CamelliaMix_Line
файл на civitaiстраница на civitaiSHA256: 8CB4025C4A668EB09A8EFC24B1E7DF3D525299F581F777D25C9DE9B1D1633059
CamelliaMix 2.5D is re-uploaded
This is CamelliaMix variation model
CamelliaMIx
dalcefo_painting
Fachion Girl LoRA
Sampling method : DPM++ SDE Karras
Clip skip : 2
Hires steps : 13
Hires.fix upscaler : R-ESRGAN 4x+Anime6B
CFG Scale : 7~11
VAE : ft-mse-840000
Prompt : (masterpiece:1.2, best quality), (real picture)
Negative : (worst quality, low quality:1.4), EasyNegative
Textual Inversion : EasyNegative
It features strong contrast, bloom Effect and color tones
Based on Legendary Dalcefo, but a lot has changed. not suitable for hard NSFW
I don't recommend negative embedding in most cases
because it has a huge impact on color and figure
Still in very early stages, but have fun playing with it 🙂
////////////////////////////////////////////////////////////////////////////////////
Recommended Settings - VAE is already included
Clip skip : 2
Hi-Res Fix : R-ESRGAN 4x+ Anime6B / Steps: 14 / Strength: 0.4
Sampler : DPM++ 2M Karras
CFG : 8+ / Steps : 25+
Prompts
(best quality, masterpiece:1.3)
Neg : (worst quality, low quality:1.3)
////////////////////////////////////////////////////////////////////////////////////
Do you like my work? check out my profile and see what else!
And A cup of coffee would be nice! 😉
////////////////////////////////////////////////////////////////////////////////////
For anything other than general personal use, please be sure to contact me
You are solely responsible for any legal liability resulting from unethical use of this model
CamelliaMix is re-upload
CamelliaMix_V1
dalcefopainting_3rd
Counterfeit-V2.5
Motomurabito Style LoRA
Hipoly 3D Model LoRA
Shojo Vibe LoRA
Kidmo//style LoRA
Sampling method : DPM++ SDE Karras
Clip skip : 2
Hires.fix upscaler : R-ESRGAN 4x+Anime6B
CFG Scale : 7~10
Prompt : (masterpiece:1.2, best quality)
Negative : (worst quality, low quality:1.4), EasyNegative
Textual Inversion : EasyNegative
! ! ! l o t s o f j u n k d a t a ! ! !
! ! ! l o t s o f j u n k d a t a ! ! !
! ! ! l o t s o f j u n k d a t a ! ! !
! ! ! l o t s o f j u n k d a t a ! ! !
! ! ! l o t s o f j u n k d a t a ! ! !
! ! ! l o t s o f j u n k d a t a ! ! !
! ! ! l o t s o f j u n k d a t a ! ! !
! ! ! l o t s o f j u n k d a t a ! ! !
! ! ! l o t s o f j u n k d a t a ! ! !
! ! ! l o t s o f j u n k d a t a ! ! !
I don't know why, but this model becomes clearer or simpler depending on the prompt.
Expmix_Line re-upload
Expmix variation model.
This model show 2D anime style using Flat colors and strong outlines
ExpMix_Line
ChikMix
SamDoesArts (Sam Yang) Style LoRA
ligne claire style(cogecha焦茶) LoRA
Motomurabito Style LORA
Kidmo//style LoRa
Sampling method : DPM++ SDE Karras
Clip skip : 1~2
Hires.fix upscaler : R-ESRGAN 4x+Anime6B
Denoise strength : 0.4~0.65
CFG Scale : 6~10
Prompt : (masterpiece:1.2, best quality), 1lady, solo
Negative : (worst quality, low quality:1.4), eastnagative
Textual Inversion : EasyNegative
※このモデルにはいくつかのバリエーションがあることを見逃さないでください
Note:Don't miss that there are several variations of this model!
,
Note: If you like it, please give it a STAR MARKS !
The caulkinumV2_AR series is a model designed to beautifully portray anime characters and light.
This checkpoint was spawned accidentally through multiple iterations of hierarchical merging.
Therefore, the detailed recipe is already lost.
,
However, there is no doubt that Silicon28 is at the root of it and that it has inherited the influence of ElysiumAnime_V2.
If someone likes it I will be very happy.
,
The caulkinumV2 series has several variations.
"AR" is the first model, which is a modern anime/game style.
"AR2" is the normal evolution of the first model, and it can create better illustrations.
"A4FS" has a dramatic style, which is more in line with recent RPG games.
"ARCT" is an anime-style painting that makes the characters look young.
"ARc" has the same anime style, but is a bit more difficult to handle and a bit outlandish.
