Skip to main content
Version: 2024.3

Hugging Face Image Classification

This action can be executed on an image level and lets you automatically send selected images to a configurable Hugging Face endpoint to classify the images by using tags.

To get the best results, you should use your own predefined model for this action. In comparison to the 'Hugging Face Zero Shot Image Classification', there is no need to include the possible results in the request as they are already predefined. This also leads to the omission of the limitation of possible results.

Available Context

For more information on context limitations refer to the Available Context section.

Multiselect: Yes Elements: Images

Configuration Options

tag_root_node: 1
tag_only_leaf_nodes: true
replace_existing_tags: true
minimum_confidence: 0.8
model_endpoint: 'https://your-hugging-face.huggingface.cloud/'

Detailed Configuration Options

  • tag_root_node: Type: Integer. Default: 0. The Root Tag to be used for the classification
  • tag_only_leaf_nodes: Type: Boolean. Default: false. If true, only leaf nodes of the tag tree will be used for the classification
  • replace_existing_tags: Type: Boolean. Default: false. If true, existing tags will be replaced with the new ones
  • minimum_confidence: Type: Float. Default: 0.8. The minimum confidence for a tag to be added to the image.
  • model_endpoint: Type: String. Endpoint url of the Hugging Face model to use.
  • asset_thumbnail_configuration_name: Type: String. Default: ''. The name of the asset thumbnail configuration to use for the image classification.