Generate Images Faster with Stable Diffusion and RTX

Поделиться
HTML-код
  • Опубликовано: 2 июн 2024
  • ComfyUI offers a streamlined interface for Stable Diffusion, accelerated on NVIDIA RTX GPUs with NVIDIA TensorRT. Fast image generation combined with one-step RTX-enhanced ControlNets unlocks unprecedented workflow control.
    ✨ #TensorRT and GeForce #RTX unlock ComfyUI SD superhero powers 🦸⚡
    📗 DIY notebook: nvda.ws/3Kv1G1d ✨
    RTX GPUs not only speed up image generation but offer access to the newest and broadest range of AI features. Learn more about AI on RTX 👉 www.nvidia.com/en-us/ai-on-rtx/
    Join the NVIDIA Developer Program: nvda.ws/3OhiXfl
    Read and subscribe to the NVIDIA Technical Blog: nvda.ws/3XHae9F
  • НаукаНаука

Комментарии • 15

  • @TomanswerAi
    @TomanswerAi 25 дней назад

    Very cool! Does the notebook only contain workflow for basic generation? Anywhere to locate the other workflows used in this example?

  • @wasasquatch4027
    @wasasquatch4027 20 дней назад

    Is this a pre-compile solution?

  • @realthing2158
    @realthing2158 29 дней назад +2

    Would this also benefit RTX 2080 Super and what do I need to do to enable it? Is downloading the latest drivers enough?

  • @SyamsQbattar
    @SyamsQbattar День назад

    how to run Faster stable diffusion with rtx?

  • @WallyMahar
    @WallyMahar 27 дней назад

    there is no try. BUY. correct?

  • @megaigrovoy
    @megaigrovoy 27 дней назад +1

    Where is tensor rt loader???

    • @NVIDIADeveloper
      @NVIDIADeveloper  27 дней назад +2

      Here's the related notebook console.brev.dev/launchable/deploy?userID=2x2sil999&orgID=ktj33l4xj&name=ComfyUI_TensorRT&instance=L4@g2-standard-4:nvidia-l4:1&diskStorage=500&cloudID=GCP&baseImage=docker.io/pytorch/pytorch:2.2.0-cuda12.1-cudnn8-runtime&ports=ComfUI:8188&file=github.com/brevdev/notebooks/blob/main/tensorrt-comfyui.ipynb&launchableID=env-2hQX3n7ae5mq3NjNZ32DfAG0tJf&=&linkId=100000264904516

    • @amoujhang1384
      @amoujhang1384 26 дней назад +2

      I think this video is not using the TensorRT node. The link provided from notebook shows a different workflow.

    • @megaigrovoy
      @megaigrovoy 21 день назад

      @@NVIDIADeveloper Ok, but where is instantid in your notebook?

  • @MilesBellas
    @MilesBellas 29 дней назад +6

    Nvidia could buy Stable Diffusion, The Foundry and Autodesk to create a next generation development platform.....

    • @a.tevetoglu3366
      @a.tevetoglu3366 27 дней назад +1

      No need to buy if omniverse connects all within one frame.

    • @asafun
      @asafun 27 дней назад +7

      We want to keep Stable Diffusion free.

    • @a.tevetoglu3366
      @a.tevetoglu3366 25 дней назад

      @@asafun even blender, which also is free, is an option within NVIDIA's onmiverse.

  • @mihirchitnis905
    @mihirchitnis905 29 дней назад

    Be honest who all thinks that the AI has ripped off green lantern for this super hero design.