Meet Poppy, or rather jp-Poppy my latest in my attempt to create Textural Inversions.

• The name is random.

• Poppy is trained on 24 images.  I used the same 10 images from my jp-gingerv1-275 embedding and another 14 images of a different model to create this embedding. 

• She is not a real person, rather is created from a series of handpicked and manually captioned stock images of different models to create the redhead you see here.

• 24 images trained for 5000 steps.

• 10 vectors per token.

• I used the following progressive learning rate 0.05:10, 0.02:20, 0.01:60, 0.005:200, 0.002:500, 0.001:3000, 0.0005

• 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!