many many checkpoints merged , including 2 of my own custom dreambooth creations..

clip skip 2 works well , i also am using 4x_NMKD-PatchySharp_240K upscaler , ( see second set of pictures i just made

Notice

The EXIF prompt is randomly generated for convenience and is created only for reference to large batch sample images, so the prompt may be completely different. Don't ask me why image and fromm are different.

BBMIX-LUCI-V2

She is a model who is luxurious and fresh but has her own idiocy.

BBMIX-LUCI-V1

Previously deleted version of LUCI.

Re-uploaded for friends asking for the previous version

referral prompt

• from above, from below

• shiny skin, (nice leg line:1.3),thick thighs,thin waist

negative

• {1$$EasyNegative|verybadimagenegative_v1.3}

VAE

• clearvae_main , clearvae_main2

• vae-ft-mse-840000-ema-pruned

We will continue to add sample images after finding good Loras so that we can copy and use EXIF in the sample post.

Precautions (Be sure to observe this)

1. Models may not be traded or sold. Because this is free. .

2. Models are not available for online paid services. (Free service available)

3. In using the model, all responsibility lies with the user.

How to high quality

1. You can output an image like the sample by using an extension to increase the quality. (All sample images were used with the extensions below)

• 1. Hires.fix -> SwinIR_4x or R-ESRGAN 4x+ Anime6B

• 2. Dynamic Thresholding (CFG Scale Fix)

• 3. Detection Detailer (must use)

• 4. SD upscaler or https://oo.pe/https://www.upscayl.org/

1.Hires.fix ( built-in ) or

2. Dynamic Thresholding

https://github.com/mcmonkeyprojects/sd-dynamic-thresholding.git

3.Detection Detailer

https://github.com/Bing-su/dddetailer.git

Questions that do not use the above four cannot be answered. Please note that images printed without using the four extensions may not look good.

TIP

In order to keep token 75, do not insert resolution, detail, or quality tokens. Since extension add-ons such as DD or DT handle it anyway, there is no need to insert tokens like the ones below.

bad prompt (do not use)

official art, unity 8k wallpaper, ultra detailed, ultra high res, 8k uhd, film grain, delicate, RAW, light particles, detailed skin texture, detailed armor texture, detailed face, intricate details, ultra detailed,

Reality Emphasis Prompt Excludes Detail Emphasis Prompt.

v3.0版本说明：

• 图片信息里的XXMix_4_v2893模型就是v30版本，只不过图片是在模型改名前生成的

• 1.很高兴向大家介绍XXMix_9系列的3.0版本。这个版本在泛用性和对LORA的支持上都有明显的加强，并且手部的表现要明显好于之前的版本。3.0版本是由v2.5、v2.6和XXMix_4这三个版本Mix而来。生成的图片我尽量不用任何Embedding模型，因为我发现有些Embedding模型比较隐晦，你不知道哪些Embedding模型起了作用哪些没起作用，从而不能还原图例。

• 2.如果你想还原图例，请先安装以下扩展：

• Adetailer:建议在生成图片时始终开启（如果你想90%以上还原图例，那么建议你在图片信息内查看adetailer是否已开启）。

• 注意:Adetailer需要下载一些模型https://huggingface.co/Bingsu/adetailer/tree/main，这里是模型地址。模型存放路径：webui/models/adetailer。没有找到adetailer文件夹自己建一个即可。

• Adetailer视频教程，这里我就贴娜乌斯嘉的教程喽https://www.bilibili.com/video/BV13s4y197cK/?spm_id_from=333.337.search-card.all.click&vd_source=8c2a86ab53df9752cdd75679f58834a6

• CFG Scale Fix:有需求的时候开启，会提高画面的质感。我用的默认数值7左右，如果是白天CFG数值可以稍微大一些，晚上数值要小一些。

• （经过我的测试，在第二台电脑上没有办法100%还原图例，我现在还不知道是什么原因，有可能是CFG Scale Fix这个扩展的问题，也有可能是分块VAE的问题，不过基本上你可以还原到90%-95%左右，对画面的影响不是很大。）

• 3.对于生成图片，个人的小心得：如果你得到了一张非常喜欢的图片，但是手部或其他部位的问题很严重，如果你不想用局部重绘修改的话，那么建议你在固定好seed之后，微调CFG的数值（每次调整0.2-0.3这种幅度来尝试），这样你就有可能在保持原图的基础上得到一张完美的图片。

• 4.在这里，我还想分享一个我喜欢的后缀句子，它可以让画面的表现力更强。当然，你可以根据需要修改句子中的单词来微调画面风格。这些单词包括：fantasy, high contrast, ink strokes, explosions, over exposure, purple and red tone impression , abstract, ((watercolor painting by John Berkey and Jeremy Mann )) brush strokes, negative space,

• 5.最后，如果你喜欢这次模型的更新，希望你可以把生成的好看图片分享出来。

Version 3.0 Description:

• The XXMix_4_v2893 model in the image information is actually the v3.0 version, but the images were generated before the model was renamed.

