Attention of a Kiss: Exploring Attention Maps in Video Diffusion for XAIxArts
- URL: http://arxiv.org/abs/2509.05323v2
- Date: Tue, 09 Sep 2025 12:40:17 GMT
- Title: Attention of a Kiss: Exploring Attention Maps in Video Diffusion for XAIxArts
- Authors: Adam Cole, Mick Grierson,
- Abstract summary: This study proposes a method for extracting and visualizing cross-attention maps in generative video models.<n>Our tool provides an interpretable window into the temporal and spatial behavior of attention in text-to-video generation.
- Score: 0.03437656066916039
- License: http://creativecommons.org/licenses/by/4.0/
- 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.
Related papers
- ORIBA: Exploring LLM-Driven Role-Play Chatbot as a Creativity Support Tool for Original Character Artists [47.41729889651234]
Generative AI (GAI) has raised ethical concerns in the visual artists community.<n>This paper explores how GAI can assist visual artists in developing original characters (OCs) while respecting their creative agency.
arXiv Detail & Related papers (2025-12-14T10:29:35Z) - From Sound to Sight: Towards AI-authored Music Videos [6.8291397456847625]
We propose two novel pipelines for automatically generating music videos from any user-specified, vocal or instrumental song.<n>Inspired by the manual of music video producers, we experiment on how well latent feature-based techniques can analyse audio.<n>Next, we employ a generative model to produce the corresponding video clips.
arXiv Detail & Related papers (2025-08-20T13:54:53Z) - ArtistAuditor: Auditing Artist Style Pirate in Text-to-Image Generation Models [61.55816738318699]
We propose a novel method for data-use auditing in the text-to-image generation model.<n>ArtistAuditor employs a style extractor to obtain the multi-granularity style representations and treats artworks as samplings of an artist's style.<n>The experimental results on six combinations of models and datasets show that ArtistAuditor can achieve high AUC values.
arXiv Detail & Related papers (2025-04-17T16:15:38Z) - Generative AI for Film Creation: A Survey of Recent Advances [9.778792224015275]
Generative AI (GenAI) is transforming filmmaking, equipping artists with tools like text-to-image and image-to-video diffusion, neural radiance fields, avatar generation, and 3D synthesis.<n>This paper examines the adoption of these technologies in filmmaking, analyzing from recent AI-driven films.<n>We highlight emerging trends such as the growing use of 3D generation and the integration of real footage with AI-generated elements.
arXiv Detail & Related papers (2025-04-11T06:54:29Z) - Generative AI for Cel-Animation: A Survey [59.20171452237911]
GenAI is revolutionizing traditional animation by lowering technical barriers, broadening accessibility for a wider range of creators.<n>Despite its potential, challenges like consistency, stylistic coherence, and ethical considerations persist.<n>This paper explores future directions advancements in AI-assisted animation.
arXiv Detail & Related papers (2025-01-08T20:57:39Z) - Diffusion-Based Visual Art Creation: A Survey and New Perspectives [51.522935314070416]
This survey explores the emerging realm of diffusion-based visual art creation, examining its development from both artistic and technical perspectives.
Our findings reveal how artistic requirements are transformed into technical challenges and highlight the design and application of diffusion-based methods within visual art creation.
We aim to shed light on the mechanisms through which AI systems emulate and possibly, enhance human capacities in artistic perception and creativity.
arXiv Detail & Related papers (2024-08-22T04:49:50Z) - State of the Art on Diffusion Models for Visual Computing [191.6168813012954]
This report introduces the basic mathematical concepts of diffusion models, implementation details and design choices of the popular Stable Diffusion model.
We also give a comprehensive overview of the rapidly growing literature on diffusion-based generation and editing.
We discuss available datasets, metrics, open challenges, and social implications.
arXiv Detail & Related papers (2023-10-11T05:32:29Z) - Text-Guided Synthesis of Eulerian Cinemagraphs [81.20353774053768]
We introduce Text2Cinemagraph, a fully automated method for creating cinemagraphs from text descriptions.
We focus on cinemagraphs of fluid elements, such as flowing rivers, and drifting clouds, which exhibit continuous motion and repetitive textures.
arXiv Detail & Related papers (2023-07-06T17:59:31Z) - Inspire creativity with ORIBA: Transform Artists' Original Characters
into Chatbots through Large Language Model [4.984601297028257]
This research delves into the intersection of illustration art and artificial intelligence (AI)
By examining the impact of AI on the creative process and the boundaries of authorship, we aim to enhance human-AI interactions in creative fields.
arXiv Detail & Related papers (2023-06-16T11:25:44Z) - Pathway to Future Symbiotic Creativity [76.20798455931603]
We propose a classification of the creative system with a hierarchy of 5 classes, showing the pathway of creativity evolving from a mimic-human artist to a Machine artist in its own right.
In art creation, it is necessary for machines to understand humans' mental states, including desires, appreciation, and emotions, humans also need to understand machines' creative capabilities and limitations.
We propose a novel framework for building future Machine artists, which comes with the philosophy that a human-compatible AI system should be based on the "human-in-the-loop" principle.
arXiv Detail & Related papers (2022-08-18T15:12:02Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.