SDXL

DarkFunIXL

DarkFunIXL - AI Model封面圖片
上傳時間
2025年2月28日 凌晨4:49
使用數
1.6k
評論
非常好  (1)
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

This is a merge of the checkpoint and LoRAs used by DarkFun for his storytelling.V2 - Alexx E. EditionSo, new stories, new checkpoint! This one is more of an experiment, i don't expect anyone to use it intensively, it does not behave well regarding following prompt :DThe base checkpoint used by DarkFun for the Alexx E. story is Illustrij V7, but i wanted to try some Block Merge, so i used as base here a "special" merge between this checkpoint and VauxzGrandMerge:BASE, MID: 0.5IN and OUT blocks from Illustrij: 0,2,4,7,8IN and OUT blocks from VauxzGrandMerge: 1,3,5,6On top of this, i added the LoRA used at their respective weight:reij-detaILer: 0.3Incase_New_IllustV3: 0.25hand 5.5: 0.55illustrious_flat_color_v2: 0.8For this one, Euler A + SGM Uniform is normally the way to go :DV1 - Tuli EditionPart one of the story - Part two of the story - Part three of the story - I am looking forward reading/seeing more!Usage:Sampler: Euler A - Scheduler: Beta (other choices displayed here)CFG: 5.5Steps: 36Clip skip: 1Prompt quality tags: "HDR,best quality,detailed,realistic"Negative prompt: "bad quality,low detail,child,kid,lolita,worst quality, bad anatomy, bad hands,anime,lowres,plastic skin"Update: I have created and uploaded a dataset of 1300 "1girl" in a cyberpunk setting using this checkpoint. It is available hereMy next step will be probably first to create an embedding for Tuli, the OC presented in the story, and maybe a LoRA, trained specifically on this model :DNB: Beware of ADetailer with this model/settings. A complex prompt can't be used as-is for face inpainting! Shorten it to only the face features, use low denoising strength, match the number of steps.Recipe:iLustMix v1.0 (base checkpoint)Teeth XL 0.45Hand XL v5.5 0.45MoriiMee Gothic Niji Style Ilustrious Test 0.55Darker Than Dark Illustrious 0.55NoobAI-XL Detailer V-Pred1_V1 0.55

留言

由 DarkFunIXL 製作的作品

1