R_REDDYX.XYZ
AIPython★ 1,517⑂ 12 forks

Tencent-Hunyuan/Prism

Dynamic Sparse Attention for Video-Audio

Prism enables native joint video‑audio generation by applying a dynamic sparse attention mechanism that scales to 2K resolution.

// KEY FEATURES

  • Implements dynamic sparse attention patterns that adapt per frame and audio token.
  • Enables joint video‑audio training at 2K with lower memory use.
  • Provides modular Python code with adjustable sparsity for easy integration.
#diffusion-models#high-resolution#sparse-attention#video-generation
Open on GitHub →

New repositories every 30 minutes

REDDYX AI scans GitHub 24/7 and ships the best AI/ML/Web3 projects to Telegram.

Join on Telegram
← Full catalog·Full index

// SIMILAR REPOSITORIES

FIND RUST BOTTLENECKS FAST★ 1517MCP Server for French Open Data★ 1517SKILLS: AGENTS.MD TEMPLATE FOR AI★ 1517CLAUDE-PRISM – OFFLINE SCIENTIFIC WRITING★ 1515Awesome AI Web Search★ 1519AI Interview Cheat Sheet★ 1523

← FULL CATALOG

Tencent-Hunyuan/Prism — Dynamic Sparse Attention for…