• Pleased to introduce the 3.0 version of the XXMix_9 series. This version has significantly improved in versatility and support for LORA, and the hand performance is significantly better than the previous versions. The 3.0 version is a mix of v2.5, v2.6, and XXMix_4. When generating images, I try not to use any Embedding models as much as possible because I have found that some Embedding models are more obscure, and you don't know which ones are working and which ones are not, which makes it difficult to restore the example.

• If you want to restore the example, please install the following extensions first:

• Adetailer: It is recommended to always enable it when generating images. If you want to restore the example by more than 90%, it is recommended to check whether Adetailer is enabled in the image information.

• Note: Adetailer requires downloading some models from https://huggingface.co/Bingsu/adetailer/tree/main. Here is the model address. The model should be stored in the path: webui/models/adetailer. If you cannot find the adetailer folder, please create one yourself.

• Adetailer Chinese Video Tutorial，这里我就贴娜乌斯嘉的教程喽https://www.bilibili.com/video/BV13s4y197cK/?spm_id_from=333.337.search-card.all.click&vd_source=8c2a86ab53df9752cdd75679f58834a6

• CFG Scale Fix: Enable it when needed, it will improve the quality of the image. I use the default value of about 7. If it is daytime, the CFG value can be slightly larger, and at night, the value should be smaller. (After my test, I cannot restore the example 100% on the second computer. I still don't know the reason. It may be a problem with the CFG Scale Fix extension or the block VAE. However, you can basically restore it to about 90%-95%, and the impact on the image is not significant.)

• For generating images, here is my personal experience: If you get a picture that you really like, but there are serious problems with the hands or other parts, and you don't want to use local redraw to modify it, then it is recommended to adjust the CFG value slightly (0.2-0.3 range) after fixing the seed. This way, you may get a perfect picture while keeping the original image.

• Here, I would like to share a suffix sentence that I like, which can make the image more expressive. Of course, you can modify the words in the sentence to fine-tune the image style. These words include: fantasy, high contrast, ink strokes, explosions, overexposure, purple and red tone impression, abstract, brush strokes ((watercolor painting by John Berkey and Jeremy Mann)), negative space.

• Finally, if you like the updates of this model, we hope you can share the beautiful images you generated.

------------------------------------------------------------------------------------------------------

v26-fp16-no-ema update

------------------------------------------------------------------------------------------------------

v2.6版本说明:

这版算小更新，优化了脸型，手的问题有优化，不过主要还是抽卡。大问题下个版本解决。

Version 2.6 release notes:

This version is a minor update that optimizes the face and hand issues. However, the main focus is still on the gacha system. The major issues will be addressed in the next version.

------------------------------------------------------------------------------------------------------

有人留言说模型基本不能用，麻烦新朋友看下自己的设置是否和图例的设置一样，除了全身图会有IMG2IMG放大的操作，其他图都是直出的。请一定先确定自己设置是否和图里一样哈！！！

V2.5版本的光影效果表现更好，支持更多幻想内容，调整了基础脸型，场景方面的表现更好。

V2.5 version has better lighting effects and supports more fantasy content. The basic face shape has been adjusted, and the performance in scenes has been improved.

------------------------------------------------------------------------------------------------------

适当调小(CFG Scale)的数值，可以得到与众不同的效果。

V2版本说明:

1.更换了默认脸。

2.更好的光影表现。

3.融合了更多模型，后面还会继续迭代。

4.如果想得到更好的皮肤质感，那么生成图片的时候不要开启高清修复，而是将生成的图片传入图生图模式，启用Tiled Diffusion，来进行放大，从而得到更真实的皮肤质感。

5.我会继续更新迭代这个大模型，希望能不断填充内容，让模型更具趣味性。

谢谢您的支持！

Version 2 Release Notes:

1. Changed the default face.

2. Improved lighting and shadow effects.

3. Added more models and will continue to iterate in the future.

4. For better skin texture, do not enable Hires Fix when generating images. Instead, use the "Tiled Diffusion" mode to enlarge the generated image and achieve a more realistic skin texture.

5. I will continue to update and iterate on this large model, hoping to add more content and make it more interesting.

Thank you for your support!

