Alibaba's TaoMate-HD streams high-res audio-video via progressive-resolution autoregression
TaoLiveAIGC · hf · 2026-11-06
Alibaba's TaoLive-AIGC team and Nanjing University present TaoMate-HD, an autoregressive model for high-resolution streaming audio-video generation targeting streaming digital humans that keep speaking and rendering as new text arrives.
Per chunk, two denoising steps establish coarse video structure at low resolution, a final step refines to high resolution, and audio is generated along the same trajectory. Each stage passes its audiovisual predictions to the same stage of the next chunk as history, retaining context across text updates to avoid repeated or interrupted speech, with optimized parallel deployment for faster coherent long-form output.
More from Multimodal
- Maestro v4 ships with built-in MCP server letting ChatGPT, Claude, Codex control it locally or remotely — cocktailpeanut · 2026-11-06
- Local AI video studio Maestro: reference-video workflows with LTX, Wan, Flux and more — cocktailpeanut · 2026-11-06
- Early tests suggest Qwen Image Edit 2.1 underperforms 2511 and 2512 — cal_01 · 2026-11-06
- VESTIGE: a one-day I2V experiment faking a continuous 42-second camera move — magratheya_64 · 2026-11-06
- Recreating GTA 6's Rockstar art style with Magnific + Nano Banana 2.1, prompt included — azed_ai · 2026-11-06
- No image or video models: developer generates visuals, music and SFX purely with Claude-written code — azed_ai · 2026-11-06