Download
1 variant available
License:
AnimaThe 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
触发词：kinrolstyle,
也可以不加任何触发词也能生效吧，可以尝试。
在anima模型中生成较为真实的照片风格，常态情况下lora强度建议为1，在搭配角色lora的情况下建议将lora的强度提高到1.5。
注意：只建议使用原版anima-base-v1.0模型使用,搭配其他风格类的模型也不是不可以风格会弱化，可以尝试提高到1.5的强度，但是我没试过。
建议使用双采样出图
第1个KSampler建议：步数:30 cfg:5.0 采样器:euler_ancestral 调度器:simple
第2个KSampler(Advanced)建议：步数:30 cfg:5.0 采样器:euler_ancestral 调度器:simple 开始步数:18。
---------Keywords: kinrolstyle,
You can also do it without any additional words. Feel free to give it a try yourself.To generate a more realistic photo-like style in the Anima model, the recommended LORA strength is 1 under normal circumstances. When using a character-specific LORA, it is recommended to increase the LORA strength to 1.5.
Note: This is only recommended for use with the original Anima-base-v1.0 model. While it is possible to use it with other style-based models, the style may be weakened. You can try increasing the strength to 1.5, but I haven’t tested this myself.
It is recommended to use dual sampling for image generation.
Recommended settings for the first KSampler: Steps: 30, CFG: 5.0, Sampler: euler_ancestral, Scheduler: simple.
Recommended settings for the second KSampler (Advanced): Steps: 30, CFG: 5.0, Sampler: euler_ancestral, Scheduler: simple, Start Steps: 18.