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
FAQ
Comments (8)
Awesome 👍👍👍
Pee eyes. :)
What is the model you use for realistic showcase of your loras? gonna test that one out.
Epicphotogasm, mostly. Be sure to be sparing with your prompt words! It's pretty flexible when you don't overprompt but gets a little samey with words like 8k in there.
A bit sad that a facial expression LORA affects so much arm positioning... you have to fight the model for it not to automatically put both of the subject's hands behind their back.
Very strongly agree, and is definitely on the top of the list for fixing in the next version. Thanks for the feedback!
Updated version coming in tomorrow (I think). You should get a notification if you follow my account. Let me know if it works better for you.
Thanks again for sharing!
Inpainting is your friend :)
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.