A lora born of my irritation with the lack of the AI's ability to output truly insane or traumatized looking characters. I recommend for most use cases you refer to the "constricted pupils" tag followed by a facial expression. Check out "About This Version" for more details.
Description
Entirely retrained on 100 images. Version notes are as follows:
No longer generates random mask parts and stuff. Should work better when blended with other LORAs now. I think.
May have a tendency to lower detail in the overall image, try to use mid to high weights.
Inpaint tested, need only highlight the eyes now.
With this version, there are only two trigger token: "constricted pupils, small pupils"
If you experience any issues with this version, I recommend downgrading or you can also try https://civitai.com/models/48579/yameroyandere
FAQ
Details
Files
Available On (2 platforms)
Same model published on other platforms. May have additional downloads or version variants.