jp-j3a-1250 is the latest in my attempt to learn TI's.

• She is not a real person and does not reproduce any of the training images exactly, rather the look of a cute brunette.

• 22 images trained for 2250 steps.

• 12 vectors per token.

• I used the following learning rate .004

• Batch size of 1 with 1 gradient accumulation step.

I'd appreciate any feedback you may have and would love to see what you come up with. Thanks and enjoy!