This is my first and likely only attempt at merging models. I have no idea what I'm doing and just ran through some tutorials and hit buttons. This model is a merge of 3 different 'cartoon' style models to give a blend of more 'western' stylizing while gaining a lot of responsiveness to prompts. Seriously, no need for a prompting guide, it responds to all styles, including anime tags and 'natural language' sentence fragments. This model works well with most LoRAs and negative embeddings. It struggles with hands a bit still and the occasion extra limbs, but otherwise outputs are solid.

All images were generated using only prompting, via an advanced wildcard extension called Umi AI. One of the unpublished source models used for this merge was created by a member of their team. Check out their published model Macross V2.

There is no VAE baked in. I recommend the standard Stable Diffusion VAEs, Clear VAE, or my own Anime VAE.

I stand on the shoulders of giants. Credit to CivitAI for providing this space for us, and to the community that seeks ever greater levels of perfection.

Like all checkpoints since the originals released by Stable Diffusion, this model is responsive to age related keywords. It is also capable of producing NSFW content. What you do with this model is your choice. I suggest not making questionable images by using negative prompting as needed. I am marking this model as intended for mature audiences because of this.

Ce modèle a été entraîné avec ~15-20 images haute résolution du sujet trouvé sur le web et le modèle v1-5-pruned-emaonly.ckpt comme base en utilisant le Colab Dreambooth de Shivam à la fin d'octobre 2022.

À la base un fichier checkpoint, il a seulement été converti en safetensors avec l'option Checkpoint Merger de l'interface Automatic1111. FP16 et Baked-in VAE.

This is a model that was trained with ~15-20 high resolution images of the subject found on the web and v1-5-pruned-emaonly.ckpt model as base using Shivam's Dreambooth colab in late October 2022.

Initially a checkpoint file, it was only converted to safetensors using the Checkpoint Merger option in Automatic1111. FP16 and Baked-in VAE.

***

Shivam Shrirao's colab:

https://colab.research.google.com/github/ShivamShrirao/diffusers/blob/main/examples/dreambooth/DreamBooth_Stable_Diffusion.ipynb

Baked-in VAE:

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

negative textual inversions:

https://civitai.com/models/7808/easynegative

https://huggingface.co/nick-x-hacker/bad-artist

https://civitai.com/models/17083/bad-picture-negative-embedding-for-chilloutmix

extension:

https://github.com/Bing-su/adetailer

***

Ce modèle fourni par jeanguylafleur et mis à disposition exclusivement sur civitai.com a été créé strictement à des fins ludiques et éducatives.

Il n'est pas destiné à être utilisé de manière malveillante.

Ni l'auteur de ce modèle ni civitai.com ne pourront être tenus responsables d'une mauvaise utilisation ou d'une mauvaise application du modèle.

L'utilisateur assume la pleine responsabilité de toute utilisation ou conséquence qui pourraient découler de l'utilisation du modèle et est strictement interdit de commercialiser ou de privatiser le modèle pour son usage à but lucratif.

Veuillez utiliser de manière responsable.

Notez qu'il n'y a aucun plan pour entraîner davantage le modèle ou développer une version LoRA.

This model provided by jeanguylafleur and made available exclusively on civitai.com was created strictly for fun and educational purposes.

It is not intended to be used in any nefarious manner.

Neither the author of this model nor civitai.com shall be held liable for any misuse or misapplication of the model.

The user assumes full responsibility for any use or consequences that may arise from the use of the model and is strictly prohibited from commercializing or privatizing the model for their own for-profit usage.

Please use responsibly.

Note that there are no plans to further train the model or develop a LoRA version.

the model trained in february has a pronounced nsfw style. please use it in appropriate situations.

Ce modèle a été entraîné avec ~15-20 images haute résolution du sujet trouvé sur le web et le modèle v1-5-pruned-emaonly.ckpt comme base en utilisant le Colab Dreambooth de Shivam à la fin d'octobre 2022.

À la base un fichier checkpoint, il a seulement été converti en safetensors avec l'option Checkpoint Merger de l'interface Automatic1111. FP16 et Baked-in VAE.

This is a model that was trained with ~15-20 high resolution images of the subject found on the web and v1-5-pruned-emaonly.ckpt model as base using Shivam's Dreambooth colab in late October 2022.

Initially a checkpoint file, it was only converted to safetensors using the Checkpoint Merger option in Automatic1111. FP16 and Baked-in VAE.

