# Control diffusion processes with Optimum Neuron - ControlNet + IP-Adapter

**URL:** <https://discuss.huggingface.co/t/control-diffusion-processes-with-optimum-neuron-controlnet-ip-adapter/82866>\
**Category:** Amazon Inferentia & Trainium\
**Created:** [April 21, 2024, 4:28am UTC](https://discuss.huggingface.co/t/control-diffusion-processes-with-optimum-neuron-controlnet-ip-adapter/82866 "2024-04-21T04:28:30Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![yahavb](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/yahavb/32/26054_2.png) [@yahavb](https://discuss.huggingface.co/u/yahavb)\
**Post date:** [April 21, 2024, 4:28am UTC](https://discuss.huggingface.co/t/control-diffusion-processes-with-optimum-neuron-controlnet-ip-adapter/82866/1 "2024-04-21T04:28:30Z")

</div>

I love using optimum.neuron.NeuronStableDiffusionPipeline and wish to build a pipeline that control Stable Diffusion generation for example, generates an image that’ll preserve the spatial information from the depth map.

Doing it today without optimum neuron is less streamlined and I wish to simplify the process. I see similar example like Image-to-Image or Inpaint. Is it doable request? Should I open a PR or is there a developer guidance I can use to build it myself?

thanks!

---

<div class="post-metadata">

**Author:** ![Jingya](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/jingya/32/29444_2.png) [@Jingya](https://discuss.huggingface.co/u/Jingya)\
**Post date:** [January 15, 2025, 5:20pm UTC](https://discuss.huggingface.co/t/control-diffusion-processes-with-optimum-neuron-controlnet-ip-adapter/82866/2 "2025-01-15T17:20:40Z")

</div>

Hi @yahavb,

Just saw this, opening a PR to add the IP adapter support, this would benefits the flux once we add the support as well.