Use a sample input to test your model before deployment
Testing with Sample Input Inferless platform provides the functionality to try and test the model in the API section. For the image generation model output, you have to use any base64 decoder to get the image.
Click on the model you have deployed
Click on the API
You can replace the input accordingly, and click on the Run button
Using the API endpoint Users can directly incorporate the provided code from the API section into their pipeline for performing inference.