SDXL

Ars Magnificat

Ars Magnificat - AI Model封面圖片
上傳時間
2025年2月4日 清晨5:27
使用數
3.7k
評論
非常好  (1)
取樣步數

20

取樣方式

Euler a

CFG Scale

6

負面

(lowres:1.2), (worst quality:1.4), (low quality:1.4), (bad anatomy:1.4), bad hands, multiple views, comic, jpeg artifacts, patreon logo, patreon username, web address, signature, watermark, text, logo, artist name, censored

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

Model Details. Initial/Final Merge.

Based on Illustrious-XL so please visit that page for a rundown of prompts, tags and other baked in features. Used Ars Aeterna as the base and added some other checkpoints/model into the mix. Also used several different block weights while testing.

The only prompt you ever need is this positive prompt: masterpiece, best quality, newest, absurdres, highres

Default negative Prompt:

(lowres:1.2), (worst quality:1.4), (low quality:1.4), (bad anatomy:1.4), bad hands, multiple views, comic, jpeg artifacts, patreon logo, patreon username, web address, signature, watermark, text, logo, artist name, censored

My Generation Settings:

•Sampler: Euler A

•Sampling Steps: 24 - 27

Upscaler Settings:

•4x-UltraSharp

•1.5x - 2x Upscale

•10 - 20 Hires steps (depends on your liking)

•Denoise: 0.4

Suggested Dimensions: 512x768, 768x512, 768x1280, 1280x768, 1024x1024, 960x540 or depends on your liking.

•CFG Scale: 4 - 6.5

Thank you

留言

由 Ars Magnificat 製作的作品