






You should use the trigger word hkwarrior
The LoRA weight I have been using is 0.85-1, but feel free to try and experiment!
I have used ComfyUI when generated pictures and the settings im using are:
Sampler: dpmpp_2m
Scheduler: Karras
Steps: 30
For A1111 enjoyers, I would use:
Sampler: DPM++ 2M Karras
Steps: 36
Example prompts used:
Prompt:"core_9, score_8_up, score_7_up, score_6_up, score_5_up, score_4_up, (a fullbody shot of a orange fantasy (robot:1.3) Samurai, holdin a blue glowing katana:1.2) hkwarrior"
Negative prompt:"text, watermark, low quality, worst quality, bad compostion, poor, low effort, child, childish, young, (3d, photo, hyperrealistic, rough sketch:1.1), censored, (derpibooru_p_low), furry, source_furry, source_comic, (realistic:1.3), helmet, female, girl, woman"
First image is with my LoRA and second is without my LoRA, same prompt and model.
Example prompts used flux:
"(A white Oni with blue smoke, holding up his sword in the air, wearing silver armor and kimono. Detailed illustration with a dynamic background in the style of fantasy art. A digital painting concept design showing a close up shot with ultra high resolution and high detail in sharp focus. An intricate studio photo shoot with highly detailed sharp focus and high quality:1.2), hkwarrior"
First image is with lora and second is without the lora, same model and prompt:
1. Quyền đối với các mô hình được đăng lại thuộc về người sáng tạo ban đầu.
2. Người sáng tạo gốc muốn xác nhận mô hình vui lòng liên hệ nhân viên SeaArt AI qua kênh chính thức. Nhấp để xác nhận
