Real-Time AttentionBender: Granular Interactive Network Bending of Video Diffusion Transformers

• URL: http://arxiv.org/abs/2606.06497v2
• Date: Mon, 08 Jun 2026 13:17:08 GMT
• Title: Real-Time AttentionBender: Granular Interactive Network Bending of Video Diffusion Transformers
• Abstract summary: Real-Time AttentionBender is a tool that extends the practice of network bending across the full depth of the video diffusion transformer (DiT)<n>It exposes self-attention, cross-attention, and the feed-forward network as independently manipulable surfaces.<n>The immediacy of live manipulation affords what we call "material intimacy" with the model.
• Score: 2.0697105762666324
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Generative video models have achieved remarkable visual fidelity, yet their prompt-only interface offers thin creative agency and obscures the model's material process from the artists working with it. We present Real-Time AttentionBender, a tool that extends the practice of network bending across the full depth of the video diffusion transformer (DiT) and brings it into live, interactive generation. Built as a plugin within the DayDream Scope ecosystem and wrapping open-source real-time Wan pipelines, the tool exposes self-attention, cross-attention, and the feed-forward network as independently manipulable surfaces, with targeting down to individual diffusion steps, DiT layers, prompt tokens, and hidden neurons. The immediacy of live manipulation affords what we call "material intimacy" with the model: a responsive, near-mechanistic feel for how specific layers and neurons shape generated video. We position the tool as simultaneously an XAIxArts probe into transformer internals and an expressive instrument for discovering aesthetics outside the model's default representational space.

Related papers

• AttentionBender: Manipulating Cross-Attention in Video Diffusion Transformers as a Creative Probe [0.03437656066916039]
  AttentionBender is a tool that manipulates cross-attention in Video Diffusion Transformers.<n>We assess AttentionBender by visualizing 4,500+ video generations across prompts, operations, and layer targets.
  arXiv  Detail & Related papers  (2026-04-22T13:11:21Z)
• FROMAT: Multiview Material Appearance Transfer via Few-Shot Self-Attention Adaptation [49.74776147964999]
  We present a lightweight adaptation technique for appearance transfer in multiview diffusion models.<n>Our method learns to combine object identity from an input image with appearance cues rendered in a separate reference image, producing multi-view-consistent output.
  arXiv  Detail & Related papers  (2025-12-10T13:06:40Z)
• SpriteHand: Real-Time Versatile Hand-Object Interaction with Autoregressive Video Generation [64.3409486422946]
  We present SpriteHand, an autoregressive video generation framework for real-time synthesis of hand-object interaction videos.<n>Our model employs a causal inference architecture for autoregressive generation and leverages a hybrid post-training approach to enhance visual realism and temporal coherence.<n> Experiments demonstrate superior visual quality, physical plausibility, and interaction fidelity compared to both generative and engine-based baselines.
  arXiv  Detail & Related papers  (2025-12-01T18:13:40Z)
• Yan: Foundational Interactive Video Generation [25.398980906541524]
  Yan is a foundational framework for interactive video generation, covering the entire pipeline from simulation and generation to editing.<n>We design a highly-compressed, low-latency 3D-VAE coupled with a KV-cache-based shift-window denoising inference process.<n>We propose a hybrid model that explicitly disentangles interactive mechanics simulation from visual rendering, enabling multi-granularity video content editing during interaction through text.
  arXiv  Detail & Related papers  (2025-08-12T03:34:21Z)
• X-Dyna: Expressive Dynamic Human Image Animation [49.896933584815926]
  X-Dyna is a zero-shot, diffusion-based pipeline for animating a single human image.<n>It generates realistic, context-aware dynamics for both the subject and the surrounding environment.
  arXiv  Detail & Related papers  (2025-01-17T08:10:53Z)
• Puppet-Master: Scaling Interactive Video Generation as a Motion Prior for Part-Level Dynamics [79.4785166021062]
  We introduce Puppet-Master, an interactive video generator that captures the internal, part-level motion of objects.<n>We demonstrate that Puppet-Master learns to generate part-level motions, unlike other motion-conditioned video generators.<n>Puppet-Master generalizes well to out-of-domain real images, outperforming existing methods on real-world benchmarks.
  arXiv  Detail & Related papers  (2024-08-08T17:59:38Z)
• Network Bending of Diffusion Models for Audio-Visual Generation [0.09558392439655014]
  We present the first steps towards the creation of a tool which enables artists to create music visualizations. We investigate the application of network bending, the process of applying transforms within the layers of a generative network, to image generation diffusion models. We generate music-reactive videos using Stable Diffusion by passing audio features as parameters to network bending operators.
  arXiv  Detail & Related papers  (2024-06-28T00:39:17Z)
• Generative Rendering: Controllable 4D-Guided Video Generation with 2D Diffusion Models [40.71940056121056]
  We present a novel approach that combines the controllability of dynamic 3D meshes with the expressivity and editability of emerging diffusion models. We demonstrate our approach on various examples where motion can be obtained by animating rigged assets or changing the camera path.
  arXiv  Detail & Related papers  (2023-12-03T14:17:11Z)
• VDT: General-purpose Video Diffusion Transformers via Mask Modeling [62.71878864360634]
  Video Diffusion Transformer (VDT) pioneers the use of transformers in diffusion-based video generation. We propose a unified spatial-temporal mask modeling mechanism, seamlessly integrated with the model, to cater to diverse video generation scenarios.
  arXiv  Detail & Related papers  (2023-05-22T17:59:45Z)
• NeuralField-LDM: Scene Generation with Hierarchical Latent Diffusion Models [85.20004959780132]
  We introduce NeuralField-LDM, a generative model capable of synthesizing complex 3D environments. We show how NeuralField-LDM can be used for a variety of 3D content creation applications, including conditional scene generation, scene inpainting and scene style manipulation.
  arXiv  Detail & Related papers  (2023-04-19T16:13:21Z)

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.