Slider LoRa to finely control the attire of individuals in generated images, allowing seamless transitions from light summer swimwear to cozy winter coats.
What does it do?
Lets the user set the amount and quality of clothing on a person using a slider.
How to use it?
Add to prompt just like any other LoRa, but adjust the weight from negative -4 to +4 to achieve roughly the following results:
Set LoRa weight to produce:
Warm winter parkas and coats: above 2
Warm outside clothing: 1 to 2
Spring/Autumn standard clothing: 0 to 1
Light summer outdoors or indoors clothing: 0 to -1
Swimwear-bikini: -1 to -2
Can produce NSFW images without any clothing below -2
Tested on v1.5, RealisticVision
Trained using: https://github.com/ostris/ai-toolkit
Acknowledgments:
I am grateful to Ostris for their outstanding AI Toolkit, which served as the foundation and inspiration for this Slider LoRa. Kindly acknowledge and credit Ostris for their invaluable contributions to the AI community.
This is my first slider LoRa any feedback, suggestion or criticism is appreciated.
If you like my work and would like to support me, you can buy me a coffee!
Description
FAQ
Comments (4)
有点意思
Can I use this with Fooocus ? I am trying few things already but I see nothing changes.. positive or negative does not impact.. Thanks
I havent used Fooocus before, I have tested this out in Comfy and AUTO1111. But if you are able to load a LORA, you should be able to see the difference. Try more extreme weights like -4 or +4 to test it out! Wish you luck!
Last time I checked foocus is not supporting models for sd1.5 only xl so probably there is now way to use it there.

