Yinzo/sd-webui-Lora-queue-helper

Enhancement? The ability to use multiple Loras for even more dynamic results?

DooDip opened this issue · 3 comments

DooDip commented

I'm not sure how hard it would be to implement, but the idea of being able to run multiple Loras from the list at a time would be pretty cool. I am not a programmer and I am new to AI, so I am unsure how the process works in the software. I've used multiple Loras in my prompts and it can create some pretty cool styles and effects.

Thanks!

Yinzo commented

I am not sure exactly what you want.
let's say we have four Loras: A, B, C, and D.
Do you want to use these 4 Loras to generate one image, or you want to create four separate images, each for A, B, C, and D?

The former can be achieved just by using a normal prompt containing all four Loras. The latter is what this script currently does.

Therefore, I am unclear about your request. Could you please provide more information or examples?

DooDip commented

4 Loras to create 1 image. I realize this is possible using a normal prompt, but running random Loras in a batch would be pretty cool.

Yinzo commented

Well maybe checkout dynamic-prompts and wildcards, they can help you using random prompt in a file, maybe it can also use on lora.