I am trying to return multiple generated images with one prompt by using num_images_per_prompt when calling a custom model through StableDiffusionPipeline.
However, the API Response always returns only 1 image, independently of the amount in num_images_per_prompt.
This is due to line return images[0] in api-inference-community/text_to_image.py.
I am wondering if there is any reason to limit the returned amount to only 1 image.
Could this be increased? If not, calling the API multiple times is the best option to get multiple images?
Thank you.