Radar
New projects people are discovering or following across Pinokio.
Turn any image into a video! (Web UI created by fffiloni: https://huggingface.co/spaces/fffiloni/MS-Image2Video)
Image-to-Image model. Download, explore files and run it on Hugging Face.
AI video generation browser for Wan2GP / WanGP (and ComfyUI output folders): library, full generation recipe per clip, settings diff and side-by-side, wipe and blink A/B comparison.
Apple Silicon TTS — curated MLX-first models for cloning, multilingual speech, narration, and expressive voices.
Text-to-Speech model. Download, explore files and run it on Hugging Face.
Fully offline speech-to-text transcription with 11 local AI models. Generates styled subtitles (SRT, ASS) and burns them directly onto video. Supports Whisper, Parakeet, Canary, Moonshine, SenseVoice, Vosk, and more. No API keys required.
Turn screen recordings into focused demos with smooth zooms and local MP4 export.
Explore Earth, Mars, and the Moon with WebGPU terrain, satellite imagery, and HDR color maps. https://github.com/agaura/elevation_atlas
Orpheus TTS is an open-source text-to-speech system built on the Llama-3b backbone. Orpheus demonstrates the emergent capabilities of using LLMs for speech synthesis https://github.com/canopyai/Orpheus-TTS
Osintgram is a OSINT tool on Instagram. It offers an interactive shell to perform analysis on Instagram account of any users by its nickname
The most powerful and modular stable diffusion GUI, api and backend with a graph/nodes interface. Now ZLUDA enhanced for better AMD GPU performance.
Dia is a 1.6B parameter text to speech model created by Nari Labs. Dia directly generates highly realistic dialogue from a transcript. You can condition the output on audio, enabling emotion and tone control. The model can also produce nonverbal communications like laughter, coughing, clearing throat, etc. https://github.com/nari-labs/dia
Multi-face FaceFusion: a new face for every person in a photo or a video, in a single pass.
Contribute to Zyphra/ZONOS3-Mini development by creating an account on GitHub.
diffusers InstantID + ControlNet inspired by face-to-many from fofr (https://x.com/fofrAI) - a localized Version of https://huggingface.co/spaces/multimodalart/face-to-all