"NCA" is a little bit special and unique, but it was created to depict a slime girl.
,
A sample comparison is provided below.
It does not always work, but I am generally satisfied with the results.
Note: Underscores at the beginning of checkpoint names are assigned by AUTOMATIC1111 for sorting purposes and have no particular meaning.
,
,
※ 気に入っていただけたならぜひ★をつけてください！
,
caulkinumV2_ARシリーズは、アニメのキャラクターと光の表現を美しく描くために考案したモデルです。
このチェックポイントは複数回の階層マージを繰り返して偶発的に産まれました。
そのため細かいレシピはもう失われています。
,
しかしSilicon28が根底にあること、ElysiumAnime_V2の影響を受け継いでいることは間違いありません。
誰かが気に入ってくれたなら私はとても幸せでしょう。
,
caulkinumV2シリーズはいくつかのバリエーションがあります。
「AR」が最初のモデルでモダンなアニメやゲームの画風です
「AR2」は正常進化版でより良いイラストを錬成できます
「A4FS」は劇画調で近年のRPGゲームらしさが表現できます
「ARCT」はアニメ風の塗りでキャラクターは幼くなるでしょう
「ARc」も同様にアニメの画風ですが、やや扱いづらく突飛なところがあります
「NCA」は少し特殊で独特の画風ですが、スライム娘を描くために作りました。
,
下記に比較サンプルを掲載しておきます。
必ずしもうまくいくとは限りませんが、私はおおむね満足しています。
注釈 ) チェックポイント名先頭のアンダースコアはAUTOMATIC1111で並べ替えのために付与したもので特に意味はありません
,
,
,
,
,
,
Coffee will increase work efficiency and motivation.
コーヒーは作業効率を高めモチベーションをアップさせるでしょう。
,
Thank you for reading to the end.
I hope one of you will use it.
,
最後まで読んでくれてありがとうございます。
使用してくれるか方が一人でもいることを祈っています。
Expmix is re-uploaded
This is an Anime Style model
Sampling method : DPM++ SDE Karras
Clip skip : 1~2
Hires.fix upscaler : R-ESRGAN 4x+Anime6B
CFG Scale : 7~10
prompt : (masterpiece:1.2, best quality)
negative : (worst quality, low quality:1.4), EasyNegative
The purpose of phobias is to elicit a sense of realism, which is achieved by collecting DNA samples from various iconic models. These models are particularly effective when creating close-up portraits.
Ancestors:
chilloutmix_NiPrunedFp32Fix
orangehardBasil05_v10
sacrumProfanum_spv1
level4_v50BakedVAEFp16
cyberrealistic_v13
Variation:
As observed, 'Phobias_c' still has problems with the eyelash.
Additional Download:
Optional: VAE
This model was trained on some ~200 odd random selections of AI art that I personally found impressive and visually interesting. The keyword is simple "tensorfunk". ENJOY!
tensorfunk
It features very strong contrast and color tones
Based on Legendary Dalcefo, but a lot has changed. not suitable for hard NSFW
I don't recommend negative embedding in most cases
because it has a huge impact on color and figure
Still in very early stages, but have fun playing with it 🙂
////////////////////////////////////////////////////////////////////////////////////
Recommended Settings - VAE is already included
Clip skip : 2
Hi-Res Fix : R-ESRGAN 4x+ Anime6B / Steps: 14 / Strength: 0.4
Sampler : DPM++ 2M Karras
CFG : 8+ / Steps : 25+
Prompts
(best quality, masterpiece:1.3)
Neg : (worst quality, low quality:1.3)
////////////////////////////////////////////////////////////////////////////////////
Do you like my work? check out my profile and see what else!
And A cup of coffee would be nice! 😉
////////////////////////////////////////////////////////////////////////////////////
For anything other than general personal use, please be sure to contact me
You are solely responsible for any legal liability resulting from unethical use of this model
针对男性进行强化的融合模型，目前还是处于测试版。
The fusion model enhanced for men is currently in beta.
muscular
本模型由多个checkpoint模型合并而来，具体有哪些我也记不太清了。以下是MoonMix与chilloutMix模型在生成人像时的一些对比。总的来说，MoonMix相比chilloutMix，真实感和锐度有所下降，但美感与丰富度有所提升。
This model is the result of merging several checkpoint models. I can't remember exactly which models there are. Here are some comparisons between MoonMix and chilloutMix models in generating portraits. In general, MoonMix is less realistic and sharper than chilloutMix, but the overall beauty and richness is improved.
