Footer

Your go-to destination for discovering trending open-source projects and uncovering the insights that matter

Legal

  • Terms and conditions
  • Privacy policy

More

  • Pricing
  • Advertise
  • onedump
  • gosnakego
  • Contact us

Social

  • X (Twitter)
  • GitHub
Trendshift owl
What they build speaks louder than words
© 2026 Trendshift, created by Julian Li with ❤️
SignalAdvertise
Trendshift
SignalAdvertise
Sign in
Trendshift owl

Discover trends that matter

SignalAdvertise
DailyWeeklyMonthlyYearly
Live mentionsTopics
RepositoriesDevelopers
InsightsStats

It's a plan
It's a plan
OfinTech Desk
OfinTech Desk
Bifrost
Bifrost
Busbar
Busbar
Omnigraph
Omnigraph

NVlabs/Sana

SANA & Sol: Efficient Generative Models and Full-Stack Training & Inference Engines for Image, Video, and World Modeling

#AI image generation#AI video generation
Visit GitHub
Python
9.8k
840
32 contributors
Apache License 2.0
website
AchievementsView all →
FeaturedAdvertise to 180K+ monthly visitors
It's a plan

Open-source Linear alternative

An issue tracker where AI agents take the work you assign them

OfinTech Desk

An open-source AI workspace for finance and accounting teams, in which every figure is traced to its source

Bifrost

Fastest Enterprise AI Gateway for Routing, Governing, and Securing all your AI Traffic

Busbar

Control what AI can do before it acts

Omnigraph

Versioned graph database on object storage. Git-style workflows and multimodal retrieval

Momentum

How fast NVlabs/Sana is gaining stars, and where it lands on Trendshift and GitHub Trending

Activity and trending

Stars, forks and merged pull requests each day or month, lined up with the repository's rank on Trendshift Trending

Sep 18 – Nov 17, 2026

Stars +735 in 61 days

0100200
170

Forks +92 in 61 days

01020
18

Merged PRs 56 in 61 days

0510
8

Trendshift Trendingwhere the repository ranked each day it made the top 25

Not in the Trendshift top 25 in this period

Sep 18Sep 26Oct 4Oct 12Oct 20Oct 28Nov 5Nov 13
The left and right arrow keys step from day to day; Home and End go to the first and the last

Stars, forks, merged pull requests and Trendshift Trending rank, by day
DayStars gainedForks gainedMerged PRs
Fri, Sep 18, 2026+3+10
Sat, Sep 19, 2026+7+11
Sun, Sep 20, 2026+5+10
Mon, Sep 21, 2026+3+01
Tue, Sep 22, 2026+3+00
Wed, Sep 23, 2026+3+00
Thu, Sep 24, 2026+11+00
Fri, Sep 25, 2026+2+00
Sat, Sep 26, 2026+1+00
Sun, Sep 27, 2026+6+11
Mon, Sep 28, 2026+11+20
Tue, Sep 29, 2026+0+11
Wed, Sep 30, 2026+7+01
Thu, Oct 1, 2026+18+20
Fri, Oct 2, 2026+4+00
Sat, Oct 3, 2026+0+00
Sun, Oct 4, 2026+10+20
Mon, Oct 5, 2026+7+10
Tue, Oct 6, 2026+11+20
Wed, Oct 7, 2026+4+10
Thu, Oct 8, 2026+10+13
Fri, Oct 9, 2026+6+01
Sat, Oct 10, 2026+6+04
Sun, Oct 11, 2026+2+05
Mon, Oct 12, 2026+24+11
Tue, Oct 13, 2026+19+10
Wed, Oct 14, 2026+30+20
Thu, Oct 15, 2026+25+50
Fri, Oct 16, 2026+19+42
Sat, Oct 17, 2026+16+10
Sun, Oct 18, 2026+10+10
Mon, Oct 19, 2026+13+03
Tue, Oct 20, 2026+9+01
Wed, Oct 21, 2026+2+20
Thu, Oct 22, 2026+170+180
Fri, Oct 23, 2026+44+38
Sat, Oct 24, 2026+12+10
Sun, Oct 25, 2026+4+00
Mon, Oct 26, 2026+17+10
Tue, Oct 27, 2026+9+01
Wed, Oct 28, 2026+29+45
Thu, Oct 29, 2026+17+22
Fri, Oct 30, 2026+5+22
Sat, Oct 31, 2026+7+20
Sun, Nov 1, 2026+11+40
Mon, Nov 2, 2026+18+10
Tue, Nov 3, 2026+7+31
Wed, Nov 4, 2026+0+10
Thu, Nov 5, 2026+10+41
Fri, Nov 6, 2026+4+11
Sat, Nov 7, 2026+6+10
Sun, Nov 8, 2026+7+00
Mon, Nov 9, 2026+10+42
Tue, Nov 10, 2026+3+10
Wed, Nov 11, 2026+9+00
Thu, Nov 12, 2026+12+28
Fri, Nov 13, 2026+1+00
Sat, Nov 14, 2026+4+00
Sun, Nov 15, 2026+8+40
Mon, Nov 16, 2026+3+00
Tue, Nov 17, 2026+1+00
Total+735+9256
  • 1#1 on the list
  • 7Rank that day
  • Not trending
6
  • GitHub trending history

