Mizumizuni - Style LoRA - NoobAI
- 上傳時間
- 2026年6月3日 晚上8:44
- 使用數
- 1.3k
- 評論
- 暫無評論
- 觸發詞
mizumizuni
- 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
Please, check the description, there is a little bit of useful information.Inеtroduction:This LoRA is supposed to represent Mizumizuni's artstyle.Please, be sure to use the same positive and negative quality prompt for better result.Compatibility:Humans: greatAnthros: greatPonies: greatMultiple characters: greatCharacter LoRAs; greatUnique characters: greatRecommendations:1.0 emphasisTrigger: mizumizuniClip Skip 1CFG 5NoobAI 1.0 V-Pred for generationsmasterpiece, best quality, highres, uncensoredin positivesworst aesthetic, worst quality, low quality, bad quality, lowres, bar censor, censored in negatives+ bright, colorful, saturated, red theme, blue theme for CIvitAI generationsCFG Rescale 0.3 - 0.4 (if you're using v-pred version)Use anything else in negatives only if you want to avoid or remove something from the image. For example, you don't want to see doors - "door" in negative. Style will look much better without garbage in negative prompt. Just try it.Credits:Trained on NoobAI 1.0, Dataset of 100 pictures (v1), 40 epochs, Clip Skip - 1Really big thanks to:Mizumizuni for beautiful artworkSome good folks from Discord serverYou, for reading, downloading, liking and reviewing this LoRA