# Textual inversion for one image only

**URL:** <https://discuss.huggingface.co/t/textual-inversion-for-one-image-only/61796>\
**Category:** 🧨 Diffusers\
**Created:** [November 10, 2023, 11:27am UTC](https://discuss.huggingface.co/t/textual-inversion-for-one-image-only/61796 "2023-11-10T11:27:46Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![jth42](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/jth42/32/21024_2.png) [@jth42](https://discuss.huggingface.co/u/jth42)\
**Post date:** [November 10, 2023, 11:27am UTC](https://discuss.huggingface.co/t/textual-inversion-for-one-image-only/61796/1 "2023-11-10T11:27:46Z")

</div>

In order to better understand what text-to-image models can do, I’d like to get the latent space representation of an image for a model that supports this and create a new image from that.

I’m curious how similar the result then is and I would think this gives me an understanding of what kind of image a model can create and what it can’t.

I’m very new to all this, and the `textual_inversion.py` where this information may be hidden is way to complex for me to understand so far.

Does somebody have an example for this?