Updated: Aug 10, 2026
styleDownload
1 variant available
bf16 SafeTensor
anima_AASML6_lora-step00007500.safetensors
BF16, good balance • 132.35 MB
Verified: 4 days ago

3640 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
8700 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
9K0 1 2 3 4 5 6 7 8 9K
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
Krea2:
推荐 LoRA 强度:0.65
Recommended LoRA weight: 0.65
推荐步数:8-10
Recommended sampling steps: 8–10
推荐 CFG:1
Recommended CFG scale: 1
推荐采样器: Euler
Recommended samplers: Euler
Anima:
推荐 LoRA 强度:1
Recommended LoRA strength: 1
推荐步数:30–40
Recommended steps: 30–40
推荐 CFG:5
Recommended CFG: 5
推荐采样器:Euler A
Recommended samplers: Euler A
这是一个混合画风 LoRA,融合并参考了多位画师的风格特征。
AASML6 整体偏向 明快、精致的二次元 CG 插画风格,强调柔润的人物塑造、清晰明亮的眼睛、细腻的头发高光、平滑渐变与鲜明色彩,尤其适合现代服装、幻想服饰、泳装以及人物海报与上半身特写。
目前版本仍可能在复杂姿势、手部、远景与强光照场景中出现一定不稳定,后续会继续优化泛化能力、人体稳定性与光影控制。
This is a mixed art style LoRA that blends and references stylistic features from multiple artists.
AASML6 focuses on a bright and refined anime CG illustration style, featuring soft character rendering, clear expressive eyes, detailed hair highlights, smooth gradients, and vivid colors. It works especially well with modern outfits, fantasy costumes, swimsuits, character posters, and upper-body portraits.
The current version may still show some instability in complex poses, hands, distant characters, or strong lighting conditions, and future updates will continue improving generalization, anatomy, and lighting control.
触发词:AASML6
触发词并非必须添加,但如果希望更稳定地触发画风,推荐使用该触发词。
Trigger word: AASML6
The trigger word is not strictly required, but it is recommended if you want to activate the style more consistently.
如果在使用过程中遇到任何问题,欢迎随时向我反馈。你的反馈也会帮助我继续完善后续版本。非常感谢大家的支持。
If you encounter any issues while using this LoRA, please feel free to let me know. Your feedback will also help me improve future versions. Thank you very much for your support.
