Andrew

Forum Replies Created

Viewing 15 posts - 61 through 75 (of 239 total)
  • Author
    Posts
  • in reply to: Say hi and introduce yourself! #16057
    AndrewAndrew
    Keymaster

      Welcome!

      in reply to: Deforum and Forge #16031
      AndrewAndrew
      Keymaster

        Like many A1111 extensions, deforum is not compatible with forge. Even the forge version of deforum is broken. You can only use it on A1111.

        in reply to: Include rsources needed in course intro #16030
        AndrewAndrew
        Keymaster

          Agreed. I will add the relevant info to the course.

          in reply to: Say hi and introduce yourself! #16029
          AndrewAndrew
          Keymaster

            Welcome Melanie! I’m happy that you are happy 😊

            in reply to: Say hi and introduce yourself! #15976
            AndrewAndrew
            Keymaster

              Welcome Jared! You come at the right time. Local AI videos have started to mature.

              in reply to: Getting Colab Automatic1111 Working for the first time #15910
              AndrewAndrew
              Keymaster

                Yes, this could be.

                in reply to: 30 Days Using Stable Diffusion Art with Scholar Monthly #15896
                AndrewAndrew
                Keymaster

                  Thanks for the feedback! It’s great that you find good value in the membership.

                  I aim to spread the knowledge while getting somewhat compensated (and justified) for my time. I’m glad to find a solution that works both ways.

                  in reply to: Local Install vs GPU / Render Farms (online GPU) #15895
                  AndrewAndrew
                  Keymaster

                    I agree it’s not entirely straightforward. I usually deal with memory issues as they arise. This can be done using a more memory-efficient version of the model (fp8, fp4), using a smaller image size, and unloading models from memory, etc.

                    in reply to: Getting Colab Automatic1111 Working for the first time #15894
                    AndrewAndrew
                    Keymaster

                      The HiRes fix function often results in memory issues. I am not sure what’s wrong with the implementation. Maybe a flux workflow with increasing batch size or image size is a better way to test.

                      in reply to: Stable diffusion video obsessed #15886
                      AndrewAndrew
                      Keymaster

                        Welcome, Jessica! Thank you for sharing your beautiful work. It is a great remix of “What is life”!

                        I’m sorry I didn’t notice your message awaiting my moderation.

                        AndrewAndrew
                        Keymaster

                          This is a good suggestion. Instructions for A1111 and Forge should be interchangeable. I will probably add new ComfyUI ones.

                          in reply to: Getting Colab Automatic1111 Working for the first time #15881
                          AndrewAndrew
                          Keymaster

                            Thanks for the suggestions.

                            When I wrote the course, I tried to keep it agnostic to how to use A1111 (local/colab/online service). So I didn’t write much about instructions specific to the Colab notebook. I will add them to lessons that require additional extensions.

                            in reply to: Local Install vs GPU / Render Farms (online GPU) #15880
                            AndrewAndrew
                            Keymaster

                              Several factors determine the relationship between model size and the required VRAM.

                              1. Not all model parts need to be in the memory simultaneously. For example, The CLIP model can be unloaded after processing the prompt, and the VAE is required only after sampling.  So, the VRAM required is smaller than the model size.
                              2. A model’s size is measured by the number of parameters. A parameter can be represented in different precisions in a GPU, e.g., FP32 (high), FP16, and FP8 (low). The lower the precision, the smaller the size of a GPU, but the quality may be reduced.

                              Optimizations like these enable fixing large models in limited VRAMs.

                               

                               

                              in reply to: Local Install vs GPU / Render Farms (online GPU) #15820
                              AndrewAndrew
                              Keymaster

                                I use all cloud services in my day job. There’s no hardware maintenance and no noise when running a heavy job. I am fortunate enough that I was allowed to keep the VM running 24/7. I won’t enjoy it as much if I need to shut it down every day.

                                Some online services, like Think Diffusion, auto-shutdown after a specific amount of time. This is not a bad way to control costs.

                                in reply to: 24gb VRAM vs Architecture series #15819
                                AndrewAndrew
                                Keymaster

                                  If you are on the fence, using an online service is not a bad idea. It is probably cheaper than owning one if you are a casual user.

                                Viewing 15 posts - 61 through 75 (of 239 total)