# AttnMod: Attention-Based New Art Styles

arXiv: https://arxiv.org/abs/2409.10028 · HTML: https://mlsanity.com/paper/2409.10028/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models.
- Builds on 8 of its 9 references that are in the map.
- First posted on arXiv 16 Sep 2024.

## Placed in

- Diffusion models / [Image generation, text-to-image and editing](https://mlsanity.com/diffusion/image-generation-text-to-image-and-editing/)

## Builds on (most cited first, 8 of 8)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [Elucidating the Design Space of Diffusion-Based Generative Models](https://mlsanity.com/paper/2206.00364/) (2022)
- [Style Aligned Image Generation via Shared Attention](https://mlsanity.com/paper/2312.02133/) (2023)
- [StyleDrop: Text-to-Image Generation in Any Style](https://mlsanity.com/paper/2306.00983/) (2023)

## Abstract (arXiv)

We introduce AttnMod, a training-free technique that modulates cross-attention in pre-trained diffusion models to generate novel, unpromptable art styles. The method is inspired by how a human artist might reinterpret a generated image, for example by emphasizing certain features, dispersing color, twisting silhouettes, or materializing unseen elements. AttnMod simulates this intent by altering how the text prompt conditions the image through attention during denoising. These targeted modulations enable diverse stylistic transformations without changing the prompt or retraining the model, and they expand the expressive capacity of text-to-image generation.