This category is to ask questions about 
Inference Endpoints, our production inference solution to easily deploy machine learning models hosted on the Hub.
1 Like
Hello!
I’m making a mobile app for text-to-image and thinking about your Inference Endpoint, but it’s not clear to me regarding the pricing. If I create one endpoint for one model it is only for that model right? I mean if I want to have ability in the app that lets user to switch between couple different models I need to create different endpoints for those models and pay for all of them separately?
Thanks!
Okey, I found that I can have a multi-model endpoint. Very nice post - Multi-Model GPU Inference with Hugging Face Inference Endpoints
What about callbacks for text-to-image generation, can I track a progress (I want to show it in the app, so user would know aprox time of the generation)? Is it possible? I saw there is Webhooks that you can create on Space but not sure if that the best/only way?
1 Like