------------------------------------------------------------------------------------------------------

推荐参数

Recommended Parameters:

Sampler: DPM++ 2M Karras alt Karras or DPM++ SDE Karras

Steps: 20~40

Hires upscaler:4x-UltraSharp

Hires upscale: 2

Hires steps: 15

Denoising strength: 0.2~0.5

CFG scale: 6-8

clip skip 2

DEEP DARK MODEL

Negative prompt: (worst quality, low quality:1.4), (bad_prompt_version2:0.8), EasyNegative, badhandv4, text, name, letters, watermark

Steps: 20,

Sampler: DPM++ 2S a Karras,

CFG scale: 4,

Denoising strength: 0.5,

Hires upscale: 2,

Hires steps: 20,

Hires upscaler: R-ESRGAN 4x+ Anime6B

Clip skip: 2,

VAE: kl-f8-anime2.vae.pt

This is a model designed to generate small girl

Steps: 20,

Sampler: DPM++ 2S a Karras,

CFG scale: 7,

Denoising strength: 0.5,

bad prompt: (worst quality, low quality:1.4), (bad_prompt_version2:0.8), EasyNegative, badhandv4, text, name, letters, watermark

enable_hr: true

Hires upscale: 2,

Hires steps: 20,

Hires upscaler: R-ESRGAN 4x+ Anime6B

Clip skip: 2,

VAE: kl-f8-anime2.vae.pt

I'm trying to incorporate better color expression and characters that fit my aesthetic on the basis of "counterfeit" universality. Have fun playing!

recipe:

• 0.4 counterfeit30

• 0.6 (mix5)

  • 0.4 blackcat

  • 0.6 (mix4)

    • 0.4 navelorange21

    • 0.6 (mix3)

      • 0.6 (mix2)

        • 0.8 pastelmix

        • 0.2 colorbox

      • 0.4 (mix1)

        • 0.8 piledream

        • 0.2 cuteyukimix30

My first attempt at merge other models to get an interesting result.

All pictures were created using a sampler DPM++ SDE Karras, 30 steps, CFG 7, upscaler - 4xUltraSharp, denoising 0.4-0.5.

Ready for summer, Luscious Fruits brings you Strawberries and Cream.

A general purpose model mix, realistic, 2.5D and Anime, Beautiful girls, highly detailed faces, great backgrounds, easy prompts and lora friendly, It can do NSFW so prompt accordingly

Thanks to the original model creators, too many to mention , Enjoy

为夏天做好准备，Luscious Fruits 为您带来草莓和奶油。 通用模型组合，逼真，2.5D 和动漫，漂亮的女孩，非常详细的面孔，很棒的背景，简单的提示和 lora 友好，它可以做 NSFW，因此提示相应 感谢原模型制作者，不胜枚举，尽情享受

It's a realistic version of the fantasticmix

↓↓↓ fantasticmix2.5D ↓↓↓

https://civitai.com/models/20632/fantasticmix25d

An example is using dynamic thresholding. Reduce the CFG scale to 7 to 10 when not in use

VAE : vae-ft-mse-840000-ema-pruned.ckpt

This model checkpoint is a model created by merging.

This is a checkpoint I made by accident.

It is a merging of realistic and anime models.

I made it with 2.5D to 3D in mind, but

After all, it is 2.5D that expresses well

We recommend using a detailer.

IMPORTANT MATTERS(重要事项)

1. Highres-Fix is A Must! Highres-Fix: 2x, denoising:0.4-0.5 or 1.5x, denoising:0.5-0.65. (一定要做高清修复! 高清修复: 2倍, 重绘幅度:0.4-0.5 或 1.5倍, 重绘幅度:0.5-0.65)

2. Make Sure you are in the right CLIP if you want to replicate my job, some themes are CLIP=1,while others are CLIP=2.Suggest download the image and put it into PNG info to check the setting (如果想要复现,确保CLIP值要对! CLIP1和CLIP2要对!建议把图下下来然后放到PNG信息里面去查设置)

3. Most Prompts in Previous Version of GhostMix can produce similiar result in New Version of GhostMix (之前用的大多数Prompts在新版本也可以生成相似的结果)

4. All images I posted did not use Lora & Controlnet. (所有图片没有用Lora和Controlnet)

5. Textual Inversion&VAE: ng_deepnegative_v1_75t and easynegative ,don't use Bad-Hand V4 & V5！（用 ng_deepnegative_v1_75t和easynegative,别用BadHandV4,V5)

6. Sampler Suggest : DPM++ series , Steps: 20-30, CFG:5-7(7 is best)（采样方法建议 DPM++系列 , 步数20-30, CFG:5-7(7最好) ）

7. Suggest resolution: 512,768! mechanical girl theme is very sensitive to the resolution, not suggest make the aspect ratio too low.(建议分辨率:512,768! 机械少女主题对分辨率设置非常敏感，不建议设太低的宽高比)

If you want to support me, please buy me a coffee : https://ko-fi.com/ghostshell

如果想支持我，可以买杯咖啡给我：https://ko-fi.com/ghostshell

2023.5.21 GhostMix-V2.0 (fp16 pruned ver replaced)

UPDATE DETAIL(中文更新说明在下面)

Hello everyone, this is Ghost_Shell, the creator. The GhostMix-V2.0 significantly improves the realism of faces and also greatly increases the good image rate. In my tests at 512,768 resolution, the good image rate of the Prompts I used before was above 50%. It is more user-friendly. During making the GhostMix-V2.0, I adjusted 47 versions of the model and finally chose one of them.

