Skip to main content

Delete Model

Deletes a custom model from Leonardo AI.

Common Properties​

  • Name - The custom name of the node.
  • Color - The custom color of the node.
  • Delay Before (sec) - Waits in seconds before executing the node.
  • Delay After (sec) - Waits in seconds after executing node.
  • Continue On Error - Automation will continue regardless of any error. The default value is false.

Inputs​

  • Connection Id (String) - Connection ID from the Connect node (optional if API Key credentials are provided directly).
  • Model ID (String) - ID of the custom model to delete.

Options​

  • API Key - Leonardo AI API key (optional if using Connection ID).

Outputs​

  • Response (String) - ID of the deleted model.

How It Works​

The Delete Model node permanently removes a custom model. When executed, the node:

  1. Validates the model ID is not empty
  2. Sends a delete request to Leonardo AI API
  3. Removes the custom model from your account
  4. Returns the deleted model's ID

Requirements​

  • Valid Leonardo AI API key (via Connection ID or credentials)
  • Valid model ID from a custom model you own
  • Permission to delete the model (must be the owner)

Error Handling​

The node will return specific errors in the following cases:

  • Empty model ID - "Model ID cannot be empty. Please provide the ID of the model to delete."
  • API error - "Failed to delete model. The model may not exist or you may not have permission to delete it."
  • Runtime error - "Failed to delete model: {details}. Please verify the model ID and try again."

Usage Examples​

Delete Failed Training​

Remove a model that failed to train:

  1. Create Model
  2. Monitor with Get Model
  3. If status becomes "FAILED"
  4. Delete Model to clean up

Clean Up Test Models​

Remove models created during testing:

// List of test model IDs
const testModels = [
  'model-id-1',
  'model-id-2',
  'model-id-3'
];

// Loop through and delete each
testModels.forEach(modelId => {
  // Use Delete Model with modelId
});

Delete Outdated Models​

Remove old versions when creating new ones:

  1. Create Model v2 with improved dataset
  2. Verify v2 works well with test generations
  3. Delete Model v1 to avoid confusion
  4. Keep only the latest version

Automated Model Lifecycle​

Manage model versions automatically:

  1. Track model IDs and creation dates
  2. When creating a new model version:
    • Create the new model
    • Wait for training completion
    • Test the new model
    • If successful, delete old versions
  3. Maintain only current models

Delete Unused Models​

Clean up models no longer in use:

  1. Review your model inventory
  2. Identify models not used in recent generations
  3. Backup any important model IDs
  4. Delete unused models to free up space

Usage Notes​

  • Deletion is permanent and cannot be undone
  • The model ID becomes invalid after deletion
  • Generations created with the model are NOT affected
  • You can only delete models you own
  • Failed models should be deleted to keep your account clean
  • Consider keeping a record of model parameters before deletion
  • Deleting a model doesn't delete the dataset it was trained from
  • Useful for managing your model library
  • Regular cleanup helps stay organized
  • Delete test or experimental models after validation
  • Keep production models until replaced with better versions
  • The dataset used to train the model remains available
  • You can retrain a model from the same dataset if needed