• Community
  • Model
  • multimodal-clip-embed

multimodal-clip-embed

CLIP-based embedding model for images and texts.

Notes

CLIP

A single model that supports both image and text inputs to produce embeddings computed by OpenAI's CLIP model. This model is part of the Universal workflow.

  • ID
  • Name
    Multimodal Clip Embedder
  • Model Type ID
    Multimodal Embedder
  • Description
    CLIP-based embedding model for images and texts.
  • Last Updated
    Oct 25, 2024
  • Privacy
    PUBLIC
  • License
  • Share
    • Badge
      multimodal-clip-embed