사용자 LoRA

XL
스타일

[Styles] Muses in Dark | Semi-real Style - Illustrious/PonyXL - Illustrious|NAI

#성숙한 여성#남성#초상화#실사풍#소녀#흑인 남성#근육남#중년남성
[Styles] Muses in Dark | Semi-real Style - Illustrious/PonyXL - Illustrious|NAI - AI Model 커버 이미지
업로드 날짜
2025. 12. 20. 오후 12:14
이용수
20.9k
리뷰
리뷰 없음
트리거 단어

muses_in_dark, inconsistent lighting, low light, realism, semi-realism

권한
  • 이미지 생성 및 공유 허용
  • 다른 사용자가 내 모델을 다운로드하도록 허용합니다
  • 생성된 이미지의 상업적 이용 허용

추천 LoRA

설명

Styles LoRA based on IllustriousXL and NoobAi, inspired by the way I visualized characters from chatbots, visual novels, and choice-based games. This LORA tend to handle semi-real artstyle.Using FallenIncursio's PaSanctuary/Incursio's Meme Diffusion model will get the more realistic result while other Pony, Illustrious and NAI will remain anime stylesRecommended weight and settings:0.7 - 1.0 / 0.3 - 1.0 (v4)Steps: 24 - 36Sampler: Euler aCFG Scale: 4Version 4 Test:Triggered Prompt: muses_in_darkExtended Prompt:dark theme, low light, realistic, inconsistent lighting,realism, semi-realism (v3-v4 only)Note: Be aware! Mixing too much LORAs may cause derailment on the main style of the model and LORA itself.Recommended Settings for Advanced Usage:To achieve the best quality and distinct artistic styles, I recommend the following configurations. These settings utilize "anti-burn" tools to allow for higher CFG scales without degrading the image.I do not recommend using DPM++ samplers with Karras, as this combination often causes artifacts or distorted results.1. ComfyUI ConfigurationPrerequisite: Install the Skimmed_CFG node by Extraltodeus, This node prevents image "burn" at high CFG scales.Choose one node: 'Skimmed CFG'; 'Skimmed CFG - replace'; 'Skimmed CFG - linear interpolation'; 'Skimmed CFG - linear interpolation dual scales'Skimming Scale: 4/6Main CFG Scale: 8/10/12Steps: 24 - 36Sampler: Euler ancestralSchedule Type: Exponential, Normal, Align Your Steps.2. A1111 / ForgeUI ConfigurationPrerequisite: Use Dynamic Thresholding by mcmonkeyprojects. (Note: This is a built-in feature in ForgeUI, but must be installed as an extension in A1111.)General Generation Settings:Steps: 24 - 36Sampler: Euler aSchedule Type: Exponential/Polyexponential, Normal, Align Your Steps.Main CFG Scale: 8/10/12Dynamic Thresholding Settings:Click on Enabled in Dynamic Thresholding's tabMimic Scale: 4/6Threshold Percentile: 0.96 ~ 0.999 (never set it to 1)Mimic Mode: Constant/Linear Down/Cosine Down/Power Down (your choice)Mimic Scale Min: 1~3CFG Mode: Constant/Linear Down/Cosine Down/Power Down (your choice)CFG Scale Min: 1~4Sched Val: 1Everything else we can set either like this:To further enhance image quality, consider using ADetailer and the Ultimate SD Upscale extension. Note that Ultimate SD Upscale is the only exception where DPM++ samplers are recommended.If you love my works, please review them with images and consider tipping me some buzz. This would be my great motivation to release more Lora

Not mine comes from : https://civitai.com/models/1300603?modelVersionId=2502921

댓글