跳过导航
One image + text + camera trajectory = controllable worlds. All on a single GPU.
0:00 / 0:20

One image + text + camera trajectory = controllable worlds. All on a single GPU.

NVIDIA AI

@NVIDIAAI36万 位关注者

在 X 上查看
1,220 个赞下载原帖

93,607 次观看

One image + text + camera trajectory = controllable worlds. All on a single GPU. Our research team just released SANA-WM, a 2.6B open source world model natively trained for 60-second video generation with precise camera control.

33 条评论

评论来自 X (Twitter) 上的原帖

  • NVIDIA AI 的头像

    @NVIDIAAI

    The architecture features Hybrid Linear Attention, Dual-Branch Camera Control, Two-Stage Generation Pipeline, and a Robust Annotation Pipeline. All of this combines for stronger action-following accuracy and higher throughput while maintaining visual quality.

    48 个赞

  • NVIDIA AI 的头像

    @NVIDIAAI

    You can find the full project including the paper, code, and model here 👇

    47 个赞

  • PublicAI 的头像

    @PublicAI_

    this sounds super cool! creating worlds with just a single gpu is a game changer. can't wait to see what people do with SANA-WM!

    3 个赞

  • The AI Colony R&D 的头像

    @TheAIColonyRD

    60 seconds of video. One image to start. One GPU to run it. Open source. The game engine just became a prompt.

    2 个赞

  • PaperTrace 的头像

    @usepapertrace

    Looks great. Can you link the paper and repo, name training data sources/licenses, and state the exact GPU/VRAM for the single GPU claim? That would let others reproduce the camera control results.

    1 个赞

  • Kekko D’Amato 的头像

    @kekkodamato_

    2.6B for 60-second world-consistent video with camera control is a wild benchmark. The open-source release is what makes this actually useful — most teams don't need Hollywood quality, they need something they can run and fine-tune. What hardware are people actually running inference on?

    1 个赞

  • Naveen 的头像

    @heynaavi

    love how you're pushing the boundaries of video generation with SANA-WM

    1 个赞

  • Supersocks 的头像

    @iamsupersocks

    @llmgram

    1 个赞

  • Jonathan 🇺🇲 的头像

    @thaonlyjonathan

    You're on the right track Nvidia, but please make it more performant and keep training. Go full send on compute for training.

    1 个赞

  • Pruthviraj P 的头像

    @ashwathama

    SANA-WM 2.6B open source world model for 60-second video on a single GPU

    1 个赞

  • Creative Side-B 的头像

    @CreativeSideB

    Looking very soulless, generic and not worth it!

    1 个赞

  • Ajeya 的头像

    @_Ajeya

    Can it run on a 4090?

    1 个赞

  • Dray 的头像

    @drayinvests

    $NVDA seriously is going to rule the world

    1 个赞

  • Apex 的头像

    @ApexMetaX

    One image + text + trajectory = controllable worlds on a single GPU. Simulation is becoming cheap and precise.

    1 个赞

  • Chiko Chiko 的头像

    @chikoevm

    bbox queen looks clean, seedance 2 with gpt image 2, huh? got a side by side without seedance to compare?

  • Tim 的头像

    @timsius

    Love this

  • Asim Hussain 的头像

    @asimcodes

    "single GPU" is the part that changes everything here. world models for video have always felt like a data center problem, shrinking that down to one GPU opens this up to a completely different audience

  • XtaxRich | AI Tool Tests 的头像

    @xtaxrich

    SANA-WM is concrete enough to test. One image, text, camera path, and single GPU are the setup. Control drift is the receipt.

  • 舔狗AI实验室 🛠️🐶 的头像

    @SamMusical6990

    2.6B for 60-second generation is compelling if SANA-WM keeps temporal drift under control.

  • Eco 的头像

    @EconEpoch

    @KashJim50723 🤷‍♂️