physical violence

weapon violence

wide hips

revealing clothes

thick thighs

downblouse

convenient censoring

huge breasts

pg-13

corpses

suggestive

oral invitation

pg13

sexy

sexual situations

male nudity

disturbing

male swimwear or underwear

female swimwear or underwear

partial nudity

undressed

female nudity

breasts out

exposed female nipple

breast out

lingerie

male underwear

hair over breasts

female swimwear

gigantic breasts

no panties

graphic violence or gore

covered nipples

huge butt

strapless leotard

sitting on face

emaciated bodies

one breast out

nsfw

female underwear

nude

graphic male nudity

adult toys

illustrated explicit nudity

nudity

graphic female nudity

hentai

futanari

porn

sexual intent

genitals

peeing

vore

oral

sexual activity

anal

blowjob

dildo riding

incest

hanging

hate symbols

nazi party

white supremacy

diapers

scat

self injury

hate speech

urine

extremist

child on child

latex clothing

swimwear

bukkake

fellatio

cumshot

implied fellatio

eat_cum

cumdrip

cum in pussy

cum on face

after fellatio

cum on hair

cum on body

cum on tongue

cum on hands

cum in mouth

triple fellatio

autofellatio

fucked silly

cum on pussy

本合集已停止更新，因为这里上传的都是我初期寻找混合规律的产物。This collection has ceased to be updated, as everything uploaded here is a product of my initial search for blending rules

这个模型还有混合扩展的可能性，建议作为混合素材使用。作为混合模型的中间阶段的产物它看着有点粗糙。This model still has the potential for mixed extension, and it is recommended to be used as mixed material. As a product of the intermediate stage of the mixed model, it looks a bit rough.LORA比模型提示词重要，而模型质量提示词比模型本身更重要。显然模型本身就是最低等的，而比模型本身还低等的就只有模型混合时的发现。lora The prompt word of the model is more important than the model itself, and the quality prompt word of the model is even more important than the model itself. Obviously, the model is the lowest existence, and the only thing lower than the model itself is the discovery when the model is mixed.{ "sd_merge_recipe": { "type": "sd-webui-supermerger", "weights_alpha": null, "weights_beta": null, "weights_alpha_orig": null, "weights_beta_orig": null, "model_a": "3dd3a5a2318c2d3000c960365dc03cc76409aa27621bb15fffbd2e4ef7bc15c4", "model_b": "f280a64d22a21970b3448657622219f069b54a955f0fc7e0e68c2113367cb2ec", "model_c": "3dd3a5a2318c2d3000c960365dc03cc76409aa27621bb15fffbd2e4ef7bc15c4", "base_alpha": 0.5, "base_beta": 0.02, "mode": "Add difference", "mbw": false, "elemental_merge": "", "calcmode": "trainDifference", "Off": [ "" ] }, "format": "pt", "sd_merge_models": { "3dd3a5a2318c2d3000c960365dc03cc76409aa27621bb15fffbd2e4ef7bc15c4": { "name": "6-27解析-10.fp16", "legacy_hash": "4210260a" }, "f280a64d22a21970b3448657622219f069b54a955f0fc7e0e68c2113367cb2ec": { "name": "检测_6-25解析-60.fp16", "legacy_hash": "5041375d" } } }

