| {"ModelId":129218,"ModelName":"MasterAnime","ModelDescription":"\u003Cp\u003EA model Made to give The best Anime realism outputs with a few parts of regular models.\u003C/p\u003E\u003Ch2 id=\u0022heading-93\u0022\u003EIMPORTANT: BF16 ONLY works on 30 series or newer Nvidia GPUs.\u003C/h2\u003E\u003Cp\u003EV3 has a more Anything V4 style but with a better flexibility and WAY better visuals (From what I got).\u003C/p\u003E\u003Cp\u003EV2 has great Locoris compatibility and I think it may be able to handle loras trained on Anylora and NAI.\u003C/p\u003E\u003Cp\u003ELink to The vae used: \u003Ca target=\u0022_blank\u0022 rel=\u0022ugc\u0022 href=\u0022https://civitai.com/models/129227?modelVersionId=141616\u0022\u003E-\u0026gt; Here \u0026lt;-\u003C/a\u003E\u003C/p\u003E\u003Cp\u003EV1 is a merge of 128~ Models (Using weight sum and normal calc mode)\u003C/p\u003E\u003Cp\u003EV2 is a Merge of 64 new models \u002B V1 and a couple test versions.\u003C/p\u003E\u003Cp\u003EV3 is basically a merge of V2 plus some newer models, I think about 64~ but it could be more.\u003C/p\u003E\u003Cp\u003EV4 is a merge of V3 plus some newer models\u003C/p\u003E\u003Cp\u003EV4.5 is a merge meant to replicate the base style of Anything V4.5 but with all around better prompting and anatomy \u003C/p\u003E\u003Cp\u003EV5 is basically just meant to expand on 4.5\u003C/p\u003E\u003Cp\u003EV6 is V5 but with 200\u002B new unused before models mixed in to attempt to get a better style and just be better all around.\u003C/p\u003E\u003Cp\u003ENote: The reason why these models have not been released is that I have not had time to make the showcase for the models\u003C/p\u003E\u003Ch1 id=\u0022heading-514\u0022\u003EHERE IS A BASIC GUIDE:\u003C/h1\u003E\u003Cp\u003EUse Adetailer, Use what ever settings you want; I suggest DPM\u002B\u002B 2M SDE Heun Karras and 38 steps. for upscaler, just any anime style upscaler will do.\u003C/p\u003E\u003Cp\u003EFor prompting here is a basic prompt which works:\u003C/p\u003E\u003Cpre\u003E\u003Ccode\u003E(masterpiece, highest quality, 8k, 16k, high quality, best quality:1.3, absurdres, highres, digital art, intricate), \u0026lt;lora:GoodHands-vanilla:1\u0026gt;\u003C/code\u003E\u003C/pre\u003E\u003Cp\u003Eand the negative:\u003C/p\u003E\u003Cpre\u003E\u003Ccode\u003E(worst quality:2),(low quality:2),(normal quality:2),lowres,((monochrome)),((grayscale)),watermark, blurred, bad face, child, shota, lolli, old, ugly, bad anatomy,(long body :1.3),(mutation, poorly drawn :1.2),(extra fingers:1.2), ( extra fingers, deformed hands), (poor quality, bad quality:1.35), \u0026lt;lora:neg4all_bdsqlsz_V3.5:1\u0026gt;, FastNegativeV2, EasyNegativeV2, NGH,\u003C/code\u003E\u003C/pre\u003E\u003Cp\u003ENote you will need the embeds \u002B Locoris if you want it too look really good... also you can add nsfw to the negative and it will try to not make nsfw stuff.\u003C/p\u003E","Nsfw":false,"Tags":["anime","female","realism","style","male","nsfw","sfw"],"ModelType":"Checkpoint","VersionId":173495,"VersionName":"V3","VersionDescription":"\u003Cp\u003EV3- LOL finally added\u003C/p\u003E","BaseModel":"SD 1.5","FileMetadata":{"fp":"bf16","size":"pruned","format":"SafeTensor"},"ImportedAt":"2023-10-11T08:36:10.8385269+00:00","Hashes":{"SHA256":"5B05F0120659D8DE7829AACE640C63DB9A587D4058C6A73FFBFEF2AEFEBE8BB7","CRC32":"BBEABF84","BLAKE3":"108954FDC1F7028D415B07A0D034A020B5A73BDEC5536D003413957E4CAFA35E"},"UserTitle":null,"ThumbnailImageUrl":null} |