SDXL

VXP_2.3 Experimental

上傳時間: 2024年11月2日下午4:18
使用數: 1.33m
評論: 非常好 (106)
取樣步數: 7
取樣方式: Euler a
CFG Scale: 1.6
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:2.0)
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

=== READ ME FIRST !! === suggested prompt : " ,(masterpiece:1.2), (best quality:1.2), (very aesthetic:1.2), (absurdres:1.2), (detailed background), (safe:1.2), newest, "

add "ai-generated" to obtain a 'add-detail' style image add "intricate details" to enhance fine details, add "safe" if it's generate too much lewd images 🤣

TAG order: "1boy/1girl, what character, from which series, everything else in random order" Put quality tags at the end of your prompts.

this is Hyper model, need to use with low CFG around 1.3~2.5, and low Euler A steps 5~7. I suggest a LOW CFG (like 1.3 ~ 1.8) for realistic style, and to rise around 1.5 ~ 2.5 for anime style.

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

VXP_2.3 Experimental

推薦 LoRA

描述

留言41

由 VXP_2.3 Experimental 製作的作品