Hyperparameters and steps to sudden convergence
#9
by
brycegoh
- opened
Hi Diffuser team, I am attempting to train my own controlnet and was wondering if your team has any tips for training a sdxl controlnet?
Given that your team seem to use a different script from the documented one, it seems like you use the EDM formulation.
Would appreciate opinions on:
- How does the EDM formulation help the training process training?
- What hyperparameters did your team use (I see that batch size and LR is documented but what about gradient accumulation, etc)?
- Did your team notice any patterns for sudden convergence?
Would appreciate some assistance and advise! Thanks!