***

Shivam Shrirao's colab:

https://colab.research.google.com/github/ShivamShrirao/diffusers/blob/main/examples/dreambooth/DreamBooth_Stable_Diffusion.ipynb

Baked-in VAE:

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

negative textual inversions:

https://civitai.com/models/7808/easynegative

https://huggingface.co/nick-x-hacker/bad-artist

https://civitai.com/models/17083/bad-picture-negative-embedding-for-chilloutmix

extension:

https://github.com/Bing-su/adetailer

***

Ce modèle fourni par jeanguylafleur et mis à disposition exclusivement sur civitai.com a été créé strictement à des fins ludiques et éducatives.

Il n'est pas destiné à être utilisé de manière malveillante.

Ni l'auteur de ce modèle ni civitai.com ne pourront être tenus responsables d'une mauvaise utilisation ou d'une mauvaise application du modèle.

L'utilisateur assume la pleine responsabilité de toute utilisation ou conséquence qui pourraient découler de l'utilisation du modèle et est strictement interdit de commercialiser ou de privatiser le modèle pour son usage à but lucratif.

Veuillez utiliser de manière responsable.

Notez qu'il n'y a aucun plan pour entraîner davantage le modèle ou développer une version LoRA.

This model provided by jeanguylafleur and made available exclusively on civitai.com was created strictly for fun and educational purposes.

It is not intended to be used in any nefarious manner.

Neither the author of this model nor civitai.com shall be held liable for any misuse or misapplication of the model.

The user assumes full responsibility for any use or consequences that may arise from the use of the model and is strictly prohibited from commercializing or privatizing the model for their own for-profit usage.

Please use responsibly.

Note that there are no plans to further train the model or develop a LoRA version.

Ce modèle a été entraîné avec ~15-20 images haute résolution du sujet trouvé sur le web et le modèle v1-5-pruned-emaonly.ckpt comme base en utilisant le Colab Dreambooth de Shivam à la fin d'octobre 2022.

À la base un fichier checkpoint, il a seulement été converti en safetensors avec l'option Checkpoint Merger de l'interface Automatic1111. FP16 et Baked-in VAE.

This is a model that was trained with ~15-20 high resolution images of the subject found on the web and v1-5-pruned-emaonly.ckpt model as base using Shivam's Dreambooth colab in late October 2022.

Initially a checkpoint file, it was only converted to safetensors using the Checkpoint Merger option in Automatic1111. FP16 and Baked-in VAE.

***

Shivam Shrirao's colab:

https://colab.research.google.com/github/ShivamShrirao/diffusers/blob/main/examples/dreambooth/DreamBooth_Stable_Diffusion.ipynb

Baked-in VAE:

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

negative textual inversions:

https://civitai.com/models/7808/easynegative

https://huggingface.co/nick-x-hacker/bad-artist

https://civitai.com/models/17083/bad-picture-negative-embedding-for-chilloutmix

extension:

https://github.com/Bing-su/adetailer

***

Ce modèle fourni par jeanguylafleur et mis à disposition exclusivement sur civitai.com a été créé strictement à des fins ludiques et éducatives.

Il n'est pas destiné à être utilisé de manière malveillante.

Ni l'auteur de ce modèle ni civitai.com ne pourront être tenus responsables d'une mauvaise utilisation ou d'une mauvaise application du modèle.

L'utilisateur assume la pleine responsabilité de toute utilisation ou conséquence qui pourraient découler de l'utilisation du modèle et est strictement interdit de commercialiser ou de privatiser le modèle pour son usage à but lucratif.

Veuillez utiliser de manière responsable.

Notez qu'il n'y a aucun plan pour entraîner davantage le modèle ou développer une version LoRA.

This model provided by jeanguylafleur and made available exclusively on civitai.com was created strictly for fun and educational purposes.

It is not intended to be used in any nefarious manner.

Neither the author of this model nor civitai.com shall be held liable for any misuse or misapplication of the model.

The user assumes full responsibility for any use or consequences that may arise from the use of the model and is strictly prohibited from commercializing or privatizing the model for their own for-profit usage.

Please use responsibly.

Note that there are no plans to further train the model or develop a LoRA version.

