Part of my facial expressions series. All of these LoRAs are designed to mesh well with each other and have low impact on your image framing.
Straightforward, but a little subtle. It's trained low to work well with other aspects of expressions (some examples of mixes in the gallery), I recommend increasing the weight of pleading in the prompt over increasing the LoRA weight.
Newly updated to reduce the default-horniness and framing/context bias like arms-over-head positioning. Am very happy with how the adjustments turned out, will be taking a pass with some of my other LoRAs to do the same, so let me know if there are other biases you're still seeing.
Recommended starting prompts:
<subject>, pleading eyes
<subject>, pleading expression
Description
Significantly less horny and easier to get SFW photos by default. Generally less context injection with subjects and photo framing
FAQ
Comments (7)
Great work! thanks a lot❤️
As suggestions, how about :
- drunk
- asleep
- shy
- gagging
facial expression?
And thanks for the feedback. If you're so inclined please do rate and leave any examples or feedback about what works well for you and what could be better!
@thegipper yes, that are fitting examples
Greetings. I mostly make images of men being spanked, with expressions from Dazed, to pleading to alarmed. And guys being Milked and teased, How applicable is this to masculine faces??
Thanks
Most of my facial expression LoRA's work pretty well with men, and most have some male faces in the training data, but it definitely depends a lot on the base model and. ADetailer works very well on SD1.5 if you are having issues with it impacting the image too much.
Thank you for the info. Much Appreciated!!!
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.