LORA trained on 25 images captioned with tags. Trigger word used in training is cum on face, but it works well with more descriptive captions e.g. she has cum on her face.
Works better on close up images, as a result of limited training data.
Description
FAQ
Comments (9)
works wonderfully, nice.
keep doing this!
Great, one question: is this model faster than CogVideo img a video? I have a 12GB 3060 so I don't know if I can use it.
I think you might be looking for this https://civitai.com/models/1048302/hunyuanvideo-12gb-vram-workflow?modelVersionId=1176230
How is the LORA, with diffusion pipe or other? formed, what are the necessary PC capacities?
you can use diffuser pipe on mimic PC online tutorial on youtube
well we're sunk, this is it.
Is there a template/ workflow that can be used on Runpod?
some vids with a workflow would be nice