Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Ben-Yosef, Matan, Halperin, Tavi, Korem, Naomi Ken, Salama, Mohammad, Cain, Harel, Joseph, Asaf, Chen, Anthony, Jelercic, Urska, Bibi, Ofir
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2603.24793
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917362227216384
author Ben-Yosef, Matan
Halperin, Tavi
Korem, Naomi Ken
Salama, Mohammad
Cain, Harel
Joseph, Asaf
Chen, Anthony
Jelercic, Urska
Bibi, Ofir
author_facet Ben-Yosef, Matan
Halperin, Tavi
Korem, Naomi Ken
Salama, Mohammad
Cain, Harel
Joseph, Asaf
Chen, Anthony
Jelercic, Urska
Bibi, Ofir
contents Controlling video and audio generation requires diverse modalities, from depth and pose to camera trajectories and audio transformations, yet existing approaches either train a single monolithic model for a fixed set of controls or introduce costly architectural changes for each new modality. We introduce AVControl, a lightweight, extendable framework built on LTX-2, a joint audio-visual foundation model, where each control modality is trained as a separate LoRA on a parallel canvas that provides the reference signal as additional tokens in the attention layers, requiring no architectural changes beyond the LoRA adapters themselves. We show that simply extending image-based in-context methods to video fails for structural control, and that our parallel canvas approach resolves this. On the VACE Benchmark, we outperform all evaluated baselines on depth- and pose-guided generation, inpainting, and outpainting, and show competitive results on camera control and audio-visual benchmarks. Our framework supports a diverse set of independently trained modalities: spatially-aligned controls such as depth, pose, and edges, camera trajectory with intrinsics, sparse motion control, video editing, and, to our knowledge, the first modular audio-visual controls for a joint generation model. Our method is both compute- and data-efficient: each modality requires only a small dataset and converges within a few hundred to a few thousand training steps, a fraction of the budget of monolithic alternatives. We publicly release our code and trained LoRA checkpoints.
format Preprint
id arxiv_https___arxiv_org_abs_2603_24793
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle AVControl: Efficient Framework for Training Audio-Visual Controls
Ben-Yosef, Matan
Halperin, Tavi
Korem, Naomi Ken
Salama, Mohammad
Cain, Harel
Joseph, Asaf
Chen, Anthony
Jelercic, Urska
Bibi, Ofir
Computer Vision and Pattern Recognition
Multimedia
Sound
I.4.9; I.2.10
Controlling video and audio generation requires diverse modalities, from depth and pose to camera trajectories and audio transformations, yet existing approaches either train a single monolithic model for a fixed set of controls or introduce costly architectural changes for each new modality. We introduce AVControl, a lightweight, extendable framework built on LTX-2, a joint audio-visual foundation model, where each control modality is trained as a separate LoRA on a parallel canvas that provides the reference signal as additional tokens in the attention layers, requiring no architectural changes beyond the LoRA adapters themselves. We show that simply extending image-based in-context methods to video fails for structural control, and that our parallel canvas approach resolves this. On the VACE Benchmark, we outperform all evaluated baselines on depth- and pose-guided generation, inpainting, and outpainting, and show competitive results on camera control and audio-visual benchmarks. Our framework supports a diverse set of independently trained modalities: spatially-aligned controls such as depth, pose, and edges, camera trajectory with intrinsics, sparse motion control, video editing, and, to our knowledge, the first modular audio-visual controls for a joint generation model. Our method is both compute- and data-efficient: each modality requires only a small dataset and converges within a few hundred to a few thousand training steps, a fraction of the budget of monolithic alternatives. We publicly release our code and trained LoRA checkpoints.
title AVControl: Efficient Framework for Training Audio-Visual Controls
topic Computer Vision and Pattern Recognition
Multimedia
Sound
I.4.9; I.2.10
url https://arxiv.org/abs/2603.24793