Training using the Textual Inversion tools provided by https://github.com/AUTOMATIC1111/stable-diffusion-webui using an RTX 3070 with 8GB VRAM.
Redistribution of these embeddings is encouraged.

Training parameters:
- name : vgcatsaeris
- initialization text : *
- trained checkpoint: yiffy-e18.ckpt [50ad914b]
- number of vectors per token : 16
- learning rate : 0.005
- Trained as a subject (object) using a modified subject_filewords.txt template

Trained for 40,000 steps total.
Embeddings are provided at 500 step intervals.
Training image data and sources (where available) provided in the Dropbox folder, most images sourced from e621 and tagged accordingly.
Some images edited to fit 1:1 aspect and maintain a solo focus on Aeris alone. Text and signatures were also removed to benefit the training process (apologies to the original artists).

RECOMMENDED: vgcatsaeris-8000.pt
Use by installing to an embeddings folder of your stable-diffusion-webui-master installing.
You can install multiple embeddings, if you wish to use only one you can rename it however you wish.
The more training an embed has had, the less prominent yiffy-e18's own qualities and characteristics become.
Be aware that this embedding will use 16 of your 75 allotted tokens, limiting the other tokens you may use.
Also be ware that this embedding is not effective when using with any other Stable Diffusion model: use yiffy-e18 for best results.

Prompt for example x/y plots:

<vgcatsaeris-8000>, anthro, (solo), 1:1, ((hyper breasts)), (huge breasts), big areola, nipples, pussy, vagina, ((embarrassed)), (((sex))), (vaginal penetration), (watercolor) drawing by greg rutkowski and sssonic2 and joelasko
Negative prompt: background, text, speech, speech bubble, dialogue, blue fur,  (((mutation))), (((deformed))), ((ugly)), blurry, ((bad anatomy)) (((disfigured))), (((deformed))), blurry ((deviantart)) (((tiling))) poorly drawn
Steps: 50, Sampler: Euler a, CFG scale: 7.5, Seed: 300887396, Size: 512x512