⚝⚝⚝⚝⚝⚝⚝⚝⚝⚝⚝⚝⚝⚝⚝⚝⚝🔥🐉 WND NOW UPDATED TO V2.0! 🐉🔥⚝⚝⚝⚝⚝⚝⚝⚝⚝⚝⚝⚝⚝⚝⚝⚝⚝

(PRUNED MODEL UPLOADING SOON)

FOR ALL INTENTS & PURPOSES THIS IS THE ANIME VERSION OF DNW!

It’s still a bit flavored to younger faces so (mature adult) may be necessary.

A bit less NSFW heavy but you can keep it in the negative to be sure.

Very variable and very good at fantasy! w/ amazing backgrounds!

✔️ANIME STYLE
✔️ILLUSTRATION
✔️FANTASY STYLE
✔️ANALOG STYLE
✔️PHOTOREALISTIC

***USE CLIP SKIP 2 FOR THIS MODEL! YOU CAN DO CLIP SKIP 1 AS WELL BUT 2 IS BEST!***

READ ME! THERE IS INFO ON HOW YOU CAN GET THE MOST OUT OF THIS MODEL!

There is no embedded VAE but it was designed to be used with this:

☞ vae-ft-mse-840000-ema-pruned.ckpt

I recommend using the following negatives:

EasyNegative (The all around catch all. Always good in a bind)
badhandv4_anime (absolutely your go to neg for anime hands)
bad-hands-5 (good for the more realistic images but will not work amazingly for anime)
bad-artist \ bad-artist-anime (I’ve had good and bad luck)
bad_prompt \ bad_prompt_version2 (works very good sometimes)
(I typically use (bad-hands-5) & (bandhandv4_anime) at the same time to cover more bases)

*** Note: that the example images are provided as a basis of reference and raw output. In most cases untouched other than mild inpainting for the eyes or face in a few examples. *** THESE SHOULD BE EASILY REPRODUCIBLE RESULTS! IF YOU HAVE QUESTIONS PLEASE ASK 🗪

Note: There is a full & pruned version of this model available. This is a complex merge so even the pruned is also large as well.

Here are some optimal example settings for you to start with, but please keep in mind YMMV!

Steps 20-30 = Sweet Spot / 15-150
Sampler DPM++ 2M Karras, DPM++ SDE Karras, Euler A, DDIM,
CFG scale 4-9.5 = Sweet Spot / 3-20
Size 512x768, 768x512, 640x840, 840x640, 600x896, 896x600, (any size)
Clip skip 2
Hires Fix Enabled
Upscale by 1.5-2
Hires Steps Equal to Half or Exact amount of Steps or higher
Upscaler Remacri Upscaler, Lollypop Upscaler, 4x_NMKD_DigArt_10k|

_________________________________ (Older Info from version 1.5) _________________________________

A handpicked and curated merge of the best of the best in waifu’s, anime, 2D, and of course, fantasy environments, characters & creature designs. It doesn’t do everything but what it can do off the bat is a pretty damned amazing images in anime styles 2 - 2.5D quite effectively. 🎨

Specializes in illustrated, semi-realistic, painterly, subjective reality and a 2.5d aesthetic with semi real to real backgrounds. Backgrounds that look like high quality anime or 3d rendered, game backgrounds.

It does styles and illustration, and artists based prompts pretty damned well and adapts to most LORAS with ease, it DEFINITELY leans a bit towards nudity / NSFW and also more towards younger looking girls. (Look I didn’t plan this… the merges just made it that way.) I suggest a (((kids))), (((child))), (Young:1.5-2.0) in your negative and a (mature adult:1.5-2.0) in your positive.

However… it will also work with Clip Skip 1 better for prompts that are going after a specific art or artists styles. (Unsure if this is directly affected by LORA’s will have to test more) Example:

Notice that the art & artist style of the prompt comes out more in 1 and 2 has more of the industrial / cyber aspects. Play with it and see what works best for you.

SHOW ME WHAT YOU MAKE WITH THIS!! 😉

Here are some example image comparisons with some of the most common / top anime oriented models and also my previous model Dungeons N Waifu’s v2.2:

I was asked recently how to get higher quality images like the examples and about blurred eyes and faces:

Blurred eyes, or sometimes warped faces are not that uncommon in SD and sometimes require an inpaint to pull off. Most of my examples are not inpainted. But a few are.

First off when you run txt2img ALWAYS use HIRES FIX!

latent (nearest or exact) upscale / denoise 0.4-0.7 (Complete variable - depends on the type and complexity of the image. YMMV!)

Upscale by 1.5-2 but no more than that.

This will get you a pretty good base image to work with.

