CVShenghaoLi's profile picture. Algorithm Engineer at MiniMax. Ph.D in 3D vision and GenAI.

Shenghao Li

@CVShenghaoLi

Algorithm Engineer at MiniMax. Ph.D in 3D vision and GenAI.

Shenghao Li reposted

顶级运动员都是这样热身的?


Shenghao Li reposted

🔥 KEEP - New sota for video face super-resolution


Shenghao Li reposted

最烦的就是百度网盘、夸克网盘,这几个网络垃圾。今天,哥终于找到了一个下载中文影视的终极网站 seedhub.cc


Shenghao Li reposted

Melhor vídeo do ano!


Shenghao Li reposted

Are you ready for the big reveal? 👀🐰 Drumroll please… 🥁🥁🥁 🥁🥁🥁 🥁🥁🥁 Pika 2.1 is dropping soon. Want early access? Apply via the link in thread.


Shenghao Li reposted

Bro has no enemies 🥺🎀


Shenghao Li reposted
didengshengwu's tweet image.

Shenghao Li reposted

The face says it all.. 😂


Shenghao Li reposted

Squirrels sleeping


Shenghao Li reposted

What a beautiful person to perform CPR on a sea turtle. 💖


Shenghao Li reposted

Minimax by Hailuo AI is insane. It's the best AI video model right now. 10 wild examples: 1. Girl with Pearl Earring


Shenghao Li reposted

A real life teddy bear 🧸


Shenghao Li reposted

Flux + Hailuo AI // API Level Dancing 3D Character Generation with Your Face! @eachlabs allows you to drag and drop to connect multiple AI models. You can use ready to use templates or create your own flow from endless possibilities. We are an API partner of @Hailuo_AI


Shenghao Li reposted

[NeurIPS '24] DreamMesh4D: Video-to-4D Generation with Sparse-Controlled Gaussian-Mesh Hybrid Representation Abstract (excerpt) We introduce DreamMesh4D, a novel framework that combines mesh representation with sparse-controlled deformation technique to generate high-quality 4D…


Cool~ Intelligence with everyone!

This post is unavailable.

Shenghao Li reposted

This Just Made My Day


Shenghao Li reposted

Say goodbye to tedious rotoscoping 👋 MaGGIe can efficiently predict high-quality human instance mattes from both images and videos 🔥 maggie-matt.github.io


Shenghao Li reposted

Goodbye LoRA? 👋 Not this time! ID-Aligner is able to improve identity preservation and the visual appeal of generated images and can be applied to both LoRA and Adapter models 🥳 idaligner.github.io

dreamingtulpa's tweet image. Goodbye LoRA? 👋

Not this time! ID-Aligner is able to improve identity preservation and the visual appeal of generated images and can be applied to both LoRA and Adapter models 🥳

idaligner.github.io
dreamingtulpa's tweet image. Goodbye LoRA? 👋

Not this time! ID-Aligner is able to improve identity preservation and the visual appeal of generated images and can be applied to both LoRA and Adapter models 🥳

idaligner.github.io
dreamingtulpa's tweet image. Goodbye LoRA? 👋

Not this time! ID-Aligner is able to improve identity preservation and the visual appeal of generated images and can be applied to both LoRA and Adapter models 🥳

idaligner.github.io

Shenghao Li reposted

DreamPhysics: Learning Physical Properties of Dynamic 3D Gaussians from Video Diffusion Priors Code: github.com/tyhuang0428/Dr…


United States Trends

Loading...

Something went wrong.


Something went wrong.