ZOYKU · Open Source Intelligence · Repository archive

tencent-hunyuan/prism

We propose Prism, a dynamic sparse attention framework for natively training joint video-audio generation models at 2K.

PythonRegularly maintained · Pushed 8d ago#diffusion-models #high-resolution #sparse-attention #video-generation

DocumentationOpen on GitHub

stars

1.5k

forks

issues

Daily star gain

—

days old

6-Axis Combat Radar

Combat Limits & Architectural Persona

Compare with other repos ->

Architectural Persona

Specialized Tactical Vanguard

Distinct edge and dedicated footprint in specialized territory

Combat Score

/ 100

7-Day Star Velocity

Fork/Star Adoption

0.8%

Cumulative stars

Next Milestone: 2k (487 stars to go)

2026-11-08: 1.5k

Daily star gain

Max: +1 / day

More by tencent-hunyuan

tencent-hunyuan/hy-memory2k tencent-hunyuan/auk1.6k tencent-hunyuan/hy-wu997

Similar projects · shared language & topics

public-apis/public-apis497.3k ebookfoundation/free-programming-books401.3k donnemartin/system-design-primer377.3k vinta/awesome-python333.4k practical-tutorials/project-based-learning289.3k nousresearch/hermes-agent261.7k

Maintainer Badge Studio

Embed GitHub README Live Badge

Embed dynamic SVG badges into your README to reflect real-time rankings and documentation mirrors.

Preview240 x 64 px SVG

GitHub Dark Theme

GitHub Light Theme

GitHub README <picture> (Auto Dark/Light)

<a href="https://git.zoyku.com/en/repo/tencent-hunyuan/prism" target="_blank" rel="noopener noreferrer">
  <picture>
    <source media="(prefers-color-scheme: dark)" srcset="https://git.zoyku.com/api/badge/card/tencent-hunyuan/prism?theme=dark&lang=en" />
    <img alt="GitHub Hot Rank - tencent-hunyuan/prism" src="https://git.zoyku.com/api/badge/card/tencent-hunyuan/prism?theme=light&lang=en" height="64" />
  </picture>
</a>