A causal VAE with variable reference guidance and a Rectified Flow Transformer enables real-time streamable high-quality talking portrait video generation from audio and images.
Chatanyone: Stylized real-time portrait video generation with hierarchical motion diffusion model
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Real-Time Generation of Streamable Talking Portrait Video with Reference-Guided Deep Compression VAEs
A causal VAE with variable reference guidance and a Rectified Flow Transformer enables real-time streamable high-quality talking portrait video generation from audio and images.