Stable Diffusion LoRA profile based on Martina from the Youtube channel Nerdforge.
This was a quick profile - literally the quickest i've ever made, 40 pictures in half an hour, I plan on making a v.2.
Place it in "stable-diffusion-webui\extensions\sd-webui-additional-networks\models\lora" folder in Automatic1111 WebUI root folder.
Made using kohya-ss.
In txt2img, under "Additional Networks", select "Enable" and under Model 1 select "Martina" and assign a weight around 0.7 (the weight required can change depending on the checkpoint being used - feel free to experiment!). In the prompt text window use "Martina" within your prompt to generate images.
Embed has been trained on Stable Diffusion 1.5 model.
Description
FAQ
Comments (5)
did you get the missing finger tho?
Would you care to share your training settings? I can't get LORA training on people to work properly while I get good results with the same images and tags on TIs.
why
this may be useful for this lora as of late: https://civitai.com/models/40396?modelVersionId=45686
They don't seem to work very well together, so it needs multiple passes
Cough Cough PEYTON LIST 1986 COUGH COUGH