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
This Lora was trained using 93 images from the official Blue Archive series, season 1 with 12 episodes.
No fan art or AI-generated images were used; I wanted to keep the art style as close to the original as possible.
I checked all the images, removing the worst or blurry ones, as well as other characters in the background to avoid training errors.
Based on my quick tests, a weight of 0.8 is ideal, but it may vary from one checkpoint to another, so feel free to try different weights.
I did not use trigger words in the Lora, it was trained with a tag database, however I advise you to use
nonomi (blue archive),Here is my test setup (note that this isn't necessarily the most optimized) :
I'm using the official Anima Base checkpoint version 1.0 : Link.