Thank you

[Hololeon]

I just wanted to say thanks for making this, which is something I've been wanting for A LONG time. My workflow usually consists of 3 passes to generate each image, and for that I made a huge maze of dozens of nodes because the prompt for each pass is slightly different, and I wanted to type the same things as few times as possible, so automating this process took many many hours and nodes.

Sometimes I wanted to trigger a lora only on the 1st pass, but not the 2nd. Sometimes it was the opposite. The 3rd pass is tile-based, so sometimes I wanted to add a prefix to each tile's prompt as well as an embedding, sometimes not. I always use a single positive and negative embedding, but it's only valid for Illustrious-based checkpoints, not realism ones, so I had to account for that as well. So on and so forth and before I knew it, I found myself with dozens of nodes that I even get lost in occasionally.

This pack achieves the same things with 90% fewer nodes, and thank you again for having a non-bloat philosophy. Custom nodes like this always have things like pulling words from external .txt files and randomization features and other things I don't use.

[Lex-DRL]

You're welcome 🤗

The exact same purpose for this node was in my mind when I coded it. And it was there for more than a year. The only reason I didn't do it sooner is bc I didn't have any spare time to finally learn coding nodes for ComfyUI. The actual python part of this node is EXTREMELY simple (this is basically a helloworld code). But those most basic things are usually the ones that cause the most QoL improvement if done right... or the most friction if done wrong.