EmbeddingGemma 2 Demo: One Search Across Images, Video and Audio in Browser
tomaarsen · x · 2026-10-07
tomaarsen showcased his favorite multimodal embedding search demo: typing "Birds" retrieves images, videos, and even audio snippets of birds — and you can search with images or sound too.
- Powered by Google DeepMind's EmbeddingGemma 2, released the day before
- Runs fully in-browser via WebGPU
- Open-sourced on Hugging Face (google/embeddinggemma-2), supporting text/image/video/audio feature extraction, 600+ likes on day one
Related event: EmbeddingGemma 2 Demo Searches Images, Videos and Audio at Once(2 posts)→
More from Multimodal
- New tool turns AI-generated 3D models into fully rigged VTuber avatars with VRM export — Promptmethus · 2026-10-07
- Restoration LoRA for LTX-2.5 turns 240p mush into crisp 720p video — multimodalart · 2026-10-07
- Neural Emission Fields: Real-Time Rendering of Pre-integrated Neural Emitters — ssh4net · 2026-10-07
- Blender's The City Generator brings Houdini-style procedural 3D city building to everyone — bilawalsidhu · 2026-10-07
- MiniCPM-V-4.7-35B-A3B quietly appears on Hugging Face without a model card — BreakfastFriendly728 · 2026-10-07
- E-commerce product showcase animation built with Opus 5.5 + Higgsfield — Tegadesigns · 2026-10-07