interacting with the Ovis2-8B model. The script allows users to load the model, process image and video inputs, and generate text-based responses using a conversational chatbot.
Radar
New projects people are discovering or following across Pinokio.
A minimal image-to-3D app with IDOL, IDOL Turbo, a rotatable Gaussian-splat preview, and low-memory mode. Windows/Linux and Apple Silicon macOS, subject to upstream hardware support.
Unofficial ChatGPT desktop app for Linux (formerly the Codex app), built locally from OpenAI's official Linux package. Includes Chat, Work, and Codex. https://github.com/ilysenko/codex-desktop-linux
ElevenLabs at home. Multilingual TTS with Voice Design, Voice Cloning, and end-to-end LoRA fine-tuning straight from a video or podcast. Built on VoxCPM2 by OpenBMB. 30 languages incl. Russian.
The ultimate video editor powered by natural language and FFMPEG https://huggingface.co/spaces/huggingface-projects/ai-video-composer
🎬 Professional Video Dubbing Pipeline with Parakeet-TDT-0.6b-v2, Gemini AI, and Edge TTS. Complete solution for automated video dubbing with step-by-step processing and batch video creation from multiple audio files.
An Open Source Model for Audio Samples and Sound Design https://github.com/Stability-AI/stable-audio-tools
A spy satellite simulator in your browser with real-time spatial intelligence on a photorealistic 3D globe.
Multilingual Text-to-Speech with Voice Cloning (Supports: English, Japanese, Korean, Chinese, French, German, Arabic, and Spanish) https://github.com/fishaudio/fish-speech
Self-hosted, open-source video and audio downloader with a clean web UI. Supports YouTube, TikTok, Instagram, X, and 1000+ other sites via yt-dlp.
[NVIDIA ONLY - WINDOWS ONLY] InfiniteYou: Flexible Photo Recrafting While Preserving Your Identity [LoRA support fork] https://github.com/petermg/InfiniteYou
[NVIDIA ONLY] Advanced Web UI for CogVideo (text to video, image to video, video to video, extend video, etc) -- Generate videos with less than 10GB VRAM
Professional text-to-speech with voice cloning — powered by Kyutai Pocket TTS