Material6-27-20Stage2

{ "format": "pt", "sd_merge_models": { "35efe875735163d14d3939bb08fb70203f4f6704693901c96bbefa5f4b673a2b": { "name": "1混合_3高适用性_画风元素_2.5D风格厚涂画风模型1", "legacy_hash": "5776ebdb" }, "032ee69d6697a1736d736e7a1a38fc89cfa261aff19565e83af175a49b71cafa": { "name": "1混合_3高适用性_基础元素_4-19画片组合测试22222.fp16", "legacy_hash": "da06e9e4" }, "290a1c4836da21ee4978ef428a73cd4db3492dc62ee89ca4ac8f8e4b0610bed7": { "name": "提纯测试_4-19画片组合测试10.fp16", "legacy_hash": "6f00cbbf" } }, "sd_merge_recipe": { "type": "sd-webui-supermerger", "weights_alpha": null, "weights_beta": null, "weights_alpha_orig": null, "weights_beta_orig": null, "model_a": "35efe875735163d14d3939bb08fb70203f4f6704693901c96bbefa5f4b673a2b", "model_b": "032ee69d6697a1736d736e7a1a38fc89cfa261aff19565e83af175a49b71cafa", "model_c": "290a1c4836da21ee4978ef428a73cd4db3492dc62ee89ca4ac8f8e4b0610bed7", "base_alpha": 0.735, "base_beta": 0.02, "mode": "Add difference", "mbw": false, "elemental_merge": "", "calcmode": "trainDifference", "Off": [ "" ] } }{ "sd_merge_recipe": { "type": "sd-webui-supermerger", "weights_alpha": null, "weights_beta": null, "weights_alpha_orig": null, "weights_beta_orig": null, "model_a": "eb5b00f31b8da09c51b99177ac6c7794a05c4fdedc091c118286ce0719fbccde", "model_b": "6c909887a3981b9331b8f24a616d7fe0aa1d2e938e80d28737a1e52f2bcd9d9b", "model_c": "eb5b00f31b8da09c51b99177ac6c7794a05c4fdedc091c118286ce0719fbccde", "base_alpha": 0.534, "base_beta": 0.02, "mode": "Add difference", "mbw": false, "elemental_merge": "", "calcmode": "trainDifference", "Off": [ "" ] }, "format": "pt", "sd_merge_models": { "eb5b00f31b8da09c51b99177ac6c7794a05c4fdedc091c118286ce0719fbccde": { "name": "6-24解析-20.fp16", "legacy_hash": "4d10fff3" }, "6c909887a3981b9331b8f24a616d7fe0aa1d2e938e80d28737a1e52f2bcd9d9b": { "name": "1混合_3高适用性_画风元素_2.5D艳丽色彩", "legacy_hash": "1f4a4985" } } }{ "sd_merge_recipe": { "type": "sd-webui-supermerger", "weights_alpha": null, "weights_beta": null, "weights_alpha_orig": null, "weights_beta_orig": null, "model_a": "13fe1ce0968332ef877ecc48ba37e957e328246079bde389ae6d995423131c45", "model_b": "54708ba711744a39e6903f6244597801e29d7c5d74f9007c79bbf1c5bfdb1321", "model_c": "13fe1ce0968332ef877ecc48ba37e957e328246079bde389ae6d995423131c45", "base_alpha": 0.366, "base_beta": 0.02, "mode": "Add difference", "mbw": false, "elemental_merge": "", "calcmode": "trainDifference", "Off": [ "" ] }, "sd_merge_models": { "13fe1ce0968332ef877ecc48ba37e957e328246079bde389ae6d995423131c45": { "name": "6-24解析-21.fp16", "legacy_hash": "4a25fb62" }, "54708ba711744a39e6903f6244597801e29d7c5d74f9007c79bbf1c5bfdb1321": { "name": "新素材_基础元素_画风融合测试6-23-32.fp16", "legacy_hash": "7776d3de" } }, "format": "pt" }简述混合行为：第一步在画风模型中添加基准模型进行固定，第二步添加下一个画风，第三步再次添加基准模型固定The first step is to add a reference model to the style model for fixation, the second step is to add the next style, and the third step is to add the reference model again for fixation

