41просмотров
9.3%от подписчиков
28 марта 2026 г.
🎬 ВидеоScore: 45
X-Dub A context-rich visual dubbing. Video-to-video editing approach to synchronize lip movements with new audio while preserving identity and handling occlusions. 🔴Noise-level specialized LoRA experts for structure, lip-sync, and texture refinement.
🔴1B-parameter DiT + Whisper audio encoding.
🔴 96.36% success rate on complex dataset 👉 Project 👉 GitHub 👉 Model