Setting the weights to approximately 1.0 is recommended.
Anima
Please Use Anima BASE 1.0!
Activation tag : uminekocg
Anima Recommend Prompt
Positive: This digital illustration features natural form-following lighting, clear subject focus, coherent anatomy and body proportions, clean linework, controlled shading, and carefully refined details for a polished digital finish. year 2025, (masterpiece, best quality, good quality, highres, absurdres:1.1), uminekocg, (tag),Negative: This digital illustration has distorted anatomy, inconsistent body proportions, awkward posing, messy linework, poor shading control, and poorly resolved details. (worst quality, low quality, worst aesthetic:1.1), bad quality, score_1, score_2, score_3, lowres, bad anatomy, (artistic error:1.2), (bad:1.2), off-topic, multiple views, comic, extra digits, fewer digits, fewer, error, missing, jpeg artifacts, artist name, signature, twitter username, username, logo, watermark, scan, unfinished, variations, bad hands, ai-generated, anaglyph, chromatic aberration, bad perspective, multiple subjects, duplicate character, extra person, extra character, Characters supported by LoRA:
Beatrice
Virgilia
Bernkastel
Lambdadelta
Furudo Erika
Gauntlets
Shannon
Kanon
Ushiromiya Battler
Ushiromiya Ange
Ushiromiya Jessica
Ushiromiya George
Ushiromiya Maria
Ushiromiya Krauss
Ushiromiya Eva
Ushiromiya Rudolf
Ushiromiya Kyrie
Ushiromiya Rosa
Ushiromiya Natsuhi
Ushiromiya Lion
Willard H. Wright
Furfur
Zepar
Chiester00
Chiester410
Chiester45
Clair Vaux Bernardus
Eva Beatrice
Gaap
Lucifer
Leviathan
Satan
Belphegor
Mammon
Beelzebub
Asmodeus
Hachijou Tooya
NoobAI
When using the Civitai Generator, if you do not enable Enhanced Compatibility, abnormal results will be generated!
If the generated image looks strange, set the CFG Scale to between 5 and 7.
Please Use NoobAI V-Pred 1.0 Checkpoint!
Activation tag : uminekocg
Recommend Prompt
Positive: uminekocg, (tag), ((masterpiece, best quality, highres, absurdres)), (newest, very awa), Negative: worst quality, worst aesthetic, bad quality, bad anatomy, (artistic error), old, ealry, mammal, anthro, furry, feral, semi-anthro, lowres, (bad), off-topic, multiple views, comic, very displeasing, displeasing, chromatic aberration, (extra digits), fewer digits, fewer, text, error, missing, jpeg artifacts, artist name, signature, twitter username, username, watermark, scan, unfinished, [abstract], variations, (((bad hands))), ai-generated, Description
For this version, I added natural-language captions to the dataset and trained it using a customized LoKr. However, the example images I uploaded here were generated without natural-language prompts, so they do not fully demonstrate what this model is capable of. I believe that including natural-language descriptions in the prompt should allow you to achieve much better, potentially near-perfect results.



















