Hunyuan clip load error

Viewing 4 reply threads
  • Author
    Posts
    • #17682
      David Rawlins
      Participant

        Hi Andrew, I’m attempting the Hunyuan image to video workflow and have installed llama_llama3_vision in the clip_vision folder in Colab. But I get this error from the clip vision loader. I’ve not pasted the whole error code but can if helpful. Hope you can help

         

        ComfyUI Error Report

        Error Details

        • Node ID: 82
        • Node Type: CLIPVisionLoader
        • Exception Type: TypeError
        • Exception Message: ‘NoneType’ object is not callable
      • #17683
        David Rawlins
        Participant

          The same thing happens with the Wan 2.1 workflow

        • #17684
          AndrewAndrew
          Keymaster

            It seems that the model is not loaded.

            I just added the models to the notebook. Select Hunyuan or Wan_2_1 to load the model.

            If it still doesn’t work, posting the error in console helps.

          • #17685
            David Rawlins
            Participant

              Thanks, Andrew, that’s fixed it, though I can’t work out why as I’m sure the models were in the right folders. Anyway, saves me running out of disk space!

            • #17686
              David Rawlins
              Participant

                I see Comfy manager is reporting: [clip vision] There is a compatibility bug with Load CLIP Vision in the latest ComfyUI, which is not the stable version.

                Not sure if that means I need to update to the latest version of Comfy or not. I’ll report back

            Viewing 4 reply threads
            • You must be logged in to reply to this topic.