用戶LoRA

DiT.1DiT.2
角色

Samus Aran / サムス・アラン | Metroid / メトロイド | DiT V1/V2

#薩姆斯·阿蘭

#銀河戰士

#零式戰衣

Samus Aran / サムス・アラン | Metroid / メトロイド | DiT V1/V2 - AI Model cover image
上傳時間
2026年4月27日 上午9:41
使用數
685
返利
93,337
評論
暫無評論
觸發詞

Samus Aran, Metroid, blue eyes, blonde hair, long hair, ponytail, red hairband, Zero suit, large breasts,

許可權
  • 允許圖片生成與分享
  • 允許使用者下載此模型
  • 允許生成圖片用於商業用途

描述

Trained on Tsubaki, 13 images.

Images I used for training were Samus in the Zero Suit. You can prompt her to have the black dot below her left side lip. I used some fanarts with it in the learning material, so she will sometimes generate with it without prompting. I didn't use trigger words for her eyes; she has blue eyes with a little bit of green. I was worried it would be inconsistent.

I use Euler A. 28 steps. Because the results are pretty good, I think you can generate 3 images in parallel, and you will still be fine. Unlike SDXL, DiT is pretty consistent from my initial experience. Of course, if you demand a lot of detail, then maybe go cheap first.

I use 3, 4.5 and 6CFG. 0.7 Rescale CFG, same as every DiT V1 LoRAs I use.

Thumbnail model: Tsubaki

評論