演示样例中所使用Lora模型“1girlmix”可以在此处获取：https://civitai.com/models/33208/lora
The Lora model "1girlmix" used in the demo example is available here: https://civitai.com/models/33208/lora
Deep boys 2.5D ver.2 creates a more mature male face.
The background is even more detailed.
Recommended Settings
Sampling method : Eular a
Clip skip : 2~5
Hires.fix upscaler : SwinIR_4x / Latent
CFG Scale : 7~9
VAE : vae-ft-mse-840000-ema-pruned
Recommended Prompt : realistic
Negative prompt : 3d
realistic
This is a merged model of:
The original models are very good, SO I mixed them together!
Like the original models it can produce SFW and NSFW images
furryanthropomorphic
Take 1 part ICBINP v2 with 6 splashes of semi-realism models (credit to ReV Animated as a dash of that was used), and 1 part JAFA Mix v3b and voila - RCNZ Optimus Primate.
Has the "rcnz_niji style" trigger word for the merged lora. I think it works well for landscapes, anime and semi-realistic prompts, but it seems to struggle a bit with the full photo-realistic stuff.
Recommended Settings: Clip Skip = 2, VAE of either kl-f8-anime2 or 840000, and Discard Penultimate Sigma = True
I hope you all enjoy it, and I look forward to seeing what you can make with this/merge this into!
rcnz_niji style
A fully revamped checkpoint based on the 512dim lora and chilloutmix_NiPrunedFp32Fix + deliberate_v2.
Training data: 512 DIM LORA
https://civitai.com/models/41893/lora-eggeaster-fusion
Here is how it looks using the lora on top of models:
lora weights: TEnc Weight 0.2 UNet Weight 1
Merged the 512dim lora to chillout and deliberate / --ratios 0.99 toward my fusion lora
C is CHillout / d is deliberate
Merged C and D with:
Base_alpha=0.53
Weight_values=0,0.157576195987654,0.28491512345679,0.384765625,0.459876543209877,0.512996720679012,0.546875,0.564260223765432,0.567901234567901,0.560546875,0.544945987654321,0.523847415123457,0.5,0.476152584876543,0.455054012345679,0.439453125,0.432098765432099,0.435739776234568,0.453125,0.487003279320987,0.540123456790124,0.615234375,0.71508487654321,0.842423804012347,1
and
1,0.842423804012346,0.71508487654321,0.615234375,0.540123456790123,0.487003279320988,0.453125,0.435739776234568,0.432098765432099,0.439453125,0.455054012345679,0.476152584876543,0.5,0.523847415123457,0.544945987654321,0.560546875,0.567901234567901,0.564260223765432,0.546875,0.512996720679013,0.459876543209876,0.384765625,0.28491512345679,0.157576195987653,0
both results merged
Weight_values=
1,0.842423804012346,0.71508487654321,0.615234375,0.540123456790123,0.487003279320988,0.453125,0.435739776234568,0.432098765432099,0.439453125,0.455054012345679,0.476152584876543,0.5,0.523847415123457,0.544945987654321,0.560546875,0.567901234567901,0.564260223765432,0.546875,0.512996720679013,0.459876543209876,0.384765625,0.28491512345679,0.157576195987653,0
And voila..
here is Egg_fusion checkpoint with the 512 dim-trained lora
Enjoy your eggs 🤟 🥃
If you ran into any troubles with my mix, please read description below. There is plenty of useful information.
02.02.2023 - Added lightweight pruned fp-16 no ema model for DivineEleganceMix and DivinePastelMix.
16.02.2023 - DivineEleganceMix2 released.
17.03.2023 - DivineEleganceMix3 released.
24.03.2023 - DivineEleganceMix4 released.
18.04.2023 - DivineEleganceMix5 released.
All the models i've used before first ever DivineElegance realse did not fit my requirements at all, so i decided to do something by myslef. I saw different mixes built on Anything v4 or v4.5 and i've realized what i truly need. But the main differences between Any | AOM and DivineElegance was the backgrounds.
DivineElegance at the beginning was a mix for my personal use, but it was warmly received by Unstable Diffusion's discord community and some time later i decided to share it, due to many requests.
Right now DivineElegance is my favourite model and quite unique thing for me. The main goal of DivineElegance - anime characters with as many details as it could have. Hair, clothes, backgrounds, all of this things should be beautiful, slightly more realistic and detailed.
I hope you also would like DivineElegace, so stay tuned for newer versions of mix!