Afterwards… You can always send your txt2img picture to inpaint on the bottom right under the result area > select the face or eyes > lower the denoise strength to 0.5-0.57. > make sure your seed is set to random.

masked content = fill / inpaint area = whole picture ====== for faces

masked content = fill / inpaint area = only masked ====== for eyes

With “whole picture” selected for larger inpaint target aka faces (or hands) you may need the denoise to be lower to pick up more of the original image. 0.53-0.56

Now with “only masked” and a smaller target like eyes you get a little more freedom so your denoise can be 0.54-0.57

Run a batch of 4-5 (or more) for the faces… go through pick the best one… if you’re lucky you got the eyes and face in one go… if not you may need to choose the best face… send back to inpaint again… select just the eyes… and rerun a new batch (changing it to only masked and the settings described above for eyes.)

Finally when you get it all together send to extras:

Resize to 1.5-2

Upscale 1= Nearest
Upscale 2= R-ESERGAN 2x or 4x
But google & get yourself Remacri Upscaler and Lollypop Upscaler
4x_NMKD_Superscale-SP_178000_G

Upscaler 2 is what will get you there. If you want super sharp / realism images you choose NMKD

You want a good all around upscaler that can do nearly any subject you choose Remacri

If you’re working on toons, anime, animated, cell shaded you choose Lollypop

Each of these is unique and so is their outputs if you want to compare simply change the pull down and run off the various types and contrast / compare the finished results.

For the more advanced upscale: Get yourself Ultimate SD Upscale
(click the link for a basic tutorial on how to get it and how to use it.)

Good Luck & Have Fun!

Ce modèle a été entraîné avec ~15-20 images haute résolution du sujet trouvé sur le web et le modèle v1-5-pruned-emaonly.ckpt comme base en utilisant le Colab Dreambooth de Shivam à la fin d'octobre 2022.

À la base un fichier checkpoint, il a seulement été converti en safetensors avec l'option Checkpoint Merger de l'interface Automatic1111. FP16 et Baked-in VAE.

This is a model that was trained with ~15-20 high resolution images of the subject found on the web and v1-5-pruned-emaonly.ckpt model as base using Shivam's Dreambooth colab in late October 2022.

Initially a checkpoint file, it was only converted to safetensors using the Checkpoint Merger option in Automatic1111. FP16 and Baked-in VAE.

***

Shivam Shrirao's colab:

https://colab.research.google.com/github/ShivamShrirao/diffusers/blob/main/examples/dreambooth/DreamBooth_Stable_Diffusion.ipynb

Baked-in VAE:

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

negative textual inversions:

https://civitai.com/models/7808/easynegative

https://huggingface.co/nick-x-hacker/bad-artist

https://civitai.com/models/17083/bad-picture-negative-embedding-for-chilloutmix

extension:

https://github.com/Bing-su/adetailer

***

Ce modèle fourni par jeanguylafleur et mis à disposition exclusivement sur civitai.com a été créé strictement à des fins ludiques et éducatives.

Il n'est pas destiné à être utilisé de manière malveillante.

Ni l'auteur de ce modèle ni civitai.com ne pourront être tenus responsables d'une mauvaise utilisation ou d'une mauvaise application du modèle.

L'utilisateur assume la pleine responsabilité de toute utilisation ou conséquence qui pourraient découler de l'utilisation du modèle et est strictement interdit de commercialiser ou de privatiser le modèle pour son usage à but lucratif.

Veuillez utiliser de manière responsable.

Notez qu'il n'y a aucun plan pour entraîner davantage le modèle ou développer une version LoRA.

This model provided by jeanguylafleur and made available exclusively on civitai.com was created strictly for fun and educational purposes.

It is not intended to be used in any nefarious manner.

Neither the author of this model nor civitai.com shall be held liable for any misuse or misapplication of the model.

The user assumes full responsibility for any use or consequences that may arise from the use of the model and is strictly prohibited from commercializing or privatizing the model for their own for-profit usage.

Please use responsibly.

Note that there are no plans to further train the model or develop a LoRA version.

太晚了不修了。

目前手还是会崩，不过能roll出来较为正常的手指了

其他的目前无能为力

tag识别程度的话。。。。这画风要啥识别（其实基本元素能识别，就是花里花哨）

It's too late to fix it.