    Where the repository ranked on GitHub Trending, one dot for each day it was on a list

    Jan 15, 2025 – May 18, 2026Best #11

    #1#5#10#15#20#25
    Top 10
    Feb 2025MayAugNovFebMay
    The left and right arrow keys step from day to day; Home and End go to the first and the last

    Mentions and achievements

    Where people are talking about NVlabs/Sana, and every badge it has earned
    1. Oct 311 post
      • MiniMax opened H3, but not the step that makes it sharp. Now someone has, and it’s not a hobbyist. It’s NVIDIA. You type a prompt into a video model and wait. What you get first is a draft: a small,…

        Read full on X, posted by @Ldataengineer

        @Ldataengineer · x.com

    2. 9 days earlier
    3. Oct 223 posts
      • AI 视频生成速度又被英伟达刷新了! Sol-H3 开源,MiniMax H3 推理提速 11 倍! 5 秒的视频,1.65 秒就能生成!🤣

        Read full on X, posted by @AndyL5cc

        @AndyL5cc · x.com

      • 5秒视频,1.65秒就生成完了。 英伟达开源 Sol-H3,专门给 MiniMax H3 视频模型提速。 这是在8张 B300、1344×768分辨率下跑出来的成绩,生成的视频还带同步音频。 🔗

        Read full on X, posted by @NFTCPS

        @NFTCPS · x.com

      • 英伟达开源Sol-H3: MiniMax H3提速11倍, 5秒视频1.65秒完成

        Read full on X, posted by @PixelAigc

        @PixelAigc · x.com

    4. 8 days earlier
    5. Oct 141 post
      • Woow Nvidia has a 2.6B open-source world model 🔥 Turn an image, a text prompt, and a camera trajectory into a controllable world. All on a single GPU. - Code available on GitHub - Paper on arXiv -…

        Read full on X, posted by @simplifyinAI

        @simplifyinAI · x.com

    6. Oct 122 posts
      • StreamRender-H3 keeps physics in a game engine and generates the visuals with H3 diffusion. Its demo runs at 24 FPS on eight GB200 GPUs.

        Read full on X, posted by @shariqriazzz

        @shariqriazzz · x.com

      • ゲームの世界を、生成AIがリアルタイムに描画する。 「StreamRender-H3」が登場。ゲームエンジンが物理演算やオブジェクトの状態、プレイヤー操作を管理し、H3が映像を生成する仕組み。 24FPS、2ステップのデノイズ処理でストリーミング描画を実現。

        Read full on X, posted by @taziku_co

        @taziku_co · x.com

    7. 12 days earlier
    8. Sep 301 post
      • Clean & confirmed in the NVIDIA Research Github repo. 0xdb2d3e2ac810237ed3eba4beb94f900100838439 $ASI

        Read full on X, posted by @attestify_

        @attestify_ · x.com

    9. 1 month earlier
    10. Aug 261 post
      • Why do most high-quality image generators need a serious GPU just to even run? Because bigger models make better images, right? NVIDIA's SANA argues that's not actually true. It's 20x smaller and…

        Read full on X, posted by @simplifyinAI

        @simplifyinAI · x.com

    11. 8 days earlier
    12. Aug 181 post
      • • Supports text-to-image, video, and world model generation • Includes Sol-RL with NVFP4 rollout and BF16 training • Integrates with SGLang, ComfyUI, and Cosmos-RL

        Read full on X, posted by @the_osps

        @the_osps · x.com

    You might also like

    Repositories close to NVlabs/Sana
    FeaturedAdvertise to 180K+ monthly visitors
    OfinTech Desk

    An open-source AI workspace for finance and accounting teams, in which every figure is traced to its source

    Bifrost

    Fastest Enterprise AI Gateway for Routing, Governing, and Securing all your AI Traffic

    Omnigraph

    Versioned graph database on object storage. Git-style workflows and multimodal retrieval

    It's a plan

    Open-source Linear alternative

    An issue tracker where AI agents take the work you assign them

    Busbar

    Control what AI can do before it acts

    openai/guided-diffusion

    Python
    7.4k837

    Stability-AI/generative-models

    Python

    Generative Models by Stability AI

    27.3k3.1k

    howardhx/speed

    Python

    Code repository for "Spectral Progressive Diffusion for Efficient Image and Video Generation"

    254

    apple-aiml-research/ml-starflow

    Python
    59440

    End2End-Diffusion/diffusion-bench

    Python

    Towards Holistic evaluation of Generative Diffusion Transformers!

    1116

    NVlabs/PixelDiT

    Python

    [CVPR 2026 Best Paper Finalist & NeurIPS 2026]

    1k79

    NVlabs/FastGen

    Python

    NVIDIA FastGen: Fast Generation from Diffusion Models

    1.1k97

    Stability-AI/StableCascade

    Jupyter Notebook

    Official Code for Stable Cascade

    6.5k508

    dcharatan/millivid

    Python

    [to appear at NeurIPS 2026] Official implementation of "MilliVid: Adaptive Latents for Long-Range Consistency in Video Generation"

    11713