Internal Server Error 500 on making inference API calls.
When making requests per 2 seconds for image generation, I am getting 500 error. It should be more of 429 error for rate limitation. But that implies there is some error with the HF inference API or the model itself. Please add a comment if you know how to solve it.
The issue is not resolved. I have the same issue here witha basic API call. I get the same with a few other text-to-image models.
I'm also experiencing the same issue, continually encountering the internal error 500.
I'm also getting it but only when I deviate from the default aspect ratio. If I don't specify any width or height in the API call, it generates the image without any issue.
I am not sure if aspect ratio is even supported or not.
Hey any update on this? I am facing the same issue