Use danbooru tagging for prompts
Sampler: Euler at / 30-50 steps
Sampler: UniPC at 30 steps for landscapes
Cfg scale: 7
Clip Skip: 2 <---- VERY IMPORTANT
ENSD (Eta noise seed delta) - leave blank
Upscaler: Fatal Anime
Hires steps: 10-15
Denoising strength: 0.35
Denoising strength (Latent): 0.5
Upscale by: any
If you want to get mostly the same results, you difinitely will need negative embeddings:
I'd also recomment it for permanent use.
If you're ran into any problem with my mix, you can dm me on discord: TroubleDarkness#6280, I'll be glad to help | Буду рад помочь.
My main model right now.
To merge it by yourself you need:
Step 0: Cocoa + AOM3 at Weighted Sum 0.4
Convert Anything v5 PRT-RE to ckpt
Convert AbyssOrangeMix3 to ckpt
Convert Grapefruit 3.1 to ckpt
Convert SenzusHolyshit to ckpt
Convert FaceBombMix to ckpt
Step 1: Anything-5 + BasilMix-Fixed
MBW: 1,0.9,0.7,0.5,0.3,0.1,1,1,1,1,1,1,0,0,0,0,0,0,0,0.1,0.3,0.5,0.7,0.9,1 - Alpha 0
Step 2: Previous mix + (NovelAI-NSFW - NovelAI-SFW) at Add Difference 0.3
Step 3: Previous Mix + Grapefruit 3.1 at Weighted Sum 0.5
Step 4: Previous mix + CocoaAOM3 at Weighted Sum 0.5
Step 5: Previous mix + SensuzHolyshit at Weighted Sum 0.2
Step 6: Previous Mix + Face-Bomb-Mix at Weighted Sum 0.3
Step 7: Convert .ckpt file to fp16 no-ema .safetensors model
Don't save anything before Step 7 as safetensors of half!
Old version of DivineElegance.
To merge it by yourself you need:
Step 0: You need:
Anything V4.5 (Full version)
BasilMixFixed with TensorFix and coverted to .ckpt
Grapefruit 3.1 converted to .ckpt
Step 1: Block Merge (Anything4.5 + BasilMix Fixed) at weights 1,0.9,0.7,0.5,0.3,0.1,1,1,1,1,1,1,0,0,0,0,0,0,0,0.1,0.3,0.5,0.7,0.9,1 and Base Alpha 0
Step 2: Previous Mix + NovelAI NSFW + NovelAI SFW at Add Difference 0.3
Step 3: Previous Mix + Grapefruit 3.1 at Weighted Sum 0.5
Step 4: Previous Mix + Anything V4.5 at Weighted Sum 0.4
Step 6: Previous Mix + FaceBombMix (no vae) at Weighted Sum 0.3
Step 7: Convert .ckpt file to fp16 ema-only .safetensors model
Don't save anything before Step 7 as safetensors of half!
Old version of DivineElegance.
To merge it by yourself you need:
Step 0: You need:
Anything V4.5 (Full version)
BasilMixFixed with TensorFix and coverted to ckpt
Step 1: Block Merge (Anything4.5 + BasilMix Fixed) at weights 1,0.9,0.7,0.5,0.3,0.1,1,1,1,1,1,1,0,0,0,0,0,0,0,0.1,0.3,0.5,0.7,0.9,1 and Base Alpha 0
Step 2: Previous Mix + NovelAI NSFW + NovelAI SFW at Add Difference 0.3
Step 3: Previous Mix + Grapefruit 4.1 at Weighted Sum 0.5
Step 4: Previous Mix + Cocoa at Weighted Sum 0.3
Step 5: Previous Mix + ZeroTolerances at Weighted Sum 0.15
Step 6: Previous Mix + FaceBombMix at Weighted Sum 0.25
Don't save anything above as safetensors of half!
Old version of DivineElegance.
Recipe is lost :(
Actually, the same receipe as V1, but with different weight values and without TensorFix. Receipe would be changed in future releases.
Old version of DivineElegance.
To merge it by yourself you need:
Step 1: Block Merge (Anything V4.5 + BasilMixFixed) at weights 1,0.9,0.7,0.5,0.3,0.1,1,1,1,1,1,1,0,0,0,0,0,0,0,0.1,0.3,0.5,0.7,0.9,1 and Base Alpha 0
Step 2: Previous Mix + NovelAI NSFW + NovelAI SFW at Add Difference 0.3
Step 3: Previous Mix + AnythingGape (Made of Anything4.5 + Gape60 + NAI NSFW at Add Difference 1.0) + NAI NSFW at Add Difference 0.3
Step 4: Previous Mix + Cocoa at Weighted Sum 0.5 = DivineEleganceMix, then, make a TensorFix (aka ClipFix)
That's all you need for base model. Also, you can skip step 3 to avoid more nsfw-ish images in generations.
