capabilities.work

Pick a Model from a Collection and Predict

A 4-step recipe with Replicate. We can help you get access.

Recipe · 4 steps

Pick a Model from a Collection and Predict

with Replicate · Artificial Intelligence Management

Resolve a model from a curated collection and run a prediction on its latest version.

  1. Read the curated collection to confirm it exists and that it lists models to choose from.
  2. Confirm the chosen model and capture its latest version ID to run.
  3. Create a prediction for the chosen model's latest version with the supplied input.
  4. Retrieve the prediction state, repeating via the retry branch until the prediction reaches a terminal status.
What you'll need to have ready
  • apiToken: Replicate API token used as a Bearer credential.
  • collectionSlug: The slug of the collection, like super-resolution or text-to-image.
  • modelOwner: The owner of the model chosen from the collection.
  • modelName: The name of the model chosen from the collection.
  • input: The model's input as a JSON object for the prediction.
For your developer

Arazzo workflow replicate:collection-predict, 4 operations: collections.get → models.get → predictions.create → predictions.get. Specs on APIs.io.

More recipes with Replicate

Create a Deployment and Run a Prediction Through ItResolve Latest Version and PredictRun an Official Model and PollCreate Prediction and Poll Until CompleteRun a Prediction with Bounded Wait and CancelScale a Deployment and Run a PredictionSearch for a Model and Run a PredictionStart a Training and Poll Until CompleteFetch Webhook Secret and Run a Webhook Prediction