Model splicing 6-24-022

{ "sd_merge_recipe": { "type": "sd-webui-supermerger", "weights_alpha": null, "weights_beta": null, "weights_alpha_orig": null, "weights_beta_orig": null, "model_a": "623689fbb0fd3a3a7a7c7a75f3d987e40c52983b1e8e50bc0f87e945582b6814", "model_b": "a0498f4122a48f831814385491ab2f23477e4fbd21b2f672dd0bcd32e9590792", "model_c": "623689fbb0fd3a3a7a7c7a75f3d987e40c52983b1e8e50bc0f87e945582b6814", "base_alpha": 0.575, "base_beta": 0.02, "mode": "Add difference", "mbw": false, "elemental_merge": "", "calcmode": "trainDifference", "Off": [ "" ] }, "format": "pt", "sd_merge_models": { "623689fbb0fd3a3a7a7c7a75f3d987e40c52983b1e8e50bc0f87e945582b6814": { "name": "1混合_2中适应性_画风元素_kmMIXByproduct_styleTransfer61317", "legacy_hash": "0f7a0ff1" }, "a0498f4122a48f831814385491ab2f23477e4fbd21b2f672dd0bcd32e9590792": { "name": "1混合_3高适用性_基础元素_km_realistic", "legacy_hash": "56b88092" } } }{ "format": "pt", "sd_merge_models": { "833201253ca67f56abe174686c44e7e3aec73b2efcf67558dd86f8b7b06a7578": { "name": "6-24解析-62.fp16", "legacy_hash": "faa93276" }, "9d893468624d68a7a30c1c1cf0d40527973faa0c93ac38dd8c275cf373b2d2d3": { "name": "1混合_5连接之力_6-2附加测试3.fp16", "legacy_hash": "5041375d" } }, "sd_merge_recipe": { "type": "sd-webui-supermerger", "weights_alpha": null, "weights_beta": null, "weights_alpha_orig": null, "weights_beta_orig": null, "model_a": "833201253ca67f56abe174686c44e7e3aec73b2efcf67558dd86f8b7b06a7578", "model_b": "9d893468624d68a7a30c1c1cf0d40527973faa0c93ac38dd8c275cf373b2d2d3", "model_c": "833201253ca67f56abe174686c44e7e3aec73b2efcf67558dd86f8b7b06a7578", "base_alpha": 0.245, "base_beta": 0.02, "mode": "Add difference", "mbw": false, "elemental_merge": "", "calcmode": "trainDifference", "Off": [ "" ] } }Model style:<a target="_blank" rel="ugc" href="https://civitai.com/models/381194?modelVersionId=571701">https://civitai.com/models/381194?modelVersionId=571701</a>Model basic:<a target="_blank" rel="ugc" href="https://civitai.com/models/397967?modelVersionId=444044">https://civitai.com/models/397967?modelVersionId=444044</a>

Model splicing 6-24-63

{ "format": "pt", "sd_merge_recipe": { "type": "sd-webui-supermerger", "weights_alpha": null, "weights_beta": null, "weights_alpha_orig": null, "weights_beta_orig": null, "model_a": "237fed5e69f69030f772568ab45ca878f1a662ab3c3e42bf3a4e362b01428495", "model_b": "9169945ccd4c77f8631c15d3316ec86e3ad02b8a7a1f82cb035c27357b2c8f0d", "model_c": "237fed5e69f69030f772568ab45ca878f1a662ab3c3e42bf3a4e362b01428495", "base_alpha": 0.65, "base_beta": 0.02, "mode": "Add difference", "mbw": false, "elemental_merge": "", "calcmode": "trainDifference", "Off": [ "" ] }, "sd_merge_models": { "237fed5e69f69030f772568ab45ca878f1a662ab3c3e42bf3a4e362b01428495": { "name": "concentrate style 6-16-8", "legacy_hash": "56b88092" }, "9169945ccd4c77f8631c15d3316ec86e3ad02b8a7a1f82cb035c27357b2c8f0d": { "name": "1混合_2中适应性_基础元素_漫画风格基础模型", "legacy_hash": "8d04d192" } } }{ "format": "pt", "sd_merge_recipe": { "type": "sd-webui-supermerger", "weights_alpha": null, "weights_beta": null, "weights_alpha_orig": null, "weights_beta_orig": null, "model_a": "be133583313d920bcb75b60f54ceff9e51c12f3bf4ba716a538bfea3f0934c82", "model_b": "1161c177eb0ef1278bac99aa0066ec77c83daeb3084946e2cce8d40e2566d027", "model_c": "842bcbc0a7f4080efc93c8a003a7c67472fb8b17cacb58f4db775ff94fd3afda", "base_alpha": 0.158, "base_beta": 0.02, "mode": "Add difference", "mbw": false, "elemental_merge": "", "calcmode": "trainDifference", "Off": [ "" ] }, "sd_merge_models": { "be133583313d920bcb75b60f54ceff9e51c12f3bf4ba716a538bfea3f0934c82": { "name": "6-24解析-20.fp16", "legacy_hash": "7776d3de" }, "1161c177eb0ef1278bac99aa0066ec77c83daeb3084946e2cce8d40e2566d027": { "name": "1混合_5连接之力_6-3融合测试4.fp16", "legacy_hash": "d4e89f22" }, "842bcbc0a7f4080efc93c8a003a7c67472fb8b17cacb58f4db775ff94fd3afda": { "name": "1混合_3高适用性_基础元素_2.5D画风线条特征1", "legacy_hash": "025ad103" } } }