Really BIG thanks to:
Nigurumi for BasilMix.
WarriorMama777 for AbyssOrangeMixes and reciepes.
andite for Anything4.5/Cocoa/PastelMix.
Ikena for Grapefruit.
Cyria for ZeroTolerances.
devdevice545734 for FaceBombMix.
You, for reading, downloading and reviewing this mix.
This is a model I combined with basilmix and lucky, just to show the character lora I made, because many people asked, so I still uploaded it for easy use.
Simply put, when outputting real-life photos of anime characters, the face is more in line with my preferences
这是我用basilmix和lucky随手融合的模型，只是用来展示我制作的人物lora，因为很多人询问，所以我还是上传了它，方便使用。
简单来说，输出动漫人物的真人照片时，脸更符合我的喜好
This is a model I combined with anything and basilmix, just to show the character lora I made, because many people asked, so I still uploaded it for easy use.
To put it simply, when exporting anime characters, the picture is clean and the proportions of the characters are realistic. Of course you can use it with my kbxll.pt (0.8 weight), the effect is better
这是我用anything和basilmix随手融合的模型，只是用来展示我制作的人物lora，因为很多人询问，所以我还是上传了它，方便使用。
简单来说，输出动漫人物的时候，画面干净，人物比例写实。当然你可以配合我的kbxll.pt（0.8权重）使用，效果更佳
My model consists of two different models that I have merger
AcidBurn is here! the sequel to HELLmix, this model is extremely well tuned to basically every concept I could think of trying, and plays well with most LORA and Embedding!
I'll once again include the VAE I prefer for this model in case you don't have that one.
Stablegram
my fanslora : fanslora.com/shierry
(US/European instagram woman style)
Warning: Add "nude, naked" to the negative prompt if want to avoid NSFW.
Trained with +4000 images
Currently working on a new version with +100 000 images for better accuracy and consistency. By the way, have fun and don't hesitate to share your images !
a woman
CoffeeNSFW is intended to produce sexy/hentai anime pictures with a more cartoony art style, emphasizing lineart and cel shading.
CoffeeMix is the more general-use model, as it usually tends to lean on the sfw side.
As usual, I recommend short, simpler prompts. Use EasyNegative for negative prompt.
I like using DPM++ 2M Karras with 20 sampling steps, but other samplers work fine. VAE is baked in.
If you like my models, consider tipping me a coffee.
Historical European Uniforms use the trigger word "HistorischeUniformen".
The training has been performed on a selection of 130 historical pencil and watercolour illustrations depicting different European uniform designs from the late 1600s to the and of the1900s
for LoRa see https://civitai.com/models/44064?modelVersionId=48704
HistorischeUniformen
一款精细的合成二次元模型，希望能带给你不一样的感受
A fine synthetic anime model, hoping to give you a different feeling
Like my other model, this focuses on My Little Pony: Friendship is Magic. The difference, however, is this was merged with Elldreth's Lucid Mix model and it is easier, more likely to get realistic human/semi-human versions of the characters (depending on settings, prompts, of course!) but you can still get great pony art too, not to mention Photorealism and Anime of all sorts. Like my previous model, This also can give suggestive and explicit content.
Note: I don't know about you users who try for Rainbow Dash but I find it extremely difficult no matter what, even with "Rainbows" as a negative prompt
The beggining of a great project !
A precise chosen noise offset setting
A large variety of subjects, I took care to to keep the flavour at maximum from genesis seeds feel
No baked VAE (works fine without any tbh)
For good results please use the forAnalogPortrait negative embedding.
For my digital painting finetune, please use “character portrait” along “digital painting” for enhance the quality
use the forAnalogPortrait negative embedding aswell.
Happy tuning !
romerorz.art - Twitter - DeviantArt - Gumroad
I generally satisfy with this version.😆😆😆
If you feels it is a good mix, please comment✍️ and leave an images 🖼️. Both are appreciated.
If you like this mix, please give it a heart❤️.
This mix aims to keep photorealistic and capable with most anime lora.
version 2
🚀Improvement Highlight effect.
