# Accessing model through Inference Endpoint

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Faccessing-model-through-inference-endpoint%2F90083%3E%5C
**Category:** Beginners\
**Created:** [June 3, 2024, 1:45pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Faccessing-model-through-inference-endpoint%2F90083 "2024-06-03T13:45:36Z")\
**Posts on this page:** 3\
**Page:** 1

<div class="post-metadata">

**Author:** ![GKYagami](https://avatars.discourse-cdn.com/v4/letter/g/ba8739/32.png) [@GKYagami](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FGKYagami)%5C
**Post date:** [June 3, 2024, 1:45pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Faccessing-model-through-inference-endpoint%2F90083%2F1 "2024-06-03T13:45:36Z")

</div>

Hi,

I want to host a custom DreamBooth diffusion model and get an output in my application through an API, by sending a prompt. ( **instead of running the model locally** ) . Will I be able to do this with **Inference Endpoints** in Hugging Face? If so, can someone please guide me on where to start?

---

<div class="post-metadata">

**Author:** ![nielsr](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/nielsr/32/39617_2.png) [@nielsr](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fnielsr)%5C
**Post date:** [June 3, 2024, 1:57pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Faccessing-model-through-inference-endpoint%2F90083%2F2 "2024-06-03T13:57:00Z")

</div>

Yes that’s totally possible!

For custom models, it’s recommended to follow this guide: [Create custom Inference Handler](https://huggingface.co/docs/inference-endpoints/guides/custom_handler). Basically, it allows you to create an endpoint for any custom model.

---

<div class="post-metadata">

**Author:** ![GKYagami](https://avatars.discourse-cdn.com/v4/letter/g/ba8739/32.png) [@GKYagami](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FGKYagami)%5C
**Post date:** [June 3, 2024, 2:07pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Faccessing-model-through-inference-endpoint%2F90083%2F3 "2024-06-03T14:07:03Z")

</div>

So if I’m understanding correctly, the computational power of the machine running the application won’t matter as long as it can get the image output from the endpoint? I just want to get the generated image output to a simple Flask application without downloading the model. Are there any restrictions, and do I need to consider the paid version just for a personal project?