Recommendations (v2.0 - Anima)
Trigger: luna_dota, helmet, crescent ornament, shoulder armor, blue and black bodysuit. Weight: 1.0 (0.8–1.2).
Settings: 30 steps, CFG 4, er_sde / simple, 896×1152 or 1024×1024. Add signature, watermark, text, artist name to the negative. More tips are in the version notes.
XL version of LORA, trained on model generation results Luna (Dota 2)
Recomendations:
Lora weight: 0.5 (0.4-0.7)
Description
Anima Base v1.0 version, trained with ai-toolkit on 25 images.
Trigger: luna_dota. For the in-game look add helmet, crescent ornament, shoulder armor, blue and black bodysuit: the helmet and armor were tagged in the captions, so the trigger alone gives only the blue bodysuit.
Weight: 1.0 (0.8–1.2). At 0.6 the helmet closes into a visor; base Anima draws a generic blue knight (see the weight comparison).
Tips:
holding glaivegives her glaive.Cowboy shot and closer keep her face open. In wide shots and with
glowingthe helmet sometimes closes into a visor or a black mask covers the lower face;looking at viewerhelps.dynamic posetends to turn her back to the viewer; usefrom front, looking at viewer.Works at 896×1152 and 1024×1024.
Tested with: 30 steps, CFG 4, er_sde / simple.
Negative: worst quality, low quality, score_1, score_2, score_3, blurry, jpeg artifacts, sepia, signature, watermark, text, artist name (add nsfw, nude, topless for SFW). The dataset has artist signatures; the signature tags keep the corners clean.
DiT-only LoRA (no text encoder weights), rank 16 / alpha 16, 2000 steps, lr 2e-5.