🚀Improve Realistic skin texture
👍Positive prompt prefix:
Short:
8k, real picture, intricate details, ultra-detailed,(photorealistic),
Long:
8k, best quality, real picture, intricate details, ultra-detailed, ultra highres, depth field,(photorealistic,realistic:1.2),masterpiece,
Sometime it would get better image with Short prefix
👎Negative prompt prefix:
(raw photo), EasyNegative, badhandv5, (worst quality, low quality:1.4)
Neg promp embeddings:
https://civitai.com/models/30452/bad-hands
https://civitai.com/models/7808/easynegative
Merge List:
https://civitai.com/models/6424/chilloutmix
https://civitai.com/models/24383/grapefruit-hentai-model
https://civitai.com/models/20981/3moon-nireal
https://civitai.com/models/22402/fantasticmixreal
v1.1 added
https://civitai.com/models/22922/lyriel
https://civitai.com/models/9291/sunshinemixsunlightmix
v2 added
https://civitai.com/models/15003/cyberrealistic
https://civitai.com/models/17754/dreamful
Suggested steps: 20~35
Suggested CFG: 4~9
Some example images using extention: Dynamic Thresholding (CFG Scale Fix)
第二版我改善了一下特定成分的权重，也改善了光影 In Version2 I adjust the weight of certain element so that the hands and body can be better. I also adjust the lighting slightly.
新的展示图用了胶片风 In show case I used 胶片风女孩LoRA
融合了多种模型，可以生成好看的脸部，也能有效应对暗部处理。远距离脸部需要inpaint以达成最好效果
A good looking model, suitable for NSFW and dark scene (because I added noiseoffset). long-range facial detail require inpainting to achieve the best results.
推荐关键词 recommended positive prompts: Best quality, masterpiece, ultra high res, (photorealistic:1.4), 1girl
如果想要更暗的图像 if you want darker picture, add: in the dark, deep shadow, low key, etc.
负面关键词 use ng_deepnegative_v1_75t and badhandv4 in negative prompt
I've used a bug-fixed version of DPM++ 2M Karras, you can check this out: https://civitai.com/models/35966/dpm-2m-alt-karras-sampler
推荐参数Recommended Parameters:
Sampler: DPM++ 2M Karras (bug-fixed) or DPM++ SDE Karras
Steps: 20~40
Hires upscaler: R-ESRGAN 4x+ or 4x-UltraSharp
Hires upscale: 2
Hires steps: 15
Denoising strength: 0.2~0.5
CFG scale: 6-8
clip skip 2
脸部修复的方法 to inpaint the face: inpaint-->only masked-->set to 512x512-->Denoising strength:0.2~0.5
formula:
KanPiroMix + XSMix + ChikMix
关注我的TG频道看更多例图：https://t.me/majic_NSFW
Contaby is an anime (Hassaku-based) model, unlocked for nsfw.
I (PlayaEmblem) don't own the base of the model. Contaby is trained to have a smoother, warmer light with even more details.
Contaby vs Hassaku (Girl, City, Rainy, Blue Hair)
Contaby vs Hassaku (Girl, Flying, Sunset)
Contaby vs Hassaku (Gothic E-girl, Playing video games)
This Model is better for girls than for boys. Try it yourself and download Contaby.
Any questions? DM me on Discord: ! PlayaEmblem#9877
It has good detail and physical expression
nai's vae is enough
The preview image is not specially selected
My own model mix, its a mix of a lot of models, naming started with 1_mix_a, 1_mix_b etc...
Latest Version 1_mix_s6
My focus leans more towards realism/fantasy, but of course it all depends on the prompt.
Be warned the model is mixed with nsfw models.
Use with standard VAE 'vae-ft-mse'
Hint for more realism add 'anime,manga,drawing, 3d render' to negatives.
Update: added inpainting and pix2pix model
📷 Aiming at the most realistic Photomodel, improve of my hyperphotogodess model
Low Sampler and Cfg gives more realistic results
⁉ No VAE needed
⭐ Feel free to leave Reviews for improvement ❤
[ENG version Below]
这个CKPT是由明快制作过程中得来的2D混合3D效果，具体为近景和人物、服装倾向于绘画风格，背景和其他元素倾向于照片风格，略带一些焦外的感觉。总体仍然比较适合各类服饰Lora的展现，但适合添加背景描述。
请注意：
一共有三个版本，分别将不同的流行模型作为主混对象，请依据你的喜好选择版本.
This CKPT is a 2D mixed with 3D effect obtained during the production of "CrispMix". Specifically, the close-up shots of characters and clothing tend to have a more illustrative style, while the background and other elements tend to have a photographic style, with a slight bokeh effect. Overall, it is still suitable for showcasing various types of fashion Lora, but is more suitable for adding background descriptions.
Please note:
There are three versions in total, each using a different popular model as the main mixing object. Please choose the version according to your preference.
agdzxbabbbg
"PastelRainier" is a derivative of "RainierMix".
Sampler: DDIM or DPM++ SDE Karras
Steps: 50~
Clipskip: 2
CFG Scale: 5-12
Denoise strength: 0.5-0.65
Negative prompts should be as few as possible.