Model splicing6-24-21

记录混合数据无其他任何意义Recording mixed data has no other meaning.{ "sd_merge_recipe": { "type": "sd-webui-supermerger", "weights_alpha": null, "weights_beta": null, "weights_alpha_orig": null, "weights_beta_orig": null, "model_a": "c1d961233af81a1540df1a9a2605f501120456af706b0a0218db75173fce5e4e", "model_b": "9169945ccd4c77f8631c15d3316ec86e3ad02b8a7a1f82cb035c27357b2c8f0d", "model_c": "a8d9d3993878d3de57b00b645b8459a799c29a094a1f455026e325a24bb3580b", "base_alpha": 0.5, "base_beta": 0.289, "mode": "Add difference", "mbw": false, "elemental_merge": "", "calcmode": "trainDifference", "Off": [ "" ] }, "format": "pt", "sd_merge_models": { "c1d961233af81a1540df1a9a2605f501120456af706b0a0218db75173fce5e4e": { "name": "融合测试1_6未分类_Nullstyle_v20", "legacy_hash": "6d4d7cb1" }, "9169945ccd4c77f8631c15d3316ec86e3ad02b8a7a1f82cb035c27357b2c8f0d": { "name": "1素材整理新_附加_附加待比较_高适应性画面优化模型1", "legacy_hash": "8d04d192" }, "a8d9d3993878d3de57b00b645b8459a799c29a094a1f455026e325a24bb3580b": { "name": "1素材整理新_减免_6-8测试模型1.fp16", "legacy_hash": "0835cdbe" } } }{ "format": "pt", "sd_merge_models": { "c2c9c9b3078c0257f65ee186ec992b7dbd5a0246c3c2d65a5ff0a780d45c1629": { "name": "6-13 混合测试15.fp16", "legacy_hash": "d8cfd2a6" }, "c4555e293117486c21a729ac94538f77e1f5d7fbb6a47d228b365fd86f9052de": { "name": "1素材整理新_附加_附加待比较_写实风格画风模型2", "legacy_hash": "02ff9017" }, "8a93e0ecd2f00f101a96f93878c210a61396cc8eec4493987af93b71eff4c911": { "name": "1素材整理新_减免_过滤用细节加强模型.fp16", "legacy_hash": "506dbc94" } }, "sd_merge_recipe": { "type": "sd-webui-supermerger", "weights_alpha": null, "weights_beta": null, "weights_alpha_orig": null, "weights_beta_orig": null, "model_a": "c2c9c9b3078c0257f65ee186ec992b7dbd5a0246c3c2d65a5ff0a780d45c1629", "model_b": "c4555e293117486c21a729ac94538f77e1f5d7fbb6a47d228b365fd86f9052de", "model_c": "8a93e0ecd2f00f101a96f93878c210a61396cc8eec4493987af93b71eff4c911", "base_alpha": 0.5, "base_beta": 0.289, "mode": "Add difference", "mbw": false, "elemental_merge": "", "calcmode": "trainDifference", "Off": [ "" ] } }{ "format": "pt", "sd_merge_models": { "e34d4a5392cd825dd51fd222a55dd524f79bab4127c7d5a434d50429783baca0": { "name": "6-13 混合测试16.fp16", "legacy_hash": "d7e5a96f" }, "af2d0b9c2d7a43addb066d79985b697206cb9c57def46de36b11b15bab28706c": { "name": "1素材整理新_待提纯_提纯待比较_实验番剧1", "legacy_hash": "f4093c62" }, "a0498f4122a48f831814385491ab2f23477e4fbd21b2f672dd0bcd32e9590792": { "name": "1素材整理新_基底_km_realistic", "legacy_hash": "56b88092" } }, "sd_merge_recipe": { "type": "sd-webui-supermerger", "weights_alpha": null, "weights_beta": null, "weights_alpha_orig": null, "weights_beta_orig": null, "model_a": "e34d4a5392cd825dd51fd222a55dd524f79bab4127c7d5a434d50429783baca0", "model_b": "af2d0b9c2d7a43addb066d79985b697206cb9c57def46de36b11b15bab28706c", "model_c": "a0498f4122a48f831814385491ab2f23477e4fbd21b2f672dd0bcd32e9590792", "base_alpha": 0.5, "base_beta": 0.289, "mode": "Add difference", "mbw": false, "elemental_merge": "", "calcmode": "trainDifference", "Off": [ "" ] } }

