This model can generate and edit characters to make a ahegao face. ๐คช๐๐
It is trained on a large varied dataset with 168 images of females, that does not contain artificial data. โ๐คโ
To start open with: "Only change her facial expression to: (prompt here)".
See example images with workflows attached, just drag'n'drop in comfyui.
Triggers: ๐ฅ๐ฅ๐ฅ
both of her eyes look at each other, ๐๏ธ
she sticks her tongue out of her mouth, ๐
her mouth is wide open for a oral examination, ๐ฎ
her uvula visible in the back of her throat, ๐ฅต
she looks at her own nose, ๐ (not trained but greatly recommended as it increases the succes-rate exponentially).
saliva, ๐ง
(Do not add the emoji's to your prompts hahaha).
Notes: ๐๐๐
There is no artificial data in the dataset.
Dataset uses a combination of both tags and natural language captioning.
There are no 2D or 3D images in the dataset.
Only trained on images of adult 18+ females.
It does not produce real people, as the dataset has a lot of variation, and is not trained on names.
All preview images uploaded by me are generated using AI, without real people again.
If during edit the pose changes too much, prompt: keep the background and pose the same.
Slightly understands etnicity, so you can say a french woman, or japanese, korean, brazilian, as I did add some basic country and region tags to the captions.
Known limitations: ๐คท๐คท๐คท
The lora does not work on pictures of animals,
The lora does not work on eyes with sclera lenses,
The lora has a hard time with very low and high angles.
The input image often needs to be at a portrait angle, with a maximum rotation of about 45 degrees in all directions.
For the mouth to open up wide, a facial-focus base-image with a raised chin has a much higher succesrate.
It does not create explicit nudity / R-rated / R-18 type content.
๐งโโ๏ธ๐
Use this AI model responsibly, and do not upload any prohibited content or prompts. Follow the rules of the TOS and laws. Violations can be reported and can get your account banned. This model was not developed in affiliation with Boogu, and is a purely a hobby project.
โกโกโก
Hit the like button on the model page, and on my images if you enjoy what you see! I'm all out of buzz, and every bit helps so I can train more models! And if you download the lora, posting a image to the page grants me โก50 buzz per user, and also saving my images to your gallery helps me out bigtime! So I would appreciate it alot if you could spare a few seconds! Donations are welcome too! <3
Description
version 1, uses a combination of natural language triggers and tokens.



















