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
Sword Art Online Game CG Style LoRA for Anima 1.0
Fan-made style LoRA trained for Anima 1.0 to reproduce Sword Art Online game CG / anime cutscene look.
My first LoRA training on Anima 1.0. It may need some adjustments, feedback is welcome.
Even without anime coloring or anime screencap, the output already looks anime-styled, and the SAO-style eyes are noticeable.
Trigger
@saogcTraining info
Base model: Anima 1.0
Training tool: diffusion-pipe
Type: LoRA
Rank: 32
Epoch: 30
Trigger prefix used during training:
@saogc,Captions: Booru-style captions
Note
anime coloring and anime screencap are not required trigger words. They were only used in the comparison examples to create a closer non-LoRA baseline.