ImageBind

ImageBind is a local-AI tool - ImageBind One Embedding Space to Bind Them All.

Overview

PyTorch implementation and pretrained models for ImageBind. For details, see the paper: ImageBind: One Embedding Space To Bind Them All.

ImageBind learns a joint embedding across six different modalities - images, text, audio, depth, thermal, and IMU data. It enables novel emergent applications ‘out-of-the-box’ including cross-modal retrieval, composing modalities with arithmetic, cross-modal detection and generation.

For windows users, you might need to install 'soundfile' for reading/writing audio files. (Thanks @congyue1977)

Extract and compare features across modalities (e.g. Image, Text and Audio).

ImageBind code and model weights are released under the CC-BY-NC 4.0 license. See LICENSE for additional details.

ImageBind is open-source, written primarily in Python, with 9,077 GitHub stars under the Other license. It was last updated on 2025-11-21.

Install

A quick way to get started (always check the official docs for the latest):

pip install .

How it fits a local-AI stack

ImageBind runs on your own hardware, so pair it with a model and a GPU sized to your needs. Use the VRAM calculator to pick a model that fits your card, and see what you can run for hardware guidance. Related local-AI tools in the directory:

• "algernon"
• "blinko"
• Continue
• "exo"

Sources

• Source code & docs: facebookresearch/ImageBind

Stats from GitHub, 2026-10-24.