This model was trained on SD1.5. This model is not that great, as the output pictures only look 75% like her. Finding good quality photos of just her face was a little difficult. I will revisit this one in the future.
I suggest using CFG 4-7 and anything above 15 sampling steps.
Model used: realisticVisionV13_v13
The updated version of this model generates images that better resemble HeyImBee. However, it's possible that the model is over trained, so I might need to revisit it again in the future.
1. Права на репостнутые модели принадлежат оригинальным создателям.
2. Для подтверждения авторства модели создателям следует обратиться к сотрудникам SeaArt AI через официальные каналы. Нажмите, чтобы подтвердить
