AI RESEARCH
TokenDial: Continuous Attribute Control in Text-to-Video via Spatiotemporal Token Offsets
arXiv CS.CV
•
ArXi:2603.27520v1 Announce Type: new 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.