Inference Endpoints API slow generating images

Inference Endpoints on the Hub
1

Hi…members

I have a Pro plan ( 9$ for the test of my project ) and can easily access models by inference API and token authorization. I created the flux dev app. Next js but why is API slow generating images?

and this is my app.

thanks for help

1 Like
2

I’ve never used the Endpoint API, and unlike Spaces, I can’t look at the code, so I can’t say for sure.
But the image generation is really slow…
Could it be that Endpoint doesn’t have enough VRAM?
If you’re using FLUX Dev, you’ll need about 35GB of VRAM. It will still work if you have a little less, but it will be very slow.
The Zero GPU space you can use with the Pro plan gives you 40GB of VRAM for a moment, so it’s enough for FLUX too.