jp-ds824a-v3-3300

jp-ds824a-v3-3300 is a textural inversion embedding created from 10 stock images featuring light hair, high cheekbones, and fair skin, all set against white backgrounds. This embedding does not resemble any actual person and was trained for 3,300 steps for this iteration.

I'm new to making these so I'd appreciate any feedback you have. Additionally please share images if you are so inclined. I'd love to see what you all come up with.

Model Details:

• Source: Stock Images

• Images: 10

• Background: White

• Training Steps: 3,300

Thanks for checking it out.