Attention of a Kiss: Exploring Attention Maps in Video Diffusion for XAIxArts
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912577564442624 |
|---|---|
| author | Cole, Adam Grierson, Mick |
| author_facet | Cole, Adam Grierson, Mick |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_05323 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Attention of a Kiss: Exploring Attention Maps in Video Diffusion for XAIxArts Cole, Adam Grierson, Mick Artificial Intelligence Multimedia 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. |
| title | Attention of a Kiss: Exploring Attention Maps in Video Diffusion for XAIxArts |
| topic | Artificial Intelligence Multimedia |
| url | https://arxiv.org/abs/2509.05323 |