# Inverting images/encoding images into noise?

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Finverting-images-encoding-images-into-noise%2F22615%3E%5C
**Category:** 🧨 Diffusers\
**Created:** [September 6, 2022, 7:03am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Finverting-images-encoding-images-into-noise%2F22615 "2022-09-06T07:03:32Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![ryanramos](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/ryanramos/32/15559_2.png) [@ryanramos](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fryanramos)%5C
**Post date:** [September 6, 2022, 7:03am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Finverting-images-encoding-images-into-noise%2F22615%2F1 "2022-09-06T07:03:33Z")

</div>

Hi, just wondering if the diffusers repo already provides a way to invert images (or I guess latents in the case of latent diffusion models) into noise that denoise via DDIM back into the original inputs as described in the [DDIM paper](https://arxiv.org/pdf/2010.02502.pdf), sections 4.3/5.4?