Fast and Simple Image Search with Foundation Models — Ivan Zhou
In this blog post, I will guide you through the process of building an image search tool using multimodal foundation models. Traditional image search engines require significant engineering efforts to develop and are difficult to adapt to personal photos. In this project, we developed a fast and sim
Introduction In this blog post, I will walk you through how to build a fast and simple image search tool. Traditional image search engines require extensive engineering efforts to develop and are difficult to adapt to my own albums. In this project, my partner, Ran Li , and I developed an image search application that uses multimodal foundation models to search for highly accurate and relevant results. By following this blog post and our code base, you can easily build one yourself. This project was a side project that we did to explore large foundation models . Our code is publicly available
saved by
related reading
- Building a web search engine from scratch in two months with 3 billion neural embeddingsblog.wilsonl.in
- Creating In-Video Search - DEV Communitydev.to
- Faiss: A library for efficient similarity search - Engineering at Metaengineering.fb.com
- I built an image search engineyoutube.com
- How We Store and Search 30 Billion Facesclearview.ai
- Replicate - Run AI with an APIreplicate.com
- Prism: mapping interpretable concepts and features in a latent space of language | thesephist.comthesephist.com
- [2301.13823] Grounding Language Models to Images for Multimodal Generationarxiv.org
- On the Opportunities and Risks of Foundation Modelsarxiv.org
- Unified Multimodal Models as Auto-Encodersarxiv.org
- CLIP · Hugging Facehuggingface.co
- Energy-Based Modelsenergy-based-model.github.io