A total of 11 Apostles are supported, and their Civvies have been trained as well.
Try generating your own images using the prompts from my example images!
For Kommy, adding white skin to the prompt will generate her with her original skin tone.
Setting the weights to approximately 1.0 is recommended.
Please Use Anima Aesthetic v1.1 Checkpoint!
Activation tag : @trickcalcg
Anima Recommend Prompt
Positive: This digital illustration features natural form-following lighting, clear subject focus, clean linework, controlled shading, and carefully refined details for a polished digital finish. year 2025, (highres, absurdres:1.1), @trickcalcg, (chibi, chibi only:2), blush stickers, (tag),
Negative: This digital illustration has 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:1.2), off-topic, multiple views, comic, 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, long legs, NoobAI
When using the Civitai Generator, if you do not enable Enhanced Compatibility, abnormal results will be generated!
This LoRA is heavily influenced by quality tags.
Do not use resolution tags like absurdres and highres, as they have a particularly strong effect.
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 : trickcalcg
Recommend Prompt
Positive: trickcalcg, (chibi, chibi only), blush stickers, ((4 fingers)), (tag), masterpiece, best quality, newest, very awaNegative: worst quality, worst aesthetic, bad quality, 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
This LoRA has been converted from the existing DoRA to LoKR, and with mixed fp32 and bf16 training on an RTX 5090, it can now reproduce the art style in even higher quality while maintaining the previous image dataset.







