My first attempt at LoRA.
This is a LoRA trained on pictures of men wearing hi-vis workwear, PVC suits, and rubber boots.
I recommend using a strength between 0.2 and 0.6.
It tends to disfigure faces, so stronger facial restoration is recommended.
Description
Same as 1.3 but trained on SDXL.
Notoriously large file size: I would be very grateful if someone could tell me why.
This is a LoRA trained on pictures of men wearing hi-vis workwear, PVC suits, and rubber boots.
I recommend using a strength between 0.2 and 0.6.
FAQ
Comments (1)
You need to lower your rank/dim. That is why it's so big. And having such a high rank is not good for simple concepts like clothes because it gives room for it to learn other things.
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.