jp-j1a v1.0

SD 1.5 TextualInversion
Download

jp-j1-a 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 brunette.

  • 25 images trained for 2500 steps.

  • 12 vectors per token.

  • Learning rate of .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!