Character LoRA of a woman, african ethnicity. This the first LoRA I managed to train properly based on generated images.
Here is an example of a prompt:4nit4, woman, running in the park, wearing a blue tracksuit
This LoRA was initially created to see how the consistency between images during seedlocking worked, and if training a LoRA with it would leave enough flexibility for the model to follow the prompt. I find it to be working well.
The dataset creation process:
I first generated a prompt that would define the character exhaustively, locked the seed and generated about 200 images with various actions / lighting / clothes.
I then do a pass of face recognition on the generated images to keep as much consistency as possible for the input images and select about 20 that are used for training.