大家好，这里是作者Ghost_Shell。这次GhostMix-V2.0大幅提升了脸的真实性，也大幅提升了良图率，在我测的512,768分辨率之下，之前用的Prompts良图率都在50%以上，对用户更加友好。这次在测试中一共调了47个版本的模型，最终选了一个。

Other Words I want to say(题外话):

To be honest, this may be the last version of GhostMix.On one hand, it is really inefficient to use 3060ti to make models. In the past two weeks, I have almost no free time except for making models and testing them. On the other hand, I temporarily feel that this model is almost at its limit and the space for improvement is really not high. I hope you like it. If you like the model, I hope you can post your images to Civitai. Many of the prompts I tested for GhostMix-V2.0 are from your posts, which is really important for me to test the model. If you can give it a 5-star rating, that would be great. If you are willing to support my work, please click: https://ko-fi.com/ghostshell. My goal is to buy a 4070 and work more efficiently on making models. Using a 3060ti to make models is really inefficient and it basically cannot be used to test high resolution images.

说实话，这可能是GhostMix的最后一个模型，一方面3060ti去做模型真的效率太低了…最近两个星期基本没有空闲时间，除了做模型，就是测模型。另外一方面，我暂时觉得这个模型近乎极限，能提升的空间确实不高了，希望大家喜欢。如果大家喜欢模型，希望大家能post自己的作品到Civitai，这次测试的很多Prompts就是从你们post里面来的，这对我测试模型真的很关键，如果能5星评价就更好。如果愿意支持我的工作，请点击：https://ko-fi.com/ghostshell。 我的目标就希望能换一块4070，更高效的去做模型，3060ti真的测模型效率太低了，而且基本没法测更高分辨率的图片。

2023.5.1 GhostMix-V1.2 (fp16 version uploaded)

UPDATE DETAIL(中文更新说明在下面)

THIS IS NOT A 3D MODEL! THIS IS NOT A 3D MODEL! THIS IS NOT A 3D MODEL!

If you like my model，please give me 5 Stars ,it will encourage me a lot. Thanks!

Color Problem ：Check VAE is kl-f8-anime2 ？颜色问题：查VAE是否为kl-f8-anime2？

GhostMix V1.2 is an absolutely astonishing model, and I think it is the strongest 2.5D model in Civitai right now. I think a update of the model should improve the model’s compatibility, good image rate and image details given the main structure of 90% generated images doesn’t change. So I use layer combination to combine models layer by layer. And I got this model after 9 different versions of “the final version of GhostMix V1.2”,LOL.This version of GhostMix V1.2 is a balance in terms of compatibility, good image rate and image details, although sometimes using the same Promts of GhostMix V1.1, may comes up a different result.But this doesn’t happen too much.

PS: The first image of GhostMix V1.2 is a nod to Mamoru Oshii’s version of Ghost in Shell in 1995, and my name Ghost_Shell is also a nod to this movie.

中文更新说明

GhostMix V1.2是绝对让你惊艳的模型，也是自己认为现在最强的2.5D模型。我认为模型的更新应该是基于现有的画面整体不大变的前提下，提高模型的成图率，兼容性和画面细节。所以我采用了分层融合，一共做了9个版本的“GhostMix V1.2最终版本”，最终得到了现在这个版本的GhostMix V1.2。这个版本的GhostMix V1.2在兼容性，成图率和画面细节表现比较平衡，虽然有时候会出现同样的Promts，出图改变的情况，但实测不多。

PS：GhostMixV1.2的头图是致敬1995押井守版Ghost in Shell 攻壳机动队的生成的，Ghost in Shell也是作者名字的由来。

2023.3.11 GhostMix-V1.0

Introduction(中文简介在下面)

First of all , I want to thank all the people who use this Checkpoint. And this is my first Checkpoint.All the sample image can be reproduced. This Checkpoint works well on both SFW and NSFW.THE NSFW PART IS VERY GOOD!!!
I uploaded this Checkpoint yesterday and from yesterday to today , I am still trying all the possibility of this Checkpoint. So if you try the model and find some good promts , I hope you can upload it and share with me, it will help me for the next version of GhostMix, Thank you agian!

Recommend Some Promts:

1. Fractal Art（highly recommend，awsome）

(masterpiece, top quality, best quality, official art, beautiful and aesthetic:1.2), (1girl:1.3), (fractal art:1.3),

1. Color Art

(flat color:1.3),(colorful:1.3),(masterpiece:1.2), best quality, masterpiece, original, extremely detailed wallpaper, looking at viewer,1girl,solo,floating colorful water

VAE&Textual Inversion:

VAE: kl-f8-anime2 or vae-ft-mse-840000-ema-pruned(anime suggest: kl-f8-anime2)

Textual Inversion: ng_deepnegative_v1_75t, easynegative

About Image Reproduction:

Some user said that they can not reproduce my result.Maybe the setting goes wrong.I just reproduce my cover image. If you want to reproduce my result, Checkpoint Model，Postive Promt，Negative Promt，Textual Inversion，Sampler Steps，Sampler，CFG，Resolution，Seed , ALL the things should be the SAME! Then be careful if you open controlnet or lora ,don't make them influnence your result.

