Global radar

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

A local model catalog manager for Fooocus (LoRA + Checkpoints).

AI-powered visual learning platform

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

Automatically remove the mosaics in images and videos with any GPU. Offers DirectML for AMD instead of only CUDA like most other programs.

Easy to use open source fast database for search | Good alternative to Elasticsearch | Drop-in replacement for E in the ELK stack

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

Sharp Monocular View Synthesis in Less Than a Second

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!

LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation https://huggingface.co/spaces/ashawkey/LGM

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