SDXL

Visionary Illustrious Mix V3

上傳時間: 2025年6月19日晚上9:11
使用數: 8.7k
評論: 非常好 (3)
取樣步數: 36
取樣方式: Euler a
CFG Scale: 5.46
負面: (bad quality:1, worst quality:1, bad eyes:1), lowres, jpeg artifacts, bad anatomy, bad hands, multiple views, signature, watermark, censored, ugly, messy
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

TRY(Retro anime style:1)(Realistic Anime Style:1)(Fantasy High-Detail Style:1)(Minimalist Line Art Style:1)(Monochrome Manga Style:1)(Pastel Color Anime Style:1)(Dark Horror Anime Style:1)V2I made a couple of LoRAs and used them to merge the checkpoint. I hope it didn’t make things worse!The showcase images were created at a resolution of 836x1216 and upscaled to a resolution of 1248x1824 using a second sampler.V1Hey! Since I’m planning to train some LoRAs in Illustrious, I’ve merged a checkpoint to start with LoRA merge.That works for me:CFG: 6-7SAMPLER: Euler a (DPM++ 2M Karras also works in some cases)STEPS: 50The showcase images have a resolution of 1248x1824

original: https://civitai.com/models/1037883/visionary-illustrious-mix

Visionary Illustrious Mix V3

推薦 LoRA

描述

留言

由 Visionary Illustrious Mix V3 製作的作品