Style transfer6-13-17

记录混合数据无其他任何意义It makes no sense to record mixed data { "sd_merge_models": { "7ceaf62b84b3438665ba62736a8d4ed519a97644b75ed4cfa59173bfc5c48536": { "name": "1素材整理新_基底_混沌1", "legacy_hash": "e0369a82" }, "f2a05b59aed7eaa56da333f40534168ef2c0da168b8a78c5b46ea30737a719bb": { "name": "配方试做_4-29画片解包测试24-2.fp16", "legacy_hash": "85c59969" }, "290a1c4836da21ee4978ef428a73cd4db3492dc62ee89ca4ac8f8e4b0610bed7": { "name": "1素材整理新_减免_4-19画片组合测试10.fp16", "legacy_hash": "6f00cbbf" } }, "format": "pt", "sd_merge_recipe": { "type": "sd-webui-supermerger", "weights_alpha": null, "weights_beta": null, "weights_alpha_orig": null, "weights_beta_orig": null, "model_a": "7ceaf62b84b3438665ba62736a8d4ed519a97644b75ed4cfa59173bfc5c48536", "model_b": "f2a05b59aed7eaa56da333f40534168ef2c0da168b8a78c5b46ea30737a719bb", "model_c": "290a1c4836da21ee4978ef428a73cd4db3492dc62ee89ca4ac8f8e4b0610bed7", "base_alpha": 0.5, "base_beta": 0.289, "mode": "Add difference", "mbw": false, "elemental_merge": "", "calcmode": "trainDifference", "Off": [ "" ] } }

kmmix6-10-38

记录混合数据无其他任何意义Recording mixed data has no other meaning. { "format": "pt", "sd_merge_recipe": { "type": "sd-webui-supermerger", "weights_alpha": null, "weights_beta": null, "weights_alpha_orig": null, "weights_beta_orig": null, "model_a": "7ceaf62b84b3438665ba62736a8d4ed519a97644b75ed4cfa59173bfc5c48536", "model_b": "ea84902f31f5e836bf8dae63399338d8cc5a1fd84bbbc1d5eb894c0f6cd5c2a1", "model_c": "231dcc44085edb80dfff1b2ed1402ab510681131b6c5d286d352c56ef951a114", "base_alpha": 0.5, "base_beta": 0.289, "mode": "Add difference", "mbw": false, "elemental_merge": "", "calcmode": "trainDifference", "Off": [ "" ] }, "sd_merge_models": { "7ceaf62b84b3438665ba62736a8d4ed519a97644b75ed4cfa59173bfc5c48536": { "name": "1素材整理新_基底_混沌1", "legacy_hash": "e0369a82" }, "ea84902f31f5e836bf8dae63399338d8cc5a1fd84bbbc1d5eb894c0f6cd5c2a1": { "name": "配方试做_KM_解析2.fp16", "legacy_hash": "8c516f01" }, "231dcc44085edb80dfff1b2ed1402ab510681131b6c5d286d352c56ef951a114": { "name": "1素材整理新_减免_6-10测试模型12.fp16", "legacy_hash": "67a5ef4f" } } }

kmmix6-10-36

记录混合数据无其他任何意义Recording mixed data has no other meaning. { "format": "pt", "sd_merge_recipe": { "type": "sd-webui-supermerger", "weights_alpha": null, "weights_beta": null, "weights_alpha_orig": null, "weights_beta_orig": null, "model_a": "7ceaf62b84b3438665ba62736a8d4ed519a97644b75ed4cfa59173bfc5c48536", "model_b": "bbb71327d39955d580af7316ff1f24ca561b6459b5e613413ae012e9a96cc0cc", "model_c": "231dcc44085edb80dfff1b2ed1402ab510681131b6c5d286d352c56ef951a114", "base_alpha": 0.5, "base_beta": 0.289, "mode": "Add difference", "mbw": false, "elemental_merge": "", "calcmode": "trainDifference", "Off": [ "" ] }, "sd_merge_models": { "7ceaf62b84b3438665ba62736a8d4ed519a97644b75ed4cfa59173bfc5c48536": { "name": "1素材整理新_基底_混沌1", "legacy_hash": "e0369a82" }, "bbb71327d39955d580af7316ff1f24ca561b6459b5e613413ae012e9a96cc0cc": { "name": "配方试做_大眼睛特征附加1.fp16", "legacy_hash": "a0d7ff17" }, "231dcc44085edb80dfff1b2ed1402ab510681131b6c5d286d352c56ef951a114": { "name": "1素材整理新_减免_6-10测试模型12.fp16", "legacy_hash": "67a5ef4f" } } }

