1.Tencent-Hunyuan / Prism
We propose Prism, a dynamic sparse attention framework for natively training joint video-audio generation models at 2K.
+377 stars
from 1,128 · score 5.93
Trending repositories
Ranked by Attention Score: stars gained over the last 7 complete days
8 repositories by Attention Score · Oct 27, 2026 – Nov 2, 2026 (UTC)
2.FlashML-org / FreeVideo
Make videos on the computer you already own. FreeVideo runs MiniMax H3 in as little as 8 GB of VRAM and 16 GB of RAM, and adapts its acceleration path to your hardware.
+241 stars
from 2,332 · score 5.49
3.KooroshRH / AReA
Official implementation of "AReA: Adaptive Receptive-Field Attention for Efficient High-Resolution Diffusion Transformers"
+112 stars
from 40 · score 4.73
4.Lightricks / LTX-Video
Official repository for LTX-Video
+96 stars
from 11,175 · score 4.57
5.Tencent-Hunyuan / Hunyuan3D-2
High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.
+78 stars
from 15,200 · score 4.37
6.Tencent-Hunyuan / HunyuanVideo
HunyuanVideo: A Systematic Framework For Large Video Generation Model
+39 stars
from 12,668 · score 3.69
7.gcorso / DiffDock
Implementation of DiffDock: Diffusion Steps, Twists, and Turns for Molecular Docking
+7 stars
from 1,587 · score 2.08
8.guanjq / targetdiff
The official implementation of 3D Equivariant Diffusion for Target-Aware Molecule Generation and Affinity Prediction (ICLR 2023)
+1 stars
from 350 · score 0.69