RuntimeError: Expected all tensors to be on the same device

Viewing 2 reply threads
  • Author
    Posts
    • February 25, 2024 at 6:30 am #12633
      AvatarPhaisit Pruektharathikul
      Participant

        Hello Guys,

        I try to create AnimateDiff by using uploaded video.

        I am running python notebook StableDiffusionUI_ngrok_sagiodev.ipynb on Google Colab with T4 GPU.

         

        Somehow, I get the following error.

        RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cpu and cuda:0! (when checking argument for argument weight in method wrapper_CUDA___slow_conv2d_forward)

         

        This happen right after the program call ControlNet .

        2024-02-25 11:20:17,236 – ControlNet – INFO – ControlNet Hooked – Time = 144.2927029132843 0% 0/30 [00:00<?, ?it/s] *** Error completing request

         

        Thanks for your help 🙂

      • February 25, 2024 at 9:00 am #12638
        AvatarAndrew
        Keymaster

          Hi, I tested the notebook with T4 and it seems to work fine. I noticed AnimateDiff is finicky (a known issue).

          This is what I did:

          1. Run notebook with AnimateDiff and ControlNet extensions only

          2. Select Dreamshaper 8 model (SD 1.5)

          3. Enter prompt (“a beautiful girl”)

          4. Upload a video in AnimateDiff (video I used)

          5. Enable AnimateDiff

          6. Enable ContorlNet

          7. Select Openpose Full in controlnet

          8. Generate (Didn’t work. Error message but not the same as yours)

          9. Disable and enable AnimateDiff

          10. Generate (Worked)

          So you can try toggling AnimateDiff to see if that resolves the issue.

        • February 26, 2024 at 10:55 am #12689
          AvatarPhaisit Pruektharathikul
          Participant

            Hello Andrew,

            Thank you very much. It seems works now.

            I will try with different model.

            Phaisit

        • Author
          Posts
        Viewing 2 reply threads
        • You must be logged in to reply to this topic.