SDXL

WAI-ANI-NSFW-PONYXL

WAI-ANI-NSFW-PONYXL - AI Model封面圖片
上傳時間
2024年9月28日 下午4:34
使用數
65.5k
評論
非常好  (9)
取樣步數

12

取樣方式

Euler a

CFG Scale

3.5

反向提示詞

score_6, score_5, score_4, source_cartoon, 3d, (censor),monochrome,blurry, lowres,watermark,

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

hyper12step released.about size Various combinations from 768x768 to 1360x1360 can produce good images.Recommended SettingSteps: 12CFG scale: 3.5Sampler: Euler aNot very necessary to use ADetailer correctionPositive Promptscore_9, score_8_up, score_7_up,source_anime,Negative Promptscore_6, score_5, score_4, source_cartoon, 3d, (censor),monochrome,blurry, lowres,watermark,PS.The example images use a size of 896x1192. no AD no Hires. fix__________________________________________________________________________________________________Version 8 released.v7->v8Added some training related to camera angles and backgrounds.Added more NSFW materials for additional training.Added some training for special effects.Optimization of overall composition logic.Fixed some minor issues.better eyes and hands.Recommended SettingSame as v7__________________________________________________________________________________________________Version 7v6->v7Fixed the issue where images appeared entirely covered with snowflakes.Revised the composition logic to be more suitable for general scenarios.Added new assets for backgrounds, mature women, and clothing.Ensured consistency with the previous model and further fixed the issue of blurry eyes in medium and long shots.Fixed some minor issues.V7 Recommended SettingSteps: 30CFG scale: 7Sampler: Euler a/DPM++ 2M KarrasADetailer face_yolov8n/s.pt use can fix eyesPositive Promptscore_9, score_8_up, score_7_up,source_anime,Negative Promptscore_6, score_5, score_4, source_cartoon, 3d, (censor),monochrome,blurry, lowres,watermark,________________________________________________________________________________________________Regarding the 8step model, it is a lightweight model that can generate images in as few as 8 steps. However, the quality and text comprehension will be relatively lower. If speed is not a major concern for you, it is recommended to continue using version 6.0.8 STEP SettingSteps: 8-12CFG scale: 3Sampler: Euler aADetailer face_yolov8n/s.pt use can fix eyesPositive Prompt and Negative Prompt same 6.0__________________________________________________________________________________________________6.0v5->v6 Change pointBetter Backgroundbetter eyesfix vaeRecommended SettingSteps: 30CFG scale: 7Sampler: Euler a/DPM++ 2M Karras(better eyes)ADetailer face_yolov8n/s.pt use can fix eyesPositive Promptscore_9, score_8_up, score_7_up,source_anime,BREAKNegative Promptscore_6, score_5, score_4, source_cartoon, 3d, (censor),monochrome,blurry, lowres,watermark,You can view the Supported art styles from https://civitai.com/articles/5715Thank you, DeepDark_Fantasy514, for providing the test.v4->v5 Change pointBetter BackgroundClothes details upAdd some mature femaleLittle better hands and eyesRecommended SettingSteps: 30CFG scale: 7Sampler: Euler aADetailer face_yolov8n/s.pt use can fix eyesPositive Promptscore_9, score_8_up, score_7_up,Negative Prompt (THX for snipsnapsnipsnap recommend )Base:score_6, score_5, score_4, source_cartoonOptional: source_furry, source_pony can bleaches skinelse: 3d, (censor),monochrome,blurry, lowres,watermark,I often use it now[score_6, score_5, score_4, source_cartoon,3d, (censor),monochrome,blurry, lowres,watermark, ]

留言

由 WAI-ANI-NSFW-PONYXL 製作的作品