← Trending

Tangerine Index lists products launched since ChatGPT and people's reactions to them.

We compressed a 31B video+audio diffusion model to 14B, 6 steps, INT8

github.com

HyperFlow H3 Flash: Video Rebirth's 13.7B, 4- to 8-step compressed MiniMax-H3 for joint video and audio generation (INT8 and GGUF)

Open source

Visit github.comexternal siteGitHub152 starsexternal site

Reactions (2)

Similar products

by description similarity

  1. SimpleTuner

    A general fine-tuning kit geared toward image/video/audio diffusion models.

    GitHub2,955 starsgithub.comOpen sourcelatest reaction

  2. EasyAnimate

    📺 An End-to-End Solution for High-Resolution and Long Video Generation Based on Transformer Diffusion

    GitHub2,265 starsgithub.comOpen sourcelatest reaction

  3. Vchitect-2.0

    Vchitect-2.0: Parallel Transformer for Scaling Up Video Diffusion Models

    GitHub921 starsgithub.comOpen sourcelatest reaction

  4. FramePack

    Lets make video diffusion practical!

    Hacker News5 ptsGitHub17,346 starsgithub.comOpen source2 reactionslatest reaction

  5. Attempt to bring a cinematic experience in 256 bytes (WASM)

    repo of my sizecoding entries

    Hacker News133 ptsGitHub189 starsgithub.comOpen source2 reactionslatest reaction