用戶LoRA

XL
角色

Zamasu [3 Versions • Dragon Ball]

#男性#七龍珠#七龍珠超#褐色皮膚男性#肌肉男#熟男
Zamasu [3 Versions • Dragon Ball] - AI Model封面圖片
上傳時間
2024年11月26日 下午2:01
使用數
689
評論
暫無評論
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

推薦 LoRA

描述

A model of Zamasu, trained over 101 images for 1024 using AAA as a training modelZamasu:Trigger word: ZambaseasuLooks tags: colored skin, green skin, mohawk, white hair, grey eyes, pointy ears, potara earrings, single earring, green earringClothes tags: purple shirt, long sleeves, shirt under tunic, black tunic, shoulder pads, yellow trim, gold button, blue sash, baggy pants, blue pants, boots, white footwearWeight: 1 to 0.5 (0.7 is recommended)Fusion Zamasu:Trigger word: ZafmionasuLooks tags: colored skin, green skin, spiked hair, white hair, super saiyan, grey eyes, pointy ears, potara earrings, green earringsClothes tags: black shirt, long sleeves, shirt under tunic, grey tunic, shoulder pads, red trim, gold button, red sash, baggy pants, black pants, boots, white footwearWeight: 1 to 0.5 (0.7 is recommended)Fusion Zamasu Half Corrupted:Trigger word: ZamhalfasuLooks tags: multicolored skin, two-tone skin, colored skin, green skin, purple skin, heterochromia, grey eyes, red eyes, mismatched sclera, colored sclera, ring, spiked hair, short hair, white hair, parted bangs, pointy ears, potara earrings, green earringsClothes tags: black shirt, long sleeves, shirt under tunic, grey tunic, shoulder pads, red trim, gold button, red sash, baggy pants, black pants, boots, white footwearWeight: 1 to 0.5 (0.8 is recommended)Additional information:Webui I useAAA Anime VAE SDXL v1_4 as VAESampling method: Euler aSchedule type I set it to automaticSampling steps I go 20-304x-Ultrasharp as an UpscalerHires steps I go 8-15 (I don't always use hires fix)Denoising strength I go 0.4Upscale by 1.2 to 1.5 depending on the starting image dimensionsDetail Daemon at default settingsImagine dimensions vary depending on what I'm trying to doI use 5 CFG Scale and CFG Scale Fix set at 9uddetailer for faces, I use mediapipe_face_mesh set Dilation to 50 and Y offset to 30 to get the full faceI do all of my lora training here, if you can spare any buzz I would appreciate it

留言