Back
Similar todos
change training credit logic: 1) when starting training new model, remove 1 training credit; 2) if fails, add back 1 credit, 3) on training retry remove 1 training credit
See similar todos

No replies yet

try train model and see if failing changes credits properly
See similar todos

No replies yet

count currently training models to avoid race condition where user has 1 training credit, then trains 1 model, but before the model is finished, trains another one, and then only when they finish they decrement the training credits
See similar todos

No replies yet

finish saving of training data
See similar todos

No replies yet

test training model learning rates
See similar todos

No replies yet

fail with new hands trained model
See similar todos

No replies yet

clean up model training code so I can make it a function to retry failed model trainings KISS DRY
See similar todos

No replies yet

Model training
See similar todos

No replies yet

add self trained class data
See similar todos

No replies yet

see intermediary results of my custom training model
See similar todos

No replies yet

make link to auto select model after training is done
See similar todos

No replies yet

import training ID and training Docker output ZIP for models already trained so we can modify existing trained models to add ControlNet etc.
See similar todos

No replies yet

add dating photos to standard templates run after model is trained
See similar todos

No replies yet

prune my CKPT custom model after 12 hours of training
See similar todos

No replies yet

let people download training data for non-Flux models
See similar todos

No replies yet

train my own model for
See similar todos

No replies yet

test auto gen photos after training new model
See similar todos

No replies yet

Obtained trained TensorFlow model
See similar todos

No replies yet

start training my own interior model
See similar todos

No replies yet

add new base models to train on
See similar todos

No replies yet