The hand still breaks off, but it rolls out a more normal finger

Nothing else can be done for now

tag recognition degree... What does this painting style need to recognize (in fact, the basic elements can be recognized, is the fancy)

NeverEnding Dream (a.k.a. NED)

This is a dream that you will never want to wake up from

Add a ❤️ to receive future updates. This took much time and effort, please be supportive 🫂
Do you like what I do? Consider supporting me on Patreon 🅿️ or feel free to buy me a coffee ☕

V1.22 update: thanks to Bokus for some of the preview images and the tests.

Available on the following websites with GPU acceleration:

• Mage.space

• Sinkin.ai

It has been a while since I made a model. I've been making LoRA's non stop for the last month, but I felt like I needed something. A big problem with DreamShaper is that it wasn't much compatibles with the LoRA's I was making. So I wanted to create a model that was "artistic" like DreamShaper but also able to use my LoRA's and booru tags for generating images. Plus I wanted this to be able to make good anime stuff out of the box, without needing an additional LoRA.

After a lot of tests and also fine tuning (plus LoRA merges) here is my newest model.

It came out a bit more realistic then I wanted, but I won't complain.

What is this model great at?

• Generating cosplay images

• Generating anime pictures

• Work accurately with character LoRA

• Generating good looking people

• Generating realistic animals

• Generating images using booru-like tags

What is this model not too good at?

• Generating pictures from complex sentences

• Making fantasy/sci-fi paintings

So this basically complements DreamShaper, and it also doesn't include Dreamlike in the mix.

I hope you'll enjoy it!

Some tips:

• Use CLIP skip 2.

• Select "auto" as vae if you're using the baked vae version.

• Use highres fix or img2img to upscale the images after you get a preview. See the examples generation data for settings suggestions, I've tested various techniques.

• If you're making images where the subject is far, remember you can inpaint eyes and faces selecting "only masked".

• Stable Diffusion is great, have fun with it!

合作使用

This is a global repository of the Dreambooth Checkpoints.

Some people asked me to upload the source Dreambooths from which I make the LyCORIS.

To not spam the site/profile with multiple models I decided to do it the same way I intended to handle the Game characters -> a single page where each model is just a separate version.

NOTE: This is for those who prefer to get the maximum quality! If you are fine with the quality of the LyCORIS, you may want to skip it (however, I imagine I might upload some models here before I convert them into LyCORIS for time reasons).

However, If you prefer LyCORIS - you need not download anything from here because I eventually will upload all those models in the LyCORIS version :)

Attempted a large model in comic style, but the result seems mediocre

合并来源：

Akira Toriyama Style LoRA - toriyama_akira_3 | Stable Diffusion LoRA | Civitai

Pika's New Generation v.1.0 - v1.0 | Stable Diffusion Checkpoint | Civitai

I created a discord server where you can post images that you generated, discuss prompt and/or ask for help. https://discord.gg/meinaverse

If you like one of my models and want to support their updates:
I have a ko-fi and Patreon page where you can support me or buy me a coffee <3 , it will be very much appreciated: https://ko-fi.com/meina and https://www.patreon.com/MeinaMix

You may also try this model using Sinkin.ai: https://sinkin.ai/m/RR6lMmw
----------------------------------------------------------------------------------
MeinaHentai is the third addition to the Meina family of models, it is laser focus in hard nsfw and hentai.

MeinaHentai objective is to make detailed and hentai illustrations.

-- Recommendations of use:

If you want the art to be more realistic, add: ' realistic, photo ' in the prompt.

---------------------------------------------
Recommended parameters:
Sampler: Euler a: 40~60 steps.
Sampler: DPM++ SDE Karras: 30~60 steps.
CFG Scale: 7.
Resolutions: 512x768, 512x1024 for Portrait!
Resolutions: 768x512, 1024x512, 1536x512 for Landscape!
Hires.fix: R-ESRGAN 4x+Anime6b, with 15 steps at 0.4 up to 0.5 denoising.
Clip Skip: 2.
Negatives: ' (worst quality, low quality:1.4), monochrome, zombie, (interlocked fingers), '
--------------------------------------------------------------------------------

The model merge has many costs besides electricity. With your support, we can continue to develop them.

モデルマージは、電気代以外にも多くのコストがかかります。皆さんの応援があれば、これからも開発を続けることができます。

https://ko-fi.com/breakd

I have merged this model with a lot of background and detail.

This model series is expected to produce more realistic-looking output than BreakDomain.