kmmix6-10-35

记录混合数据无其他任何意义Recording mixed data has no other meaning.{ "sd_merge_recipe": { "type": "sd-webui-supermerger", "weights_alpha": null, "weights_beta": null, "weights_alpha_orig": null, "weights_beta_orig": null, "model_a": "5d6c9a76fa39d8a5e5108b3c887e0b46f660236dc424196750ece427cfe856e0", "model_b": "032ee69d6697a1736d736e7a1a38fc89cfa261aff19565e83af175a49b71cafa", "model_c": "a0498f4122a48f831814385491ab2f23477e4fbd21b2f672dd0bcd32e9590792", "base_alpha": 0.5, "base_beta": 0.289, "mode": "Add difference", "mbw": false, "elemental_merge": "", "calcmode": "trainDifference", "Off": [ "" ] }, "format": "pt", "sd_merge_models": { "5d6c9a76fa39d8a5e5108b3c887e0b46f660236dc424196750ece427cfe856e0": { "name": "6-10测试模型31.fp16", "legacy_hash": "b8145704" }, "032ee69d6697a1736d736e7a1a38fc89cfa261aff19565e83af175a49b71cafa": { "name": "1素材整理新_附加_附加待比较_4-19画片组合测试22222.fp16", "legacy_hash": "da06e9e4" }, "a0498f4122a48f831814385491ab2f23477e4fbd21b2f672dd0bcd32e9590792": { "name": "1素材整理新_基底_km_realistic", "legacy_hash": "56b88092" } } }

kmmix6-10-32

6-6kmmixTesting47

使用早期素材进行的画风混合，特殊但是并不实用The use of early materials for a mixed painting style, special but not practical.

6-6kmmixTesting46

Lora 是未来模型混合化的方向。我在分类素材以及融合尝试上浪费了好几天时间，虽然有所收获但效果仍然不如使用LORA混合Lora is the direction of future model hybridization. I wasted several days on material classification and fusion attempts. Although I gained some results, the effect is still not as good as using Lora hybrid.关于这个模型：最近我又开始尝试混合不同风格，但这太难了。你可能发现了我混合的模型都很怪异，我推测这些模型因为强化某些特征而失去了太多其他元素，因此导致了模型的适用性下降。总之我开始尝试拼接这些特征，可是我不可能像拼积木一样轻松完成混合。这是我尝试了很多次后得到的模型，或许我找到了一些方法，但这仍然需要大量时间验证。About this model: Recently, I have started to experiment with blending different styles, but it is very difficult. You may have noticed that the models I blend are all strange. I speculate that these models lose too many other elements because they reinforce certain features, resulting in a decrease in the applicability of the models. In short, I started to try to concatenate these features, but I cannot easily complete the blending like building blocks. This is the model I obtained after many attempts. Perhaps I have found some methods, but it still requires a lot of time for verification. In short, I started to try to concatenate these features, but I cannot easily complete the blending like building blocks. This is the model I obtained after many attempts. Perhaps I have found some methods, but it still requires a lot of time for verification.使用素材：<a target="_blank" rel="ugc" href="https://civitai.com/models/89004/amb12?modelVersionId=94718">https://civitai.com/models/89004/amb12?modelVersionId=94718</a> 我在两个月前尝试提取该模型特征，但不是很适用。I attempted to extract the features of this model two months ago, but it was not very applicable. 值得注意的是现在混合的模型都含有LORA的元素，而且很难被发现。It is worth noting that the current mixed models all contain elements of lora, and it is difficult to be discovered.

6-5KmMix A

模型浓度：中 Model Concentration: medium模型纯度：中 Model Purity: medium这些信息是展示这个模型的扩展性，纯度代表着它的主要属性，浓度代表这个模型在混合时的表现。These pieces of information demonstrate the scalability of this model, purity represents its primary attribute, and concentration represents the performance of this model when mixed.最后两张图片用于演示混合扩展性The last two pictures are used to demonstrate mixed scalability.新的融合流程，为此我花费很多时间整理素材库，可惜的是大部分素材都没用。New fusion process, for this I spent a lot of time organizing the material library, unfortunately most of the materials are useless.在不使用质量提示词下也有不错的效果Even without using quality prompts, there are still good results.

