You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
To clarify. I am setting a list of "checkpoint-x, checkpoint-y, checkpoint-x, etc". I want to test each model against my list of preferred samplers.
It seems to me, that the way I have set it up, the script defaults to loading a different model for each sampler before moving on to the next - when it would obviously be quicker to load one model, run all of the samplers on it, then move to the next model. That way it's not loading a new model every time a new grid image is made.
Does that make sense? ie: Load: Checkpoint-x | then apply: euler, euler a, DPM++ SDE,etc instead of Load: Checkpoint-x | then Apply:Euler Load: Checkpoint-y | then Apply:Euler Load: Checkpoint-z | then Apply:Euler
Is it as simple as placing the model list in the first axis? Or is there a trick I am missing?
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
Uh oh!
There was an error while loading. Please reload this page.
-
To clarify. I am setting a list of "checkpoint-x, checkpoint-y, checkpoint-x, etc". I want to test each model against my list of preferred samplers.
It seems to me, that the way I have set it up, the script defaults to loading a different model for each sampler before moving on to the next - when it would obviously be quicker to load one model, run all of the samplers on it, then move to the next model. That way it's not loading a new model every time a new grid image is made.
Does that make sense? ie:
Load: Checkpoint-x | then apply: euler, euler a, DPM++ SDE,etc
instead of
Load: Checkpoint-x | then Apply:Euler
Load: Checkpoint-y | then Apply:Euler
Load: Checkpoint-z | then Apply:Euler
Is it as simple as placing the model list in the first axis? Or is there a trick I am missing?
Beta Was this translation helpful? Give feedback.
All reactions