Radar

A diep.io private-server with a web control panel for editing settings and managing the game server

Pure MLX MiniMax-H3 text-to-video-and-audio inference for Apple Silicon.

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

An application to convert photos into Studio Ghibli style artwork using Stable Diffusion

🎬 Curated Seedance 2.5 video generation prompts — cinematic, anime, UGC, ads, storytelling, and more. Includes playable examples and creator attribution.

YuE: Open Full-song Generation Foundation Model, something similar to Suno.ai but open

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

A Web UI for easy subtitle using whisperx model based on whisper-webui by jhj0517.

Contribute to nedos/qwen3-tts-gradio development by creating an account on GitHub.

LLM inference server for Apple Silicon Mac, powered by MLX https://github.com/jundot/omlx

Windows-only version of ComfyUI which uses AMD's official ROCm and PyTorch libraries to get better performance with AMD GPUs. [auto-installation and popular performance enhancing packages like triton * sage-attention * flash-attention * bitsandbytes included ]

Higgs Audio Text-to-Speech Playground (Requires Python 3.10+)

Cosmos-Transfer2.5, built on top of Cosmos-Predict2.5, produces high-quality world simulations conditioned on multiple spatial control inputs.

Danbooru automatic image classifier

This app lets you upload an image and automatically creates descriptive tags and full‑length prompts suitable for AI art models. You can also add or edit character, copyright and general tags, tran...

Free, open-source GUI to decrypt, browse, and extract files from encrypted iPhone/iPad backups. 100% offline. No tracking.

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

1 min voice data can also be used to train a good TTS model! (few shot voice cloning)

AI filmmaking on a node canvas. Generate locally on your own GPU with the Inline Core engine (Z-Image, Krea 2, FLUX.2, MiniMax H3), or use hosted models with no GPU. Train your own LoRAs locally on the same canvas. Every render is kept as a versioned take, so you never lose the good version. Free and open source.