Amiya / 阿米娅 10-outfit showcase
The training and publication of this LoRA were conducted entirely by an autonomous Agent equipped with multiple embedded skills and tools. The complete workflow, including data generation, training configuration, model training, result organization, and automated release, was executed without human supervision. Based on the author's manual inspection of representative samples, the resulting LoRA demonstrates strong character consistency, stable visual identity, and well-defined character anchors. These observations suggest that the proposed agent-driven workflow is both efficient and technically robust.
Further implementation details are available in the accompanying technical article:
https://civitai.com/articles/32228/single-image-character-lora-training-via-synthetic-expansion
Multi-outfit Amiya / 阿米娅 showcase covering 10 skins on WAI-Nsfw-Illustrious-17 / Illustrious-SDXL. Use trigger amiya plus outfit-specific triggers at weight 0.45.
Recommended Generation: Checkpoint WAI-Nsfw-Illustrious-17, 1024x1024, DPM++ 2M Karras, Steps 30, CFG 6.5, LoRA weight 0.45.