Closed rafstahelin closed 3 weeks ago
Can you describe what you find confusing about LoRA scheduling? It works the exact same way as prompt scheduling.
At every step, the prompt is "expanded" to include only the parts that are active during that step, and if a LoRA is mentioned in the prompt, it gets applied during that step.
can I barge in?
I want to put fire
in prompt after 0.2 progress
I usually did it using [:fire:0.2]
in A1111, but it seems to not working here, fire already influenced the result from start. what's the prompt should be?
also what is specified range in a red [INT:dog:cat:0.2,0.8:0.05]
?
@PurplefinNeptuna That would be just [fire:0.2]
. I guess I could make the other form work too for consistency but I don't like touching the lark grammar because changing it can sometimes cause weird side-effects.
The range in INT
is the steps between which the interpolation happens.
I've also done [_:fire:0.2]
Describe what's missing A more visual guide for entry level people. I am really having a hard time understanding how scheduling lora's work here. More specific breakdowns in the readme, with particular examples would really help. Not expecting youtube tutorial but maybe from concrete examples with image and values in the workspace would be super welcome. Very keen to learn
Additional context Add any other context or screenshots about the feature request here.