theloraprodigy presents
Seethru LoRA
LoRA trained with theloraprodigy's high quality captioned dataset.
Use 2:3 ratio for best results (e.g. 512x768).
❤️Like this model? Support my work by buying me a coffee ☕
Commissions also available!
How to use this LoRA model? (AUTOMATIC1111)
Drop the LoRA into the "stable-diffusion-webui/models/Lora" folder and start AUTOMATIC1111.
Write your prompt as usual in e.g. text2img or img2img but also include the "seethru" keyword.
Example: "woman posing with seethru clothing".
On the right, under the "Generate" button, click on the button in the center that has an image icon and that says "Show / Hide Extra Networks" when hovering with the mouse on it.
A new section under the prompt will appear, go to the Lora tab there and select this model
Training models requires expensive hardware and is consuming a lot of time. All of my models are free. You can support my work by buying me a coffee ☕
Description
Initial release
FAQ
Comments (4)
I'm guessing this normalizes the boob-size and shape output?
IE does it play well with other boob loras?
It was trained with regularisation images, however I didn't test it with other loras
To an extent it does, yes. Other small boob loras sometimes work if they come before this lora in the prompt, but frequently you will see the breasts get real big.
I've been looking how I can do the reverse thing. I mean, I have an original photo from a model that is already wearing a seethru shirt, and I want remove the shirt keeping the original body that appears thru the shirt.