Starred repositories
Lyrs: Shows the lyrics of the track, playing on Spotify / YouTube Music
A clean combined interface for Jellyfin, TMDB, Radarr and Sonarr, as well as a replacement to Overseerr
Generative models for conditional audio generation
Mora: More like Sora for Generalist Video Generation
Multimodal Emotion eXpression Capture Amsterdam. Pipeline for capturing emotion expressions from multiple modalities (video, audio, text) in the wild.
ClusterPlex is an extended version of Plex, which supports distributed Workers across a cluster to handle transcoding requests.
A Twitch-inspired webpage that allows synced video and chat playback.
A content management system for video catalogs with chat replay capability.
A script that will parse, modify and update a Google Photos archive for upload to an iCloud Photo Library
A single Gradio + React WebUI with extensions for ACE-Step, OmniVoice, Kimi Audio, Piper TTS, GPT-SoVITS, CosyVoice, XTTSv2, DIA, Kokoro, OpenVoice, ParlerTTS, Stable Audio, MMS, StyleTTS2, MAGNet,…
Deeplake is AI Data Runtime for Agents. It provides serverless postgres with a multimodal datalake, enabling scalable retrieval and training.
Gecko - A Tool for Effective Annotation of Human Conversations
MinLabel is a voice label tool based on Tkinter in Python3.
Build smaller, faster, and more secure desktop and mobile applications with a web frontend.
Your self hosted YouTube media server
StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models
A command-line interface to generate textual and conversational datasets with LLMs.
Daily is a tool to transcode scene-linear openexr images into display-referred quicktime movies.
LlamaIndex is the leading document agent and OCR platform
[ECCV 2022] Relighting4D: Neural Relightable Human from Videos
Insert DFL metadata in square JPG image files
Grayscale SAEHD model and mode for training deepfakes. Notes, tests, experience, tools, study and explanations of the source code.
GeneFace: Generalized and High-Fidelity 3D Talking Face Synthesis; ICLR 2023; Official code