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
12 repositories by Attention Score · Oct 27, 2026 – Nov 2, 2026 (UTC)
2.vladimirrott / mojo-dllm
Local inference for diffusion language models (LLaDA, Dream), written in Mojo
+307 stars
from 3 · score 5.73
3.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
4.KooroshRH / AReA
Official implementation of "AReA: Adaptive Receptive-Field Attention for Efficient High-Resolution Diffusion Transformers"
+112 stars
from 40 · score 4.73
5.Lightricks / LTX-Video
Official repository for LTX-Video
+96 stars
from 11,175 · score 4.57
6.Tencent-Hunyuan / Hunyuan3D-2
High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.
+78 stars
from 15,200 · score 4.37
7.Tencent-Hunyuan / HunyuanVideo
HunyuanVideo: A Systematic Framework For Large Video Generation Model
+39 stars
from 12,668 · score 3.69
8.openvinotoolkit / openvino
OpenVINO™ is an open source toolkit for optimizing and deploying AI inference
+36 stars
from 11,066 · score 3.61
9.gcorso / DiffDock
Implementation of DiffDock: Diffusion Steps, Twists, and Turns for Molecular Docking
+7 stars
from 1,587 · score 2.08
10.diff-usion / Awesome-Diffusion-Models
A collection of resources and papers on Diffusion Models
+2 stars
from 12,380 · score 1.10
11.RunanywhereAI / runanywhere-sdks
Production ready toolkit to run AI locally
+1 stars
from 10,331 · score 0.69
12.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