Gemini Omni – A curated list of native multimodal guides and showcases
Just a list of links to Google's own docs and Twitter demos.
Reverse lookup XKCD comics using Gemini multimodal embeddings (gemini-embedding-2-preview)
Search XKCD by image or text description using Gemini multimodal embeddings.
XKCD fans, developers experimenting with multimodal search
Google Lens · Pinterest Lens
Just a list of links to Google's own docs and Twitter demos.
Ten storage providers, but other Obsidian image upload plugins already exist.
3D UMAP visualization finds conceptually similar constitutional provisions across 188 countries.
Direct video-to-vector embedding skips transcription entirely—Twelve Labs but self-hosted.
httpie for embeddings, but it's just a Gemini API wrapper with caching.
Multimodal embeddings in one vector space—text queries find images and audio locally.