Closed tlack closed 2 years ago
I've been finetuning an SD model and training seems to work OK.
But I'm stuck when merging the files back together for inference.
Which files in logs/ need to be combined to create a usable output model-merged.pt?
model-merged.pt
When I try python3 merge.py ../sdv14ema.ckpt logs/output015000.pt and use the resulting model-merged.pt for inference, I get this error:
python3 merge.py ../sdv14ema.ckpt logs/output015000.pt
$ python sample.py --model_path model-merged.pt --batch_size 3 --num_batches 3 --text "A Humvee in a ditch" ... lots of output trimmed ... Unexpected key(s) in state_dict: "epoch", "global_step", "pytorch-lightning_version", "state_dict", "callbacks", "lr_schedulers".
I have tried with the ema-0.9999-015000.pt and opts015000.pt files and neither seem to contain the right keys.
What am I doing wrong?
To answer my own question, turns out sample.py uses the output/model015000.pt file directly. I was mixing up the commands and their input.
My experiment seems to have worked.
Thanks for creating this great repo.
I've been finetuning an SD model and training seems to work OK.
But I'm stuck when merging the files back together for inference.
Which files in logs/ need to be combined to create a usable output
model-merged.pt
?When I try
python3 merge.py ../sdv14ema.ckpt logs/output015000.pt
and use the resultingmodel-merged.pt
for inference, I get this error:I have tried with the ema-0.9999-015000.pt and opts015000.pt files and neither seem to contain the right keys.
What am I doing wrong?