The model has strong habits.
PastelRainier
Prompt:
(morning), 1girl, solo, looking at viewer, winter, cowboy shot, (downtown), cowboy shot, smile, black hair
===========================================================
Русскоязычных товарищей я приглашаю в наш уютный чатик по нейронным девочкам, и нейросетям в частности. Нас там не много, но все свои. Делимся артиками, фишками, общаемся и помогаем друг другу.
https://t.me/neuroaestheticschat
Так же там отвечу на ваши вопросы по модели если они есть.
===========================================================
To achieve a good result without using the hires fix.
To make the model universal, not tied to a specific style.
Avoid using a lot of quality tags, such as hyper-detailed, photorealistic, ultra realistic and others, so as not to overload the query.
Use a short negative prompt
A visual demonstration of the differences
The images are different from those attached to the first version, because the generation was done on a different hardware and operating system.
Set clip skip 1-2, ENSD: 31337, use samplers: DPM++ 2M Karass, Eular A, DDIM, CFG Scale 6-10 on average, but values above or below may also give good results.
(deformed, distorted, disfigured:1.3), EasyNegative, (bad_prompt:0.8), (bad_prompt_version2:0.8), poorly draw, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, (mutated hands and fingers:1.4)
(worst quality:1.4, low quality:1.4), (zombie, interlocked fingers), watermark, signature
这个模型是私炉的产物，整体风格偏幼化。它可以比较轻松的画出可爱风格的人物，但并非只能画萝莉风格人物，您可以尝试各种有意思的prompt，并且它画风景(背景)效果也很好。
关于v2版本，增强稳定性以及细腻程度，推荐参数如下:Steps: 30, Sampler: DPM++ SDE Karras, CFG scale: 7, Size: 512x768, Denoising strength: 0.57, Clip skip: 2, Hires upscale: 2, Hires steps: 25, Hires upscaler: R-ESRGAN 4x+ Anime6B.
Negative prompt:NG_DeepNegative_V1_75T, EasyNegative, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, (worst quality, low quality:1.4), (bad anatomy), (inaccurate limb:1.2), bad composition, inaccurate eyes, extra digit,fewer digits, (extra arms:1.2), (bad-artist:0.6), bad-image-v2-39000
The reason for this model's name is that it can easily create cute-style images, and its overall color tone is also visually appealing, making it suitable for landscape-style pictures as well. We hope you'll enjoy it!
Regarding the V2 version, to enhance stability and delicacy, the recommended parameters are as follows:
Steps: 30, Sampler: DPM++ SDE Karras, CFG scale: 7, Size: 512x768, Denoising strength: 0.57, Clip skip: 2, Hires upscale: 2, Hires steps: 25, Hires upscaler: R-ESRGAN 4x+ Anime6B.
Negative prompt:NG_DeepNegative_V1_75T, EasyNegative, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, (worst quality, low quality:1.4), (bad anatomy), (inaccurate limb:1.2), bad composition, inaccurate eyes, extra digit,fewer digits, (extra arms:1.2), (bad-artist:0.6), bad-image-v2-39000
x
ascendentreduxgoldroomgundamgirl
x
martianwarlord
Shin Yun-bok, Kim Hong-do, and Ukiyo-e lora combined steampunk girl and oriental punk mix.
vae kl f8 anime2
good luck
KenCanMix
This merged model is between 2.8D to realistic.
VAE is required: https://huggingface.co/stabilityai/sd-vae-ft-mse-original
Hires upscale + Dynamic Thresholding is Highly Recommended.
Recommended Parameters*:
Sampler: DPM++ SDE Karras
Steps: 25-50
Hires upscaler: Latent (bicubic antialiased) or ESRGAN_4x
Hires upscale: 1.5+
Hires steps: 15+
Denoising strength: 0.5-0.7
CFG scale: 6-9
or
CFG scale: 20-30 + Dynamic Thresholding
Mimic scale: 7-10
Threshold percentile: 99+
Mimic mode: Half Cosine Up
Mimic scale minimum: 3-7
CFG mode: Half Cosine Up
CFG scale minimum: 4-7
Clip skip: 2
*This is just how I use so far, feel free to play around and share with us any better one.
===v.1.0===
If you want Asian faces, LoRA is MUST, and the weight should be higher, try using [from:to:when] prompts. Or applying embeddings such as Ulzzang-6500
Credit to the authors of the following:
A simple random merge I did with two models I thought are very very good :>
More coming on the way
VAE：blessed.vae
THE merge recipie is simple merge
CamelliaMix_NSFW_v1.1(55) and cetusMix_whalefall (45)
-------------------------------------------------- -------------------
원한다면 Arca.live에 공유할 수 있습니다 :}
모델만큼은 아니지만^^
I trained this model mainly for assisting 3d style graphic effect design, to help designers to realize and express their ideas more easily, so that they can put more energy into some real design things (LOL).
