Sign In

Light Armor | Conan Exiles Enhanced | Anima

0

Updated: Sep 29, 2026

clothingheavy armorconan exiles

Not loaded

Download

1 variant available

bf16 SafeTensor

LightArmor_Anima.safetensors

BF16, good balance • 87.6 MB

Verified:

Type
LoRA
Stats

51

0

Generation

Not loaded

Reviews
Published

Sep 27, 2026

Base Model

Anima

Training
Steps: 1,000
Epochs: 10
Usage Tips
Strength: 0.8
Hash
AutoV2
53BB7399EF
Trigger Words
1girl, solo, l1ght4rm0r, navy headwrap, navy cross-strap bodice, brown wrapped waist sash, navy ragged skirt, thigh slit, navy fingerless gauntlets, brown wrapped shin guards, brown leather sandals
1girl, solo, l1ght4rm0r, missing headwear, black eyes, black eyeshadow, long hair, black hair, navy cross-strap bodice, brown wrapped waist sash, navy ragged skirt, thigh slit, navy fingerless gauntlets, brown wrapped shin guards, brown leather sandals
default creator card background decoration
Reactions - 11951

12K

Followers - 482

482

Likes - 1433

1.4K

Acolyte Badge

License:

Anima

The Anima Model is licensed by CircleStone Labs LLC. Copyright CircleStone Labs LLC. IN NO EVENT SHALL CIRCLESTONE LABS LLC BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH USE OF THIS MODEL.

Built on NVIDIA Cosmos

00281-[2550401059] -- [None] -- [oneObsessionAnima_v40] -- [832 x 1216].png

If you like my work and would like to leave a review, go for it. Motivation is motivation. I do this for fun mainly.


This LoRA is part of a Collection!


Model Information

A Clothing LoRA from Conan Exiles Enhanced. The armor set is called Light Armor, it's one of the original vanilla armor sets

This is the Anima version. The Illustrious XL version is over here.


Helpful Information

Sample images were not meticulously hand-crafted one by one in Forge Neo and may not be the best representation of what the LoRA can do. I used semi-decent wildcards, and generated several batches of images across multiple checkpoints and picked the best 20.

Checkpoints I typically use


Metadata is not scrubbed so feel free to reference the sample images for whatever you please.


Training Notes

  • Illustrious outfits are trained at 1500 steps (50 images, 15 epochs, 6 repeats, 3 batch size)

  • Anima outfits are trained at 1000 steps (50 images, 10 epochs, 6 repeats, 3 batch size).

They get 1500 steps / 1000 steps respectively to look as good as they can at the final epoch, which I give you. For my screenshot workflow, see previous models. All outfits are female only and male variants will not be supported any time soon.

Load my safetensor into LoRA Metadata Viewer if you're curious about any settings. I don't use nasty stuff like AI Toolkit so the metadata should be there.


Prompt Usage

Here is everything you should know this LoRA, mainly things specific to the LoRA. The use of expressions, poses, angles, framing, background and the sort is your job.

I've provided the main prompt for each outfit. Refer to the other tags section and the additional prompts to the right panel for more info.

Light Armor (in-game preview)

1girl, solo, l1ght4rm0r, navy headwrap, navy cross-strap bodice, brown wrapped waist sash, navy ragged skirt, thigh slit, navy fingerless gauntlets, brown wrapped shin guards, brown leather sandals

Other Tags: medium breasts, pale skin, black eyes, black eyeshadow, long hair, black hair, missing headwear, grassy field, wildflowers, pine trees, rocky cliff, river, 1girl, solo, outdoors, 3d, game screenshot, realistic

Important Notes

  • The only tested LoRA strength range is 0.8 ~ 0.9, so I recommend that range. Lower is probably better than higher.

  • You will generate my character's hair and or face if you use certain tags from the other tags section above.

  • A lot of outfits have images with the headwear removed for variation, so if you want to try to remove a helmet, use missing headwear instead of the headwear tags. Might not work for circlets and similar.

  • Unless you're trying to reproduce the video game's style, do not prompt 3d, realistic, game screenshot when generating images. Slap those into your negative prompt, especially if you're going for anime.


Final Notes

Slapping this at the very end of my description(s) in an attempt not to annoy people as much.

1) I create content entirety for fun. I refuse to do this for money or to ask for money. I don't do commissions or anything of the sort. You can request things, but if I don't like it or care for it, you won't get a response.

2) If you are curious how I made something, just ask me. I don't mind sharing a dataset, training settings and the sort. I am a curious person. I'm not overly protective of my work and I am not worried about who does or does not jack off to it.