KM_MIX Improve cute 1

探索融合时的产物Exploring the product of integration in time.缺少独特性Lack of uniqueness.

Style extraction cute 1

在模型融合时，我最不想发现自己融合的模型与别的模型相似，但我也想让你们知道我融合的结果和使用的素材，来验证我的提取实验。这很矛盾，因此我减少了混合次数以增加素材的辨识度，但这也导致混合的模型缺少差异性When it comes to model fusion, what I least want to discover is that the model I fused is similar to other models. However, I also want you to know the results of my fusion and the materials I used to validate my extraction experiment. This is contradictory, so I have reduced the number of mixings to increase the distinguishability of the materials, but this also leads to the lack of distinctiveness in the blended model.Model：<a target="_blank" rel="ugc" href="https://civitai.com/models/94726">https://civitai.com/models/94726</a>LORA：<a target="_blank" rel="ugc" href="https://civitai.com/models/119625?modelVersionId=129992">https://civitai.com/models/119625?modelVersionId=129992</a>我使用了一个特征模型做减免，你或许能理解这是什么意思I used a feature model for reduction, perhaps you can understand what this means.

Style extraction cute

现在你可以看到低浓度这一特征代表着什么。因为多进行了一次融合所以我发布在这个页面Now you can see what the low concentration represents. Because I have performed an additional fusion, I am posting it on this page.奇妙的是我在过去混合出了一个低浓度现实画风模型，而我竟然没有发现。It is amazing that I have inadvertently created a low-concentration realistic painting style model in the past, and I didn't even realize it.

Low density byproduct 1

不建议你们下载这个模型，因为它只是为了展示高浓度这个现象，而且这个混合的很敷衍，我只使用了一道制作工序进行混合。嗯之后我会在我混和的模型标注这一点，可是谁在乎这一点。I don't recommend that you download this model, because it's just to show the high concentration, and it's a very perfunctory mix, and I only used one process to mix it. Well, I'll note that in my mixed model later, but who cares.我在进行一个非常消耗时间的项目，希望我能成功。如果成功的话我可以得到更多融合素材，当然不会有人在意这个I am working on a very time-consuming project and I hope to succeed. If I succeed, I can get more fusion materials, but of course, no one cares about this.

Study of Mixed Phenomena2

这是模型混合时的一个现象，因为会将所有模型都同化为一个样子，我称呼这种模型为高浓度。This is a phenomenon during model blending, as it will assimilate all models into one appearance. I refer to this type of model as "high concentration."但是我对这种现象还未进行仔细研究，今天我发现这种现象还挺不错。这个现象可以在混合时有效保留原有特征，但是我忘记这些样本是怎么混合出来的了。哈哈However, I have not conducted a detailed study on this phenomenon yet. Today, I found this phenomenon quite good. This phenomenon can effectively retain the original features during mixing, but I forgot how these samples were mixed. Haha.使用了以下LORA：<a target="_blank" rel="ugc" href="https://civitai.com/models/49254">https://civitai.com/models/49254</a> 本次使用的样本并不适合大多数人使用，因为当时我的融合课题是强化特征The sample used this time is not suitable for most people to use, because at that time my fusion project was focused on reinforcing features.

Study of Mixed Phenomena

缺乏灵感的混合物。情况可能需要等我进行完离职流程后会好转A mixture lacking inspiration. The situation may improve after I complete the resignation process.这个模型进行了多次的混合以至于制作记录都难以查找。我采用了新的方法但是我不知道这是否有用，或许我该休息一下This model has undergone multiple blends to the point where it is difficult to trace the production records. I have adopted a new approach, but I am unsure if it is effective. Perhaps I should take a break.

