Radar

Convert, quantize, split, and validate ML models for Apple MLX on Apple Silicon

Open source alternative to NotebookLM for teams. Join our Discord: https://discord.gg/ejRNvftDp9

AI Chat Browser: Fast, Full webapp access to ChatGPT / Claude / Bard / Bing / Llama2! I use this 20 times a day.

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

Local AI text-to-speech with voice cloning and voice design, powered by GGML. C++17 port of OmniVoice (k2-fsa/OmniVoice). 646 languages, 24 kHz mono output, runs on CPU, CUDA, ROCm, Metal, Vulkan.

Official inference repo for FLUX.1 models

Effort free video editing!

An automated, AI-powered video dubbing pipeline that extracts audio, separates vocals from background noise (using Demucs), diarizes speakers (using Pyannote), and generates translated voice clones (using F5-TTS). It then re-assembles the audio using fast, frame-accurate numpy math and muxes it back into a final MKV video file.

A wav2lip Web UI using Gradio

Inference Specialization

Making Flux go brrr on GPUs.

ECCV2022 - Real-Time Intermediate Flow Estimation for Video Frame Interpolation

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

Ncode™ Generation SDK 2.0

Lolighter AutoMapper and Light Generator ported to ChroMapper.

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

FireRed-Image-Edit-1.0

GUI for a Vocal Remover that uses Deep Neural Networks.

This application takes an input video and generates a depth video that visualizes the depth information of each frame. Users can upload a video file and adjust settings like resolution and FPS. The...

We’re on a journey to advance and democratize artificial intelligence through open source and open science.