Download
1 variant available
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
A style trained on the artist Inma, most well known as one of two artists for the Sakura visual novels from Winged Cloud.
The LoRA has 0 trigger words, and using a strength of 1.0 should be just fine.
Versions
Anima
Overhauled dataset & retagged from scratch. There is a slight bias towards dark-skinned females having tatts due to the contents of the dataset. I recommend negative prompting tribal tattoo to solve this at the moment.
I have not tested this version with artist tags being mixed in or other artist loras being included, results may vary.
Illustrious
v2
Updated training with the Anima dataset. There isn't a lot of testing on this version, any feedback is appreciated for any potential future updates if they're needed.
v1
Original version of the LoRA. Too strong atm, heavily biased towards the tattoos regardless of prompting. You can look at the preview images and decide if it's something for you, but I don't recommend it personally anymore :P