AttnMod: Attention-Based New Art Styles
On the map: Diffusion models → Image generation, text-to-image and editing
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.
Key facts. No citing papers in the map yet (data through 7 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.
Builds on
8 of 9 references.
References · 8
- 2020Denoising Diffusion Probabilistic Modelscited by 20,851
- 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
- 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
- 2020Denoising Diffusion Implicit Modelscited by 9,655
- 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,290
- 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 2,994
- 2023Style Aligned Image Generation via Shared Attentioncited by 214
- 2023StyleDrop: Text-to-Image Generation in Any Stylecited by 197
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2023Z^*: Zero-shot Style Transfer via Attention Rearrangement
- 2023Style Injection in Diffusion: A Training-free Approach for Adapting Large-scale Diffusion Models for Style Transfer
- 2024CreativeSynth: Cross-Art-Attention for Artistic Image Synthesis with Multimodal Diffusion
- 2025AttenST: A Training-Free Attention-Driven Style Transfer Framework with Pre-Trained Diffusion Models
- 2025The Cow of Rembrandt - Analyzing Artistic Prompt Interpretation in Text-to-Image Models
- 2023DreamStyler: Paint by Style Inversion with Text-to-Image Diffusion Models
- 2025StyleBlend: Enhancing Style-Specific Content Creation in Text-to-Image Diffusion Models
- 2022Inversion-Based Style Transfer with Diffusion Models