
using chatgpt and claude3 to reverse engineer code from whitepaper
AniPortrait
AniPortrait: Audio-Driven Synthesis of Photorealistic Portrait Animation
perplexity-ai-app
The Unofficial Perplexity AI Desktop App, powered by Electron which brings the magic of AI language processing to your desktop.
VASA-1-hack
Using Claude Opus to reverse engineer code from VASA white paper - WIP - (this is for La Raza π·)
AdaSR-TalkingHead
ICASSP2024: Adaptive Super Resolution For One-Shot Talking-Head Generation
auto-code-rover
Autonomous program improvement
decord-cuda12
An efficient video loader for deep learning with smart shuffling that's super easy to digest
desktop-search
Simple python code search
DiffSpeaker
This is the official repository for DiffSpeaker: Speech-Driven 3D Facial Animation with Diffusion Transformer
diffused-heads
Official repository for Diffused Heads: Diffusion Models Beat GANs on Talking-Face Generation
docker-fess
Docker files for Fess
elasticfeeds
A Python library for managing feeds using ElasticSearch
electron-zmq-py-toy
Toy example in which electron communicates with python with ZeroMQ
facexformer
Official implementation of FaceXFormer: A Unified Transformer for Facial Analysis
InvokeAI
InvokeAI is a leading creative engine for Stable Diffusion models, empowering professionals, artists, and enthusiasts to generate and create visual media using the latest AI-driven technologies. The solution offers an industry leading WebUI, supports terminal use through a CLI, and serves as the foundation for multiple commercial products.
Linly-Talker
Digital Avatar Conversational System - Linly-Talker. πβ¨ Linly-Talker is an intelligent AI system that combines large language models (LLMs) with visual models to create a novel human-AI interaction method. π€π€ It integrates various technologies like Whisper, Linly, Microsoft Speech Services, and SadTalker talking head generation system. ππ¬
lipsynth-experiment
End-to-end pipeline generates speech from silent lip videos using LLMs and audio-visual cues, combining "AVI-Talking" and "Towards Accurate Lip-to-Speech Synthesis in-the-Wild" techniques, enabling synthesis from visual cues alone without audio/transcripts.
livepython
Visually trace your Python code in real time.
Real3DPortrait
Real3D-Portrait: One-shot Realistic 3D Talking Portrait Synthesis; ICLR 2024 Spotlight; Official code
style2talker
[AAAI 2024] stle2talker - Official PyTorch Implementation
Vid2Persona
This project breathes life into video characters by using AI to describe their personality and then chat with you as them.
Visual-CoT
Visual CoT: Unleashing Chain-of-Thought Reasoning in the Multi-Modal Language Model