中文简介

首先感谢每一个使用这个Checkpoint的人，这是我融的第一个Checkpoint。所有样图自测都可以复现。SFW和NSFW的图都挺漂亮的，NSFW的图非常棒。这个模型昨天上传到今天，我一直在尝试这个模型的可能性。希望使用这个Checkpoint的朋友们，如果你试了，觉得有不错Promts，欢迎上传图分享，让我也了解一下这个Checkpoint的可能性，也可以帮助我调下一个版本GhostMix，再次感谢。

推荐Promts:

1. 分型艺术（超级推荐，必出好图）

(masterpiece, top quality, best quality, official art, beautiful and aesthetic:1.2), (1girl:1.3), (fractal art:1.3),

1. 色彩艺术

(flat color:1.3),(colorful:1.3),(masterpiece:1.2), best quality, masterpiece, original, extremely detailed wallpaper, looking at viewer,1girl,solo,floating colorful water

VAE&Textual Inversion:

VAE:kl-f8-anime2或者vae-ft-mse-840000-ema-pruned(动画风建议kl-f8-anime2)

Textual Inversion:ng_deepnegative_v1_75t,easynegative

关于图片复现:

有同学好像没法复现我的图，可能是设置有点问题，刚刚我才把头图给复现了。注意几个点：Checkpoint 模型，正向Promt，反向Promt，Textual Inversion，迭代步数，迭代方法，CFG，分辨率，随机种子都必须一模一样！然后复现的话，要把controlnet和lora关掉，怕影响复现。

This model is a mix of various models. This is the mix I use on other model I made

It's doing well on generating photorealistic male and female, SFW and NSFW.

I HIGHLY recommend to use Hires Fix to have better results

Below is an example prompt.

Positive:

Use the prompt from posted images

Negative:

I recommend to use bad-hands-v5, easynegatives, bad-artist

Settings :

Steps: 30-150

Sampler: DDIM or UniPC

CFG scale: 7-14

Size: from 512x512 to 750x750

Denoising strength: 0.6

Clip skip: 1

Hires upscale: 2

Hires steps: 30-150

Hires upscaler: Latent (nearest)

New Update 22/5/2023:

V2 is released

if you want painterly / illustration style , use the V1.5

if you want 2.5D or realistic photography style , use the V2

New Update 20/5/2023 :
V1 update:

- the V1 just been reupload

-the loras in V1.5 are not merge with the checkpoint in V1.0

V1.5 update:

- now V1.5 ver change to safetensor

- the ckpt ver of V1.5 is no longger can be download

- the model have been update , with some loras that have been merged

model information :
this model are merge from

Meinamix, Chikmix and Darksushi

already baked VAE

recommended sampling method:
Sampler DPM++ SDE Karas : 20 steps

CFG Scale: 7

Resolution: 512x768, 768x512, 512x512, and 768x768

Hires.fix : R-ESRGAN 4x+Anime6b, with 7 steps at 0.1 up to 0.5 denoising

Clip Skip: 2

to find negative embeddings :

https://huggingface.co/embed/EasyNegative/tree/main

badhandv4 - AnimeIllustDiffusion - badhandv4 | Stable Diffusion Textual Inversion | Civitai

veryBadImageNegative - veryBadImageNegative_v1.3 | Stable Diffusion Textual Inversion | Civitai

VAE:ClearVAE - Main | Stable Diffusion Checkpoint | Civitai

some loras that already merge with this model :

https://civitai.com/models/25758?modelVersionId=31269

https://civitai.com/models/25769?modelVersionId=37110

https://civitai.com/models/58390/detail-tweaker-lora-lora

I hope everyone is happy with this model, can't wait to see your result!

Notice

The EXIF prompt is randomly generated for convenience and is created only for reference to large batch sample images, so the prompt may be completely different. Don't ask me why image and fromm are different.

BBMIX-KALI

The subject is on the large side, and the healthy lines are an attractive model.

It has a rich taste by expressing dark parts with pastels.

In addition, the cool features and body are attractive.

referral prompt

• from above, from below

• shiny skin, (nice leg line:1.3),thick thighs,thin waist

negative

• {1$$EasyNegative|verybadimagenegative_v1.3}

VAE

• clearvae_main , clearvae_main2

• vae-ft-mse-840000-ema-pruned

We will continue to add sample images after finding good Loras so that we can copy and use EXIF in the sample post.

