Attention of a Kiss: Exploring Attention Maps in Video Diffusion for XAIxArts

Adam Cole, Mick Grierson
8/30/2025
cs.AIcs.MM

No confident code implementation found for this paper.

Abstract

This paper presents an artistic and technical investigation into the attention mechanisms of video diffusion transformers. Inspired by early video artists who manipulated analog video signals to create new visual aesthetics, this study proposes a method for extracting and visualizing cross-attention maps in generative video models. Built on the open-source Wan model, our tool provides an interpretable window into the temporal and spatial behavior of attention in text-to-video generation. Through exploratory probes and an artistic case study, we examine the potential of attention maps as both analytical tools and raw artistic material. This work contributes to the growing field of Explainable AI for the Arts (XAIxArts), inviting artists to reclaim the inner workings of AI as a creative medium.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Analysis of Attention in Video Diffusion Transformers

90% match2025

In-Context Audio Control of Video Diffusion Transformers

88% match2025

TIMERIPPLE: Accelerating vDiTs by Understanding the Spatio-Temporal Correlations in Latent Space

86% match2025

Understanding Attention Mechanism in Video Diffusion Models

86% match2025

Target-Aware Video Diffusion Models

84% match2025

Open-Sora: Democratizing Efficient Video Production for All

84% match1 repo29.2k2024

Cite this paper

@article{cole2025attention,
  title  = {Attention of a Kiss: Exploring Attention Maps in Video Diffusion for XAIxArts},
  author = {Adam Cole and Mick Grierson},
  year   = {2025},
  eprint = {2509.05323},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2509.05323v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2509.05323.svg)](https://codeofpaper.com/paper/2509.05323)

Discussion