Update on 25 Mar 2025:

A Civitai moderator had set the setting of this LoRA to "Depicts an actual person: YES" on 22 Feb 2025. This resulted in the NSFW images, including my own, being taken down, due to violating the Terms of Services with making NSFW images using models that can reproduce the likeness of a real person. I am unable to change the setting myself as it is "Locked by moderator".

I got in touch with Civitai team who reviewed the case and got back to me stating:

This model cannot be used on the site’s generator because some of its outputs have been shown to resemble a real-life actress, especially when paired with iconic costumes or outfits associated with that individual. Even if the model wasn’t intentionally trained to replicate a specific likeness, the results are “close enough” to raise concerns about potential misuse or unintended replication of a public figure’s identity. Out of caution and respect for likeness rights, we’ve restricted it from generator use.

Apparently an AI model trained on 2D fan art of a character counts as producing the likeness of a real person. *shrugs* I did get 500 buzz refunded to me though, so I'm personally not complaining about this to be honest 😅

Wow, this LoRA turned out really good! Usually for my LoRA training, what I would do is download multiple epochs, test them in a divide-and-conquer algorithm-like sort of way, and try to find the least bad one. This one, nope, download the latest epoch, try generating an image, and it gives me a perfect-looking one on the very first try!

In addition, this LoRA is almost exceptionally good at generating "holding helmet" images, because for some reason there is a lot of fanart of her with her helmet removed and holding it lololol

Would greatly appreciate it if you could read this before posting! https://civarchive.com/articles/7060/look-both-ways-before-you-crosspost

Notes:

1. There is only one image of "from behind" (and it's of a toy figure lol), so it might not be accurate. From my personal testing, I find that adding "black bodysuit" prompt helps for accuracy since the back is mostly black

2. Likewise if leggings is not accurate when generating "from below" images, "black leggings" prompt helps

3. Can't generate accurate boots from below (particularly the shoe soles, which are meant to be black but keeps appearing as silver). Seems like some of the images in my training data, including photos of the toy figure and some fanart, have entirely silver boots, whereas the actual boots have black soles. Where can I find close-up pictures of her boots though hmmmmmm...?

4. Weapon doesn't look accurate at all LOL. There's only one image of it in the training data set, and I don't really care about it either way lololol

5. All of the "helmet removed, no headwear" images in the training data set are of ponytails, so if AI automatically generates a ponytail without being prompted, helps to add "ponytail" to negative prompt

Prompts:

go-on_silver, silver bodysuit, silver skirt, silver belt, silver gloves, shiny clothes

boots, silver footwear

dagger, holding weapon

helmet, wearing helmet

helmet, helmet removed, no headwear, unworn helmet, holding helmet

helmet removed, no headwear