Precautions (Be sure to observe this)

1. Models may not be traded or sold. Because this is free. .

2. Models are not available for online paid services. (Free service available)

3. In using the model, all responsibility lies with the user.

How to high quality

1. You can output an image like the sample by using an extension to increase the quality. (All sample images were used with the extensions below)

• 1. Hires.fix -> SwinIR_4x or R-ESRGAN 4x+ Anime6B

• 2. Dynamic Thresholding (CFG Scale Fix)

• 3. Detection Detailer (must use)

• 4. SD upscaler or https://oo.pe/https://www.upscayl.org/

1.Hires.fix ( built-in ) or

2. Dynamic Thresholding

https://github.com/mcmonkeyprojects/sd-dynamic-thresholding.git

3.Detection Detailer

https://github.com/Bing-su/dddetailer.git

Questions that do not use the above four cannot be answered. Please note that images printed without using the four extensions may not look good.

TIP

In order to keep token 75, do not insert resolution, detail, or quality tokens. Since extension add-ons such as DD or DT handle it anyway, there is no need to insert tokens like the ones below.

bad prompt (do not use)

official art, unity 8k wallpaper, ultra detailed, ultra high res, 8k uhd, film grain, delicate, RAW, light particles, detailed skin texture, detailed armor texture, detailed face, intricate details, ultra detailed,

Reality Emphasis Prompt Excludes Detail Emphasis Prompt.

Hello everyone, I'm Moogone and I'm back again. Today, I bring you a super awesome large model that was generated using over 1500 images with accompanying text. It can be described as a collection of exhibition halls/museums, and you don't even need to trigger it with any keywords - you can generate the desired results using natural language.

I request that you all submit the results generated by this model and honestly rate them for me. Thank you all so much, as I'm really curious to know if this model actually works.

If you have any questions, you can add me on WeChat at Moogone. I also welcome any business inquiries.

大家好，我，Moogone又回来了，今天我带来的是一个超级牛逼的大模型，这个模型用了1500多张带文本的图像生成，可以称之为展览馆/博物馆大集合，你甚至不需要用任何关键词触发，你只需要用自然语言就能生成想要的结果。 这次拜托大家将生成的结果发上来，并且诚实地给我打分，谢谢大家了，因为我太想知道这个模型究竟是不是行得通。 如果遇到任何问题可以加我的微信：Moogone，商业洽谈也同样支持。

A more anime/digital style model compared to ConsistentFactor.

This model will only be available in a pruned FP16 version.

Recommend: DPM++2M Karras, Steps: 32+, Hires fix 0.3 - 0.5, CFG 6 - 8.

In my never ending pursuit to make ConsistentFactor as realistic as possible I realised something, each step closer to realism took me two steps away from artistic flair. So I thought why not create a model that is fun and artistic, a model that allows you to have more expression?

I give you Project Aurora. Please enjoy irresponsibly.

The second model that tries to merge

Based on kiwi4 made by kiwi, merge with various models, some components overlap with CursepoisonMix to

The purpose is to make cute girls with big breasts, so it is more NSFW

I like hyperHeavenOrange model, but for some reason there is no safetensors version of it, so I've made a mix with perfectDeliberate, and add vae into it. Here is what I've get)

Feel free to ask any questions here in comments, or in my discord channel.

Also I am making games with AI arts. They will be free in the future, but if you want to participate in making or have an early access - you can support me on patreon)

Also my wet hair Lora was banned here, I dunno why. You can download the last version of it from my patreon for free.

sport

With Stable Diffusion, we can now create artificial intelligence art new images using our trained images. In this model, we can create images of new images containing modern building designs and a real photo style called zaha-hadid style

This model belongs to the SD2.1 series.

It is a further refined model, which underwent additional learning based on the hakoA model that was itself finetuning trained from the WD1.5beta2.

It is characterized by its kindness illustrations.

The "hakoMay" series includes A/B/C/D, but currently only D is published on civiitai.

The use of Negative Embedding from "Mayng" and upscaling with Hires fix (using tools like ESRGAN or R-ESRGAN) is recommended.

hakoMayA/B/C and Mayng Link
https://huggingface.co/852wa/hakoMay/tree/main

Welcome to the Test Lab for CyberRealistic and other fascinating models (Like Semi-Realistic Model) that are not intended for separate release but are intriguing enough for certain individuals. The Beta version of CyberRealistic will not be published on the CyberRealistic page, but it will be made available exclusively in this space ("3.0 [BETA]" is the final beta release on the CyberRealistic page).

For information about the models, kindly refer to the model description. It contains all the relevant details/specifics regarding the various models available.

Due to different styles, RuviMix_V1 and RuviMix_V2 will be separated into different models so I can work on updates for both! (^o^)7

• RuviMix_V1 ➡ KyuMix_v1.0

• RuviMix_V2 ➡ RuviMix_v1.0

• RuviMix_Style ➡ RuviStyle_v1.0

⭐ All of my stuff will be free of use! Support me on Kofi~

https://ko-fi.com/ruvikyu

期望评论多多返图 :)

推荐参数

Recommended Parameters:

Sampler: DPM++ SDE Karras or DDIM

Steps: 20~40

Hires upscaler: Latent (bicubic antialiased)

Hires upscale: 1.4

Hires steps: 15

Denoising strength: 0.2~0.5

CFG scale: 6-8

clip skip 2

Multi-model merge for good stylized images edging on realism. Works well with a number of anime-based Lora's.

