SDXL

VXP_XL v2.2

VXP_XL v2.2 - AI Model封面圖片
上傳時間
2024年8月9日 下午3:38
使用數
111k
評論
非常好  (46)
取樣步數

25

取樣方式

Euler a

CFG Scale

4

負面

(nsfw, lowres, (bad), text, error, fewer, extra, missing, (worst quality), (low quality),jpeg artifacts, watermark, unfinished, displeasing, oldest, early, chromatic aberration, signature, extra digits, artistic error, username, scan, abstract, bad anatomy, bad hands, bad feet, bad hand, bad hands, bad finger, bad fingers, extra finger, extra fingers, split finger, split fingers, extra digits, fused arms, fused hands:1.6)

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

==== READ ME FIRST !!!! (attention v1.5 work with new quality prompts!) ====

suggested prompt : "(masterpiece:1.2), (best quality:1.2), (very aesthetic:1.2), (absurdres:1.2), (detailed background),newest, " add "ai-generated" to obtain a 'add-detail' style image add "intricate details" to enhance fine details,

TAG order: "1boy/1girl, what character, from which series, everything else in random order"

Put quality tags at the end of your prompts.

suggested CFG is around 3.5~7, and Euler A steps 20~30. for anime style I suggest high value around 4.5 ~ 7. for realistic style a low value around 3.5 ~ 4.5

character list: https://huggingface.co/spaces/cagliostrolab/animagine-xl-3.1/blob/main/wildcard/characterfull.txt

shared on civitai : https://civitai.com/models/311157

留言12