KiranWells

To be honest, you can say the same about any large cloud provider. What happens if AWS, or Azure, or Google Cloud go down, or become terrible?

This is probably not the solution you are looking for, given your opinion of the company, but I wonder if using their 1.1.1.1 app (which acts as a mini VPN to a Cloudflare endpoint and changes your public IP) would fix that for you. The upside is it’s free, the downside is that it is a Cloudflare-run VPN.

I didn’t even know that, that’s pretty cool. I’ll have to try it later

The repository links to a list of examples, but the best way to learn is just to mess around with it. It is fairly intuitive to work with (especially if you have used another node-based UI before, like Blender).

The UI also has the ability to import/export your current setup (what I call a workflow) as a json file. If I get some time, I might share some of mine with a pastebin link or something.

The usefulness of ComfyUI is not just making one simple image. It is the ability to completely customize how that image is created.

For example, I have a workflow that generates a half-resolution preview image, then upscales the latent and puts it through two more sampling nodes. All three of the nodes have a different prompt input, with the focus slowly shifting to style instead of content.

I have also created a custom upscaling workflow, where the image is upscaled with normal upscaling, then re-encoded and put through just a few sampling steps, the re-encoded with a tiled VAE decoder (to save my VRAM). It creates much better results (more detail and control) than a direct ERSGAN upscale, and can even be put through ERSGAN afterward to get a super large image.

I would guess it’s one of three things:

1. You are using Windows instead of Linux for ROCm (I don’t know how much this affects performance, as I am only on Linux)
2. You are generating the batch all at the same time, instead of just doing multiple generations. This can lead to out-of-memory issues, as it is a larger image being generated.
3. You are not fully using the GPU. Does task manager say 100% utilization?

I’m also using ComfyUI. It just has the ability to do so much more than something like Automatic1111, even if it is missing a couple of features. For example, I have several workflows that do incremental changes to a photo, changing the prompt halfway through the generation, or even upscaling halfway through the generation.

I can’t really imagine going back, unless there is some killer feature that Comfy is missing.