Please react to my videos: https://civarchive.com/user/ntc/images?sort=Most+Reactions
Trained for 2000 steps with:
#:0.08|~photo of balenciaga fashion, lips pursed, stern aloof look, profile picture, full torso and head in shot, fashion magazine photoshoot, fashionable hairstyle, cheekbones, hair fluffed and down
https://github.com/ntc-ai/conceptmod
Not Balenciaga, eh? Are you sure? You could be great, you know. It's all here in your head. And Balenciaga will help you on the way to greatness, there's no doubt about that. No?
Description
FAQ
Comments (4)
There is no evil.Only Balenciaga.
how did you train a lora without a dataset
It uses the network's learned representations to self tune. See comment here https://civitai.com/models/41927/gucci-trained-with-no-dataset
Also uses https://github.com/kohya-ss/sd-scripts/blob/main/networks/extract_lora_from_models.py for lora extraction
@ntc does that mean, it's tunning the base model like hypernetworks？and, how can we control the background and clothing like lora block weight? such as generate gif with nonchangable background
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.