jp-Tut1a-2000 is the latest in my attempt to learn TI's. I actually created this one to show a couple of folks on here my workflow. You can view the link for the video at the bottom.

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

• 14 images trained for 2000 steps.

• 14 vectors per token.

• I used the a learning rate of 0.004

• 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!

Here is the link to the video I did showing my workflow: