i had problems to train this style with the original dataset, so i've trained it with many less images, and seem quite good, at least with neo forge 😅
Show more
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
test style with training images gereate with the Lilian lora
without lora: with lora:
compared with the Polly style has more soft colors, I'm new with style loras so i don't know if it's a good work or not 😅