TokenDial: Continuous Attribute Control in Text-to-Video via Spatiotemporal Token Offsets

• URL: http://arxiv.org/abs/2603.27520v1
• Date: Sun, 29 Mar 2026 05:07:41 GMT
• Title: TokenDial: Continuous Attribute Control in Text-to-Video via Spatiotemporal Token Offsets
• Abstract summary: TokenDial is a framework for continuous, slider-style attribute control in pretrained text-to-video generation models.<n>We learn attribute-specific token offsets without retraining the backbone, using pretrained understanding signals.<n>We demonstrate TokenDials effectiveness on diverse attributes and prompts, achieving stronger controllability and higher-quality edits than state-of-the-art baselines.
• Score: 26.16152568319517
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We present TokenDial, a framework for continuous, slider-style attribute control in pretrained text-to-video generation models. While modern generators produce strong holistic videos, they offer limited control over how much an attribute changes (e.g., effect intensity or motion magnitude) without drifting identity, background, or temporal coherence. TokenDial is built on the observation: additive offsets in the intermediate spatiotemporal visual patch-token space form a semantic control direction, where adjusting the offset magnitude yields coherent, predictable edits for both appearance and motion dynamics. We learn attribute-specific token offsets without retraining the backbone, using pretrained understanding signals: semantic direction matching for appearance and motion-magnitude scaling for motion. We demonstrate TokenDial's effectiveness on diverse attributes and prompts, achieving stronger controllability and higher-quality edits than state-of-the-art baselines, supported by extensive quantitative evaluation and human studies.

Related papers

• Attribute Token Arithmetic: Disentangled and Continuous Semantic Control for Visual Autoregressive Models [39.64892851584864]
  We introduce Attribute Token Arithmetic (ATA), a method that enables disentangled and continuous attribute control in visual autoregressive modelling.<n>We show that ATA achieves identity-preserving, fine-grained, and multi-attribute adjustment, outperforming existing autoregressive editing baselines in controllability, generality, and computational efficiency.
  arXiv  Detail & Related papers  (2026-08-28T08:51:57Z)
• Spatial Temporal Synergy: Balancing Change and Invariance in Text Driven 3D Human Motion Editing [78.44034844227868]
  Text-driven human motion editing aims to modify existing motion sequences according to natural language instructions.<n>Change and Invariance Motion Editing (CIME) is a unified framework that comprehensively decouples change and invariance into spatial pose and temporal rhythm dimensions.<n>Experiments on the MotionFix and STANCE Adjustment datasets demonstrate that CIME achieves state-of-the-art performance in editing alignment and structural fidelity.
  arXiv  Detail & Related papers  (2026-08-17T01:54:44Z)
• Controlla: Learning Controllability via Graph-Constrained Latent Geometry [3.797867929356259]
  We propose a modular factorized-control framework that treats controllability as a property of structured latent geometry.<n>Controlla learns identity and attribute factors from multimodal inputs and aligns them with graph priors.<n>Experiments show consistent improvements in controllability, identity preservation, and cross-modal alignment.
  arXiv  Detail & Related papers  (2026-05-15T20:06:02Z)
• Towards Arbitrary Motion Completing via Hierarchical Continuous Representation [64.6525112550758]
  We propose a novel parametric activation-induced hierarchical implicit representation framework, called NAME, based on Implicit Representations (INRs)<n>Our method introduces a hierarchical temporal encoding mechanism that extracts features from motion sequences at multiple temporal scales, enabling effective capture of intricate temporal patterns.
  arXiv  Detail & Related papers  (2025-12-24T14:07:04Z)
• FineXtrol: Controllable Motion Generation via Fine-Grained Text [46.315592728110346]
  FineXtrol is a novel framework for efficient motion generation guided by temporally-aware, precise, user-friendly, and fine-grained textual control signals.<n>We show that FineXtrol achieves strong performance in controllable motion generation.
  arXiv  Detail & Related papers  (2025-11-24T09:32:26Z)
• TempoControl: Temporal Attention Guidance for Text-to-Video Models [18.49685485536669]
  We introduce TempoControl, a method that allows for temporal alignment of visual concepts during inference.<n>Our method steers attention using three complementary principles: aligning its temporal shape with a control signal, amplifying it where visibility is needed, and maintaining spatial focus.<n>We demonstrate its effectiveness across various video generation applications, including temporal reordering for single and multiple objects, as well as action and audio-aligned generation.
  arXiv  Detail & Related papers  (2025-10-02T17:13:35Z)
• From Prompt to Progression: Taming Video Diffusion Models for Seamless Attribute Transition [57.809291244375345]
  We propose a simple yet effective method to extend existing models for smooth and consistent attribute transitions.<n>Our approach constructs a data-specific transitional direction for each noisy latent, guiding the gradual shift from initial to final attributes frame by frame.<n>We also present the Controlled-Attribute-Transition Benchmark (CAT-Bench), which integrates both attribute and motion dynamics.
  arXiv  Detail & Related papers  (2025-09-24T01:58:22Z)
• AttriCtrl: Fine-Grained Control of Aesthetic Attribute Intensity in Diffusion Models [32.46570968627392]
  AttriCtrl is a plug-and-play framework for precise and continuous control of aesthetic attributes.<n>We quantify abstract aesthetics by leveraging semantic similarity from pre-trained vision-language models.<n>It is fully compatible with popular open-source controllable generation frameworks.
  arXiv  Detail & Related papers  (2025-08-04T07:49:40Z)
• FlexiAct: Towards Flexible Action Control in Heterogeneous Scenarios [49.09128364751743]
  Action customization involves generating videos where the subject performs actions dictated by input control signals.<n>Current methods use pose-guided or global motion customization but are limited by strict constraints on spatial structure.<n>We propose FlexiAct, which transfers actions from a reference video to an arbitrary target image.
  arXiv  Detail & Related papers  (2025-05-06T17:58:02Z)
• "Principal Components" Enable A New Language of Images [79.45806370905775]
  We introduce a novel visual tokenization framework that embeds a provable PCA-like structure into the latent token space.<n>Our approach achieves state-of-the-art reconstruction performance and enables better interpretability to align with the human vision system.
  arXiv  Detail & Related papers  (2025-03-11T17:59:41Z)
• PixelPonder: Dynamic Patch Adaptation for Enhanced Multi-Conditional Text-to-Image Generation [24.964136963713102]
  We present PixelPonder, a novel unified control framework that allows for effective control of multiple visual conditions under a single control structure.<n>Specifically, we design a patch-level adaptive condition selection mechanism that dynamically prioritizes spatially relevant control signals at the sub-region level.<n>Extensive experiments demonstrate that PixelPonder surpasses previous methods across different benchmark datasets.
  arXiv  Detail & Related papers  (2025-03-09T16:27:02Z)
• Is Disentanglement enough? On Latent Representations for Controllable Music Generation [78.8942067357231]
  In the absence of a strong generative decoder, disentanglement does not necessarily imply controllability. The structure of the latent space with respect to the VAE-decoder plays an important role in boosting the ability of a generative model to manipulate different attributes.
  arXiv  Detail & Related papers  (2021-08-01T18:37:43Z)

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.