[NeurIPS 2022] Towards Robust Blind Face Restoration with Codebook Lookup Transformer
Radar
New projects people are discovering or following across Pinokio.
Text-to-Image model with 8B parameters. Download, explore files and run it on Hugging Face.
Uncensored Qwen-Image-2.1 generate + edit
An agent-native operating system, with Hermes Agent as the interface. Independent project, not affiliated with Nous Research.
A multi-voice AI audiobook generator built on Qwen3-TTS — annotate scripts with an LLM, assign unique voices to each character, per-line style instructions for delivery, clone voices from reference audio, design new voices from text descriptions, train custom voices with LoRA fine-tuning, and export to MP3 or Audacity multi-track projects
A local-first desktop workspace for persistent AI teammates. Run Codex, Claude, and Grok with dedicated workspaces, task queues, file sharing, browser control, and agent-to-agent collaboration.
An AI audiobook generator built on Qwen3-TTS. Annotate your book with an LLM, assign voices, per-line style instructions for delivery, clone voices from reference audio, design new voices from text descriptions, and export to MP3 or Audacity multi-track projects
Generate engaging 1 to 5-minute short stories with LLMs and convert them to audio with Coqui TTS, supports voice cloning, built in speakers and multilingual.
Demo showcasing ~real-time Latent Consistency Model pipeline with Diffusers and a MJPEG stream server (https://github.com/radames/Real-Time-Latent-Consistency-Model)
A multi-voice AI audiobook generator built on Qwen3-TTS — annotate scripts with an LLM, assign unique voices to each character, per-line style instructions for delivery, clone voices from reference audio, design new voices from text descriptions, train custom voices with LoRA fine-tuning, and export to MP3 or Audacity multi-track projects
See-through-walls multiplayer AR built on MultiSet VPS. Use smartphones and rayban glasses to "see" tracked entities through walls.
Testo → audio con F5-TTS scelto in base all'hardware, collegato all'LLM di LM Studio
Image-Text-to-Text model with 9B parameters. Download, explore files and run it on Hugging Face.
Local-first Facebook SOCMINT platform — automated profile intelligence, interaction network graphs, co-interactor analysis, and CNN face clustering. No LLM, no Docker, no cloud dependency. If anyone want to check AI-Powered version check the link below.
(BETA) AI shouldn't have a meter. Unlimited tokens. Forever. Your machine. Your agent. Use it from anywhere. Terminal-native coding agent powered by local LLMs — 100% open source, free forever, and installed with a single command. Proudly built on C#/.NET, because AI tooling should be infrastructure, not a subscription.
A visual workspace for your personal agent's documents, apps, and interactive artifacts.
