Multiple API Response from SDXL Model

[Anbu-Divum]

I have the generative AI stable diffusion SDXL model which is the text to image generation model. Currently, I have created a backend FastAPI script for the SDXL Model which handling multiple requests simultaneously. but However, the model processing one image request at a time (Queue pattern) and which causes delays in response when handling multiple requests.

Is there a solution to expedite the generation of multiple images for concurrent requests?

Thanks in Advance