Xiaomi's LociArt Enables Free-Style Local Video Stylization with Region Control
xiaomi-research · hf · 2026-10-28
Xiaomi's MiLM Plus team (with Xidian University) released LociArt, a unified paradigm for free-style local video stylization.
- Capabilities: foreground/background/global stylization, N-masks-one-style, mixed foreground+background, two subjects with two styles — generalizing zero-shot to unseen combinations (trained only on 1-mask, 1-style pairs).
- Method: a generative refinement network provides region-level style control with temporal consistency, plus automated dataset construction and a dedicated benchmark.
A practical open contribution for video post-production and stylization workflows.
More from Multimodal
- Hands-on with Baidu's Unlimited OCR 2: whole docs in one pass, no page limit — Baidu_Inc · 2026-10-28
- Agentic video editing goes pro: senior editors 5x output, costs to collapse — dotey · 2026-10-28
- Alibaba's OvisOCR3: a 0.8B model tops OmniDocBench at 96.74 via multi-teacher distillation + RL — ATH-MaaS · 2026-10-28
- CodeCap-Bench: executable code beats natural language as video captions — Jiafu Tang · 2026-10-28
- Moving Atoms Engine turns real-world spaces and cities into high-resolution 4D models for sim — Scobleizer · 2026-10-28
- QuiverAI Launches Arrow 2 Vector Model on FLORA with Layered SVG Editing — andpoul · 2026-10-28