This is the ultimate Henry Cavill trained Model Checkpoint trained on 17k steps with a whopping 170 images and includes over 4k regularization images.

RECOMMENDED SETTINGS SD 1.5:

Steps: 25

CFG: 5

Trigger word: hnrycvll

Tip#1: Try to use the above Steps and CFG settings first and tweak from there. I think 15 steps may be the minimum acceptable quality.

Tip#2: The model is very biased towards hnrycvll tag, so you might need to decrease the hnrycvll tag (as an example with :0.25 ~ :0.75) or increase weight for other parts of your prompts.

As a favor, please let me know your thoughts, feedback and give a review rating. I would truly appreciate it!

拿counterfeit2.5, perfect world, cetusmix, mixprov4, hassakuHentaiModel_v12等等做mbw merging整出来的，就乱塞

Detail Tweaker LoRA (细节调整LoRA) - v1.0 | Stable Diffusion LoRA | Civitai

这LoRA必须用

footjob

Cinema_4Dream is the best I can do without training a model on Cinema 4D. Im not saying this is accurate but it’s REALLY FUN!!!!  Show me what you got. 

21 Ingredients…  (First 5 are the spicy triggers): 

1. (FLUIDART: ) 

2. (LIQUID SPLASH: )—FeverDream

3. (Knollingcase: )

4. (FOOD_CRIT: ) —Jak’s Creepy Critters

5. (Beeple:)

6. Color Fusion

7. 3D Magic Space

8. Crystal Clear

9. Holographic Model

10. Unreal Engine 5

11. Slimy’s Super Model V2

12. Babes V2

13. AETHER

14. Artius

15. Orusium

16. Vodka V2

17. AW PORTRAIT

18. Project Cryengine

19. Project Unity Beta V2

20. Dreamful V3

21. RmadaArt V8 Cold Vae

22. Sentinel Diffusion

Модель включает в себя лучшее, на мой взгляд, сочетание реалистичных стилей. Она соединила в себе более 15 различных моделей в четко выверенных пропорциях, что позволяет получать гипер реалистичные портреты невероятного качества. Модель натренирована на многих знаменитостях, рисует их лучше, чем любая Лора или Ликорис. Также содержит реалистичных nsfw контент.

The model includes the best, in my opinion, combination of realistic styles. It combines more than 15 different models in well-adjusted proportions, which allows you to get hyper realistic portraits of incredible quality. The model is trained on many celebrities, draws them better than any LoRaor Lycoris. Also contains realistic nsfw content.

这是一个大杂烩模型，它融合了许多的模型和lora，该模型更偏向于生成真人图片，毕竟瑟瑟才是第一生产力

This is a hodgepodge model that combines many models with Lora, which tends to generate real-life images, as pornography is the primary productivity

have fun

推荐关键词:Best quality, masterpiece, ultra high res, (photorealistic:1.4),

recommended positive prompts: Best quality, masterpiece, ultra high res,(photorealistic:1.4)

推荐负面关键词:(worst quality, low quality:1.4),ng_deepnegative_v1_75t and badhandv4

recommended negative prompt: (worst quality, low quality:1.4),ng_deepnegative_v1_75t and badhandv4

推荐参数Recommended Parameters:

Sampler: DPM++ 2M Karras or DPM++ SDE Karras

Steps: 20~40

Hires upscaler: R-ESRGAN 4x+ or 4x-UltraSharp

Hires upscale: 2

Follow on twitter, requests please DM at https://twitter.com/fitCorderAI

Anime: Tsunade, Orihime, Beerus

Body Type: Double Thick Thighs, Perky Breasts, Round Breasts, Max Cleavage, Amazon Goddess, Big ol butts

Fashion: Crop Tops, bodycon minidress, Scrunchbutt leggings, Cybergoth, Nerdy, bodycon skirts, bodycon shorts, Tsunade Kimono, Bicycle shorts

Here is my base model. FitCorderMix. My realistic mix is fCBlendMix. My anime mix is fCAnimeMix.

Model is a result of mix'n'matching different trained or merged checkpoint with little experimentation with discarding/removing some weights.

Main goal was to create model that primary focus is men and content creation related to homosexuality, male relationships and NSFW gay content.

It's experimentation done just to learn before making a proper trained checkpoint.

Version 2 is based on my checkpoint merge and has been trained on additional data set containing 96 images.

Still working on fully trained checkpoint.

All generated samples has been made using Vladmandic or InvokeAI

If any picture has been upscaled I either used build-in upscaler in InvokeAI or UltraSharp x4

All samples are raw, meaning no in-painting or tweaking them using unified canvas (InvokeAI) or Controlnet v1.1. Only face restoration has been used, mainly CodeFormer with weight around or less than 0.35.

