Andrew

Forum Replies Created

Viewing 15 posts - 181 through 195 (of 233 total)
  • Author
    Posts
  • in reply to: What are the optimal object lora settings? #11495
    AndrewAndrew
    Keymaster

      Unfortunately I don’t have experience on this. I would change the obvious targets like learning rate and number of epochs one at at time to see if they move the needle.

      in reply to: Say hi and introduce yourself! #11490
      AndrewAndrew
      Keymaster

        Hi Rafael!

        There are two membership tiers when you sign up: Plus and Scoloar.

        Plus memberhsip gives you access to members-only workflow and resources, such as model training tools and curated comfyui workflows.

        Scholar membership includes everything in Plus, and adds the online courses on A1111 and ComfyUI.

        You can see a comparison here:

        https://stable-diffusion-art.com/member/

        You can switch the membership plan in the Accounts page.

        Regarding this forum, I am no wordpress programmer. This is the forum tool that my membership plugin recommends. It was in bad shape after I installed it. I needed to do a lot of work to make it usable LOL. But the price is right (Free).

         

        in reply to: Greetings from Japan #11489
        AndrewAndrew
        Keymaster

          Welcome Iain!

          in reply to: Hi there #11488
          AndrewAndrew
          Keymaster

            It would help if you start a new thread in an appropriate forum.

            in reply to: What are the optimal object lora settings? #11487
            AndrewAndrew
            Keymaster

              It would set you up for success if you find a token that generates objects similar to what you want to train. As always, good training images in a setting similar to what you are going to generate helps.

              in reply to: Merging Models for SDXL #11486
              AndrewAndrew
              Keymaster

                Yes, it needs to be an SDXL model. You can only merge two models with the same architecture.

                in reply to: Learning materials order for ComfyUI (and more) #11322
                AndrewAndrew
                Keymaster

                  Welcome!

                  If you want to be thorough and have a solid foundation, you can go through the Stable Diffusion levels 1 to 4 first. Then you can tackle the comfyui courses.

                  If you want to get there fast, you can take the comfyui course directly. I don’t repeat the content in the SD courses but link to relevant articles.

                  The workflows are not ordered in the skill level. You would need to judge which ones you want to study at your level.

                  The comyfui workflow on the resources page is a good resources to study a particular module in isolation. The comfyui workflows out there usually have massive number of nodes, making them difficult to study and reuse.

                  AndrewAndrew
                  Keymaster

                    Sorry for the late response. The message went into the moderation mailbox.

                    For comfyui, it is common to see the installation outdated and causing problems. You should update comfyui itself and all nodes by following this:

                    https://stable-diffusion-art.com/animate-partial-image-comfyui/#Step_0_Load_the_ComfyUI_workflow

                    If it still doesn’t work, the workflow may need to be revised. Let me know, and I will look into it.

                    Regarding things not working when changing the prompt, it is common for Stable Diffusion workflows to need some tweaking when changing the prompt. Not all prompts work with a particular workflow. Just like creating art with other mediums, it needs experimentation. The workflow is an example of what is possible. It serves as a good starting point but not a universal solution.

                     

                     

                     

                    in reply to: Say hi and introduce yourself! #11284
                    AndrewAndrew
                    Keymaster

                      Welcome Scott!

                      in reply to: Another Hello! #11275
                      AndrewAndrew
                      Keymaster

                        welcome victor!

                        in reply to: Say hi and introduce yourself! #11129
                        AndrewAndrew
                        Keymaster

                          Installing the comfy portable in Windows is the easiest way. You download, unzip and run. You can try that route if you haven’t already.

                          Comfyui is a bit harder to learn but it also has many pre-made video workflow available.

                          in reply to: Error while installing pytorch on mac #11059
                          AndrewAndrew
                          Keymaster

                            you can try using python 3.10

                            in reply to: Hi there #11032
                            AndrewAndrew
                            Keymaster

                              4090 will save you time in resolving memory issues. Don’t hesitate to ask any questions!

                              in reply to: Child Generator (ComfyUI) not working #10934
                              AndrewAndrew
                              Keymaster

                                Hi, have you installed the clip vision checkpoint file and put it in the model folder? Are you able to select it?

                                in reply to: Realistic Vision v5.1 inpainting #10862
                                AndrewAndrew
                                Keymaster

                                  Hi, you can use the “Install models from URL” section in the notebook.

                                  Put in Model_from_URL:

                                  https://huggingface.co/SG161222/Realistic_Vision_V5.1_noVAE/resolve/main/Realistic_Vision_V5.1-inpainting.safetensors?download=true

                                  Before starting the notebook.

                                  I will add the model to the list later.

                                Viewing 15 posts - 181 through 195 (of 233 total)