Using automatic, I am embedding training, using text file descriptors per image, but consistently I am being made female.
The text descriptions are all accurate. What am I missing here? I’ve tried it with multiple models.
Using automatic, I am embedding training, using text file descriptors per image, but consistently I am being made female.
The text descriptions are all accurate. What am I missing here? I’ve tried it with multiple models.
Maybe try to use the “Gender slider” embeddings : https://civitai.com/models/89709?modelVersionId=95959 I got the same issue with a LORA of a short haired woman who turned into a man one I trained it… Using those embeddings worked well for me ! (The result were close to the generated images with GS-DeMasculate-neg, but she was trained from generated picture so I can’t confirm if it will keep your face correctly…)