# GenAI Model/system every iteration visible
**URL:**
**Author:**  [@bartatluca](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fbartatluca)%5C
**Post date:** [January 10, 2025, 9:34pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fgenai-model-system-every-iteration-visible%2F135202%2F1 "2025-01-10T21:34:37Z")
Hello
A while now, I have been looking for a GenAI model/system/software where, apart from getting the final result image, all the iterations happening in the background can also be viewed.
This is to visually study, practical research, how de iterations evolve from noise to a final image result.
Can any of you point me in the right direction?
---
**Author:**  [@John6666](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FJohn6666)%5C
**Post date:** [January 11, 2025, 1:28am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fgenai-model-system-every-iteration-visible%2F135202%2F2 "2025-01-11T01:28:49Z")
Like this?
> [@How to get intermeidate output images](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fhow-to-get-intermeidate-output-images%2F29144)%3A
>
> Is it possible to get the images at each denoising step via the Diffusers library? I am sure I’ve seen it done but can’t find where or how.
---
**Author:**  [@Alanturner2](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FAlanturner2)%5C
**Post date:** [January 11, 2025, 8:51am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fgenai-model-system-every-iteration-visible%2F135202%2F3 "2025-01-11T08:51:39Z")
Hello!
For your use case, where you’d like to see the iterative process behind the generation of an image from noise to the final result, you might want to explore **Stable Diffusion** models. Many implementations of Stable Diffusion, like the ones in **Hugging Face** or **RunwayML** , provide the option to view or log intermediate steps, showing the evolution of the image as it is generated.
You can also experiment with **GANs** (Generative Adversarial Networks), specifically the **Progressive GAN** or **StyleGAN** , which allow you to observe how an image progresses from random noise through each phase of refinement. Some tools also offer the ability to visualize latent space traversal, where you can track how the model’s input evolves into the final output.
Additionally, platforms like **Google Colab** and **Kaggle Kernels** may offer notebooks where you can access and manipulate these models to visualize intermediate steps during image generation.
I hope this helps, and best of luck with your research!
---
**Author:**  [@bartatluca](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fbartatluca)%5C
**Post date:** [January 13, 2025, 11:07am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fgenai-model-system-every-iteration-visible%2F135202%2F4 "2025-01-13T11:07:15Z")
@John6666 As soon as I have time I’ll try out the callbacks.
@Alanturner2 Wow, thanks, you describe my question clearly and take me directly in the right direction!
Now figuring out how that works, do you know a tutorial, article, …, where this is explained in more depth or can this be done by the ‘callbacks’?