CGstyle

使用了以下LORA：WLOP/王凌/wlopwangling style:<a target="_blank" rel="ugc" href="https://civitai.com/models/102143">https://civitai.com/models/102143</a>阿戈魔AGM 画风:<a target="_blank" rel="ugc" href="https://civitai.com/models/85130">https://civitai.com/models/85130</a>为了使上传的原模型变得特殊，我又附加了一个艺术家风格，总之需要上传的模型有增加了。或许我找到了拯救我硬盘的方法，那就是快点上传那些模型吧！最好一天上传10个！！（不）In order to make the uploaded original model special, I added an artist style, in short the need to upload the model has increased. Maybe I found a way to save my hard drive, that is to upload those models quickly! ! Better make it 10 a day! (no)

AGMstyle + WLOPstyle

I took an artist's style model and a game's style model and mixed them together我提取了一个艺术家的风格模型和一个游戏的风格模型然后混合了起来url:<a target="_blank" rel="ugc" href="https://civitai.com/models/102143">https://civitai.com/models/102143</a><a target="_blank" rel="ugc" href="https://civitai.com/models/15382?modelVersionId=18126">https://civitai.com/models/15382?modelVersionId=18126</a>使用提示词可以强化风格表达Use prompts to reinforce your style

WLOPstyle+guigu style

模型浓度：偏高 Model Concentration: Slightly high模型纯度：偏高 Model Purity: Slightly high这些信息是展示这个模型的扩展性，纯度代表着它的主要属性，浓度代表这个模型在混合时的表现。These pieces of information demonstrate the scalability of this model, purity represents its primary attribute, and concentration represents the performance of this model when mixed.

MIX byproduct anime style

显然使用LORA进行的混合比纯粹的模型混合要简单。事情开始变得乏味起来了。Obviously, using LoRa for hybrid model mixing is simpler than pure model mixing. Things are starting to get boring.使用了以下LORAUsed the following lora.<a target="_blank" rel="ugc" href="https://civitai.com/models/29215/bartstyle-or-blue-archive-art-style-lora-or-or">https://civitai.com/models/29215/bartstyle-or-blue-archive-art-style-lora-or-or</a><a target="_blank" rel="ugc" href="https://civitai.com/models/99590">https://civitai.com/models/99590</a>

MMD style+Blue Archive v7

模型融合二阶段的产物，混合了复数的特征

A style that may feel familiar to you, but it may not be suitable for some Lora.让你感到熟悉的一种风格，但它不太适合一些LORAI tried to change the way the model was transformed to avoid the model not being able to load, but I don't know if this worked我试图改变模型转换的方式，以避免模型无法加载，但我不知道这是否有效

v5.0

This is a common painting style, but to my surprise this model is more suitable for chibi style这是一种常见的绘画风格，但出乎我预料的是这个模型更适合chibi风格

模型纯度：稍高 Model Purity: Slightly high模型浓度：稍低 Model Concentration: Slightly low这些信息是展示这个模型的扩展性，纯度代表着它的主要属性，浓度代表这个模型在混合时的表现。These pieces of information demonstrate the scalability of this model, purity represents its primary attribute, and concentration represents the performance of this model when mixed.A mixture of pencil style and realistic style, obviously it still has room for optimization.铅笔风格和写实风格的混合物，显然它还有优化的空间There are no extra features. In fact, there are already many models with this style, but perhaps I like this model more, so I chose to release it.没有多余的特点，事实上已经有很多这类画风的模型了，但可能我比较喜欢这个模型因此我选择了发布Now I can remove this file from the local, it's just great.现在我可以从本地移除这个文件了，简直太棒了

模型纯度：稍高 Model Purity: Slightly high模型浓度：稍低 Model Concentration: Slightly low这些信息是展示这个模型的扩展性，纯度代表着它的主要属性，浓度代表这个模型在混合时的表现。These pieces of information demonstrate the scalability of this model, purity represents its primary attribute, and concentration represents the performance of this model when mixed.A model imitating the style of manga, although it is close, there is still a significant gap.模仿漫画风格的模型，虽然接近了但是还是有很大差距Wait a moment, this doesn't seem to be in the style of a comic.等等，这个看起来不像是漫画的风格

Comic style V1

Surprisingly, the compatibility of this model is quite good.令人惊讶的是，这个模型的兼容性非常好。

v2.0

模型浓度：稍高 Model Concentration: Slightly high模型纯度：中 Model Purity: Medium这些信息是展示这个模型的扩展性，纯度代表着它的主要属性，浓度代表这个模型在混合时的表现。These pieces of information demonstrate the scalability of this model, purity represents its primary attribute, and concentration represents the performance of this model when mixed.A model without any distinctive features, you may even feel like you've seen these pictures before.一个没有任何独特特征的模型，甚至你可能会觉得你以前见过这些照片。

KM_MIX byproduct