Qwen Releases UniSwap: Streaming Audio-Visual Identity Swapping Model
QwenBusinessUnit · hf · 2026-08-14
Alibaba's Qwen team released the UniSwap model, designed for talking videos to achieve synchronized appearance and voice replacement.
UniSwap employs a unified streaming audio-visual diffusion transformer architecture, coupled with specialized training and inference adaptations to maintain high-quality audio-visual sync and identity transformation during video generation.
More from Multimodal
- FrankenSim builds a physics-based virtual orchestra, piano and drum demos live — doodlestein · 2026-10-16
- vLLM officially supports Muse Spark Open: multimodal, 1M context, agentic — vllm_project · 2026-10-16
- InfoVis: 9B unified model tops open-source slide generation and editing, trained on 13M records — Jiahao Wang · 2026-10-16
- RepForcing: feature-space supervision improves few-step autoregressive video distillation — zju · 2026-10-16
- SCOPE: semantic span-aware GRPO objective improves T2I prompt rewriting — university-of-rochester · 2026-10-16
- Orbia benchmark asks: do generated videos form a consistent 3D world? — tencent · 2026-10-16