Non-standard resolutions i.e anything other than 512x512 or 768x768 has been made with Tiled Diffusion/Vae built-in Vladmandic's custom fork.

Anime tags and normal sentences work well, Unet & Text encoder has been trained to recognise both, although for best result you'll still probably guide model with increasing and decreasing weights i.e (word, tag or sentence)+ or - in InvokeAI or (word, tag or sentence:1.2)

Leave a review, and comment on what you wish to see to be improved or included in future releases, but please bear in mind this is a side project and a hobby so I can only do when I have any spare time.

With your support, I can continue to develop.
You can also participate in the testing of the model under test.

皆さんの応援があれば、私は開発を続けることができます。
また、テスト中のモデルのテストに参加することもできます。

https://ko-fi.com/breakd

[Other series include]

BreakDomain (illustration output models )
https://civitai.com/models/50520/breakdomain

BreakDomainRealistic (illustration output models that are more realistic)
https://civitai.com/models/54917/breakdomainrealistic

BreakRealize LoRA (LoRA that adjusts to a realistic representation)
https://civitai.com/models/61810/breakrealize-lora

BD_Marumi LoRA (LoRA to create an animated expression)
https://civitai.com/models/70877/bdmarumi-lora

[About this model]
This version focuses primarily on outputting cartoon-like illustrations by performing additional learning on BreakDomain_m2150.

More cartoon-like illustrations are output in the basic.

It is (should be) strong for both mechas and buildings, as well as for detailed drawings, without changing.

今回のバージョンは、BreakDomain_m2150に追加学習を行うことでアニメっぽいイラストの出力を主眼に置いています。

・よりアニメっぽいイラストが基本で出力されます。

・変わらず、メカにも建物にも、詳細な描画にも強い（はず）です。

No baked VAE.
The recommended VAE is "vae-ft-mse-840000-ema-pruned.ckpt".
If you try it and make a good one, I would be happy to have it uploaded here!
The merging source is listed in each version detail.

VAEは焼いてません。
おすすめのVAEは"vae-ft-mse-840000-ema-pruned.ckpt"です。
使ってみて、いいのができたら、ぜひここにアップしてもらえると嬉しいです！

Follow on twitter, requests please DM at https://twitter.com/fitCorderAI

Anime: Tsunade, Orihime, Beerus

Body Type: Double Thick Thighs, Perky Breasts, Round Breasts, Max Cleavage, Amazon Goddess, Big ol butts

Fashion: Crop Tops, bodycon minidress, Scrunchbutt leggings, Cybergoth, Nerdy, bodycon skirts, bodycon shorts, Tsunade Kimono, Bicycle shorts

Here is my base model. FitCorderMix. My realistic mix is fCBlendMix. My anime mix is fCAnimeMix.

slappin

You can now run this model on RandomSeed 🙂

The pursuit of perfect balance between realism and anime, a semi-realistic model aimed to achieve beautiful realistic faces with sexy hentai bodies.

This model aims to be flexible with all kinds of NSFW/hentai concepts, so a large portion of the merge will be hentai models.

A simple merge of Counterfeit-V3.0 by rqdwdw and Rev Animated by s6yx

please check out the original creator's work and support them.

I use this merge to create slightly more realistic anime depictions. use with a anime style VAE like anything v4 for softer colours.

NVJOBMagicCircle v1.0. This is a model for generating magic summoning circle assets.

This is a model of generating magic summoning circle images (for video games and more). It is trained on a large dataset of summoning magic circle images, allowing her to create new unique summoning magic circles based on the training data.

Game developers can use this model to create their own magic summoning circle, allowing them to create unique visuals in their games.

With this model, developers can save time and effort that would otherwise be spent manually creating each magic summoning circle.

Stable Diffusion Parameters:

Sampling method - Euler a

Sampling steps - 30-80

Resolution - 768x768

CFG Scale - 4-12

Or

Sampling method - DPM++ 2M Karras

Sampling steps - 23-28

Resolution - 768x768

CFG Scale - 7-10

For higher resolution use Hires. fix or upscale.

Prompts examples:

• nvjobmagiccircle magic summoning circle, various symbols, pentagramus, white background, intricate

• nvjobmagiccircle magic summoning circle, sun, moon, hieroglyphs, symbols, white background, black and white

• nvjobmagiccircle magic dragon summoning circle, inscriptions, symbols, white background, black and white

• nvjobmagiccircle magic summoning circle, demonic, infernal portal, inscriptions, symbols, white background, black and white, simple, symmetrically

• nvjobmagiccircle magic summoning circle, a circle with many different symbols in it, including the names of all the zodiac signs and the numbers of all the stars, magic circle, summoning circle, black magic circle on white background, on a white background, black and white, abstract sacred geometry, complicated, with symbols, inscriptions, signatures

Negative prompts examples:

poor quality, vignetting

nvjob.github.io/donate