hunyuan_V1

This time I used more than 150 pictures as training set, and did not filter them. I was curious about what results hunyuanvideo would give me. Although the results disappointed me a little, they were okay.

Flux_V1

This is still a difficult face to train and need to reduce img for training.

SD1.5

I just try to cut out the crap I make and publish a better version.