Compared with txt2img, this model works better on img2img.
Here is some example of img2img work：
Use the word "style of dittotune" to trigger the style of the model
Because the current generation of some existing 3d effect model, may be due to sample reasons generated by the effect of a relatively strong sense of age and video game, so I try to use some more modern samples to train this model, I hope to help you in some daily design creation.
enjoy
style of dittotune3d render of
*Note that there are two different models on this page
※このページには二種類のモデルが存在することに注意してください
Note: If you like it, please give it a STAR MARKS !
,
caulkinumV1_RL was created with ingenuity to portray beautiful 2.5D characters and light.
This checkpoint was spawned accidentally after multiple iterations of hierarchical merging.
Therefore, the detailed recipe is already lost.
,
In addition, there are variant models to meet different demands.
"RL" is for 2.5D, and "RLCT" is for drawing anime characters on realistic backgrounds.
You will be amazed at the way 2D characters appear in realistic landscapes.
,
However, there is no doubt that Silicon28 is at the root of it and that it inherited the influence of ElysiumAnime_V1.
If someone likes it I will be very happy.
,
Below is a sample comparison with a highly respected model.
I am generally happy with the results, although I don't always get it right.
Note: ) Underscores at the beginning of the checkpoint names are given in AUTOMATIC1111 for sorting purposes and have no particular meaning.
,
,
※ 気に入っていただけたならぜひ★をつけてください！
,
caulkinumV1_RLは美麗な2.5Dキャラクターと光の表現を描くために工夫して作成したものです。
このチェックポイントは複数回の階層マージを繰り返して偶発的に産まれました。
そのため細かいレシピはもう失われています。
,
さらに、別の需要を満たすためにバリエーションモデルもあります。
末尾「RL」は2.5D用、「RLCT」は写実背景にアニメキャラクターを描くための物です。
まるで実在の風景に2Dキャラクターが現れる様は、あなたに驚きをもたらすでしょう。
,
しかしSilicon28が根底にあること、ElysiumAnime_V1の影響を受け継いでいることは間違いありません。
誰かが気に入ってくれたなら私はとても幸せでしょう。
,
下記に高名なモデルとの比較サンプルを掲載しておきます。
いつも必ずうまく錬成できるとは限りませんが、私はおおむね満足しています。
注釈 ) チェックポイント名先頭のアンダースコアはAUTOMATIC1111で並べ替えのために付与したもので特に意味はありません
,
,
,
,
,
caulkinumV2_AR for Anime Style
https://civitai.com/models/32537/caulkinumv2ar-for-anime-style
,
caulkinumV1_RL for semi Realistic Style
https://civitai.com/models/32958/caulkinumv1rl-for-25d-style
,
caulkinumV1_BR3 for Realistic Style
https://civitai.com/models/39670/caulkinumv1br3-for-realistic-style
,
,
Coffee will increase work efficiency and motivation.
コーヒーは作業効率を高めモチベーションをアップさせるでしょう。
,
Thank you for reading to the end.
I hope one of you will use it.
,
最後まで読んでくれてありがとうございます。
使用してくれるか方が一人でもいることを祈っています。
섹쉬하게
A model for creating photorealistic images. Very NSFW even with negative prompt added keywords "nude" and "naked", but can also create SFW.
Sample prompts:
"close up of a black girl smiling looking at the camera"
"highly detailed photography, spring, portrait of beautiful blonde woman standing in a park, top and miniskirt, perfect face, perfect body, large breasts, slightly thin skin, sharp focus, photo by Annie Leibovitz, intricate, natural lighting, high quality, 4k, cover photo"
"a 25 year old European girl with red hair wearing a white bikini top and denim skirt, posing for the camera by the beach, in a boat"
Negative prompt :
"nude, naked, child, deformed, deformed face, unreal, bad hands, bad fingers, monochrome, oversaturated, bad hands, lowers, 3d render, cinematic, cartoon, long body, blurry, duplicate, duplicate body parts, disfigured, poorly drawn, extra limbs, fused fingers, extra fingers, twisted, malformed hands, mutated hands and fingers, contorted, conjoined, missing limbs, logo, signature, text, words, low res, boring, mutated, artifacts, bad art, gross, ugly, poor quality, low quality"
Scale:
3-5
Steps:
50 - 100
clip_skip: 2-4
posing for the camera, posing for a photo, a close up of