# Class-conditional image generation

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fclass-conditional-image-generation%2F42536%3E%5C
**Category:** 🧨 Diffusers\
**Created:** [June 8, 2023, 12:14pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fclass-conditional-image-generation%2F42536 "2023-06-08T12:14:39Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![mario-dg](https://avatars.discourse-cdn.com/v4/letter/m/3be4f8/32.png) [@mario-dg](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fmario-dg)%5C
**Post date:** [June 8, 2023, 12:14pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fclass-conditional-image-generation%2F42536%2F1 "2023-06-08T12:14:39Z")

</div>

Hey everyone,  
for a university project I want to play around with class-conditional DDIM image generation based on a custom created dataset of microscopy images. Basically I want to generate synthetic microscopy images of a specific biological application based on a set of features that should be visible.

I have a dataset of roughly 3400 images that I tagged manually with 4 different features.  
I.e. for each image I have a vector of length 4, with 1 indicating that the specific feature is visible in the image. I want this to be necessary to control what kind of images are generated, like in stable diffusion but without a whole text prompt.

I need ideas or implementation hints on how to implement that using huggingface and accelerate.  
I dont how how to add the feature vector in the pipeline for training and inference.

Thanks for any kind of help! 🙂

---

<div class="post-metadata">

**Author:** ![WiNE-iNEFF](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/wine-ineff/32/30221_2.png) [@WiNE-iNEFF](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FWiNE-iNEFF)%5C
**Post date:** [October 12, 2023, 9:28am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fclass-conditional-image-generation%2F42536%2F2 "2023-10-12T09:28:03Z")

</div>

Have you found a way to add the feature vector in the pipeline for training and inference?