AI RESEARCH
StoryTailor:A Zero-Shot Pipeline for Action-Rich Multi-Subject Visual Narratives
arXiv CS.CV
•
ArXi:2602.21273v2 Announce Type: replace Generating multi-frame, action-rich visual narratives without fine-tuning faces a threefold tension: action text faithfulness, subject identity fidelity, and cross-frame background continuity. We propose StoryTailor, a zero-shot pipeline that runs on a single RTX 4090 (24 GB) and produces temporally coherent, identity-preserving image sequences from a long narrative prompt, per-subject references, and grounding boxes.