Plugin Task: Multimodal

Hugging Face Hub

Push FiftyOne datasets to the Hugging Face Hub, and load datasets from the Hub into FiftyOne

Generate & store captions for samples using state-of-the-art captioning models

Bring images to life with Stable Video Diffusion

Semantically search emojis and copy to clipboard

Find the images in your dataset most similar to an audio file

Navigate concept space with CLIP, vector search, and FiftyOne

Find images that best interpolate between two text-based extremes

Run optical character recognition with PyTesseract

Ask (and answer) open-ended visual questions about your images

Analyze a single image or multiple images at once with GPT-4 Vision