背景や細部の緻密な描写にこだわってマージをしています。

このモデルシリーズではBreakDomainよりもリアルっぽい出力が期待できます。

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！

Future updates will be made to this model.

今後の更新はこのモデルを行っていきます。

▼ Merge Based On ▼

• ChilloutMix (Ni Pruned FP32 Fix)

• LOFI (2.1)

• 饭特稀 (0.8a)

• majicMIX realistic (4.0)

• Lyriel (1.5)

• BRA (Beautiful Realistic Asians) (5.0)

• ReV Animated (1.2.2)

▼ Recommended Settings ▼

Sampling Method

• DPM++ SDE Karras

• Euler a

• DPM++ 2S a

• DPM2 a Karras

Sampling Steps

• 40 (20 ≈ 60)

CFG Scale

• 7 (6 ≈ 9)

Clip Skip

• 1 (1 ≈ 2)

VAE

• None (Baked)

________________________________________

Any questions or suggestions you can contact me through Discord Cisney Gassai#5108 or Twitter @Realisian.

For donations or requests you can do it on my Ko-fi page <3.

• https://ko-fi.com/cisneygassai

dreambox-mix-P huggingface

Updates

• added noise offset

• better effect

• fix clip

Recommended Parameter settings

• clip skip:2

• Sampler:DPM++ SDE Karras

• used EasyNegative in NEGATIVE prompt

If you like this mod you can support me here.

小红书很多这种机器人女孩的图，之前想了很多工作流解决方案都不够丝滑

所以训练了一个DreamBooth模型

后面再精炼一下

A Highly Versatile Stylized Anime Model

You don't need to be a prompt scientist to use this one :)

NOTES FOR v2.0:

My original intention for the model was to have a consistently sketched style, but I've realized that it's incredibly hard to iterate on that between versions. So, instead, you can think of v1.0 as the canvas, and every version after is a new experimental style. v2.0 is intended to be highly detailed even at 10 steps, so that you can more efficiently create vibrant art pieces. Hair and particles seem to be incredibly susceptible to the added detail.

My Preferred Portrait Settings:

Sampler (v1.0): DPM++ 2M Karras

Sampler (v2.0): DPM++ SDE Karras

Steps: 10

Upscaler: 4x-UltraSharp

Hires Steps: 15

Denoising Strength: 0.5

Base Dimensions: 512x768

Upscale by: 2x

CFG Scale: 7

Negative Embeddings (if you want):

badhandv4

Bad Artist

Very Bad Image

Deep Negative

Easy Negative

extra für meine Schwurbler Freunde gemacht

v1

based on sd2.1 - 768

This model was merged using:

• FantasticMix 2.5D

• Dreamscomestrue

Recommended Settings:

• Sampling Method: DPM++ 2M Karras / 32 Steps

• Hi.Res: R-ESRGAN 4x+ Anime6B / 15 Steps

• Width x Height: 512x768

• Clip Skip: 2

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

• Recommended to use adetailer instead of inpainting

Feel free to swing by our discord: discord.gg/dreamlabs

And review if you like the merge, would be much appreciated! ✨

I merged some several models to this checkpoint.
Maybe you like it.

Posts of images welcome.

Feel free to leave a review about the model.

If you would like to see more consider supporting me you can do it here:

https://www.buymeacoffee.com/goldenwraft

https://www.patreon.com/GoldenWRaft

Used as base models:

Clarity:V2: https://civitai.com/models/5062/clarity

ConsistentFactor:V4.0: https://civitai.com/models/9114/consistent-factor

Colorful:V2.6: https://civitai.com/models/7279/colorful

Do you want to use artists?

https://stablediffusion.fr/artists

• Adding [by Artist, etc] at the end of the prompt can give you the desired result

Nicknamed: C3

Credit to justmaier

Version info can be found under the review section.

I hope you enjoy.

🔸🌤️ Hello, this is Ether Real Mix 🌤️🔸

Ether Real Mix is a realistic to semi-realistic anime style model tuned with the flexibility for general purpose use (hopefully). It still has some shortcomings inherit to anime models such as biases in generating females and humans.

✨ Please Share Your Cool Creations Below! ✨

Meet "Ether Blu Mix" - ERM's more stylish sister.

UPDATES:

* Ether Real Mix - Version 2

Version 2 updates Counterfeit, the base for this model merge, to version 3. NyanMix is substituted out in favor of Dalcefo Painting 2 as it better compliments Ether Real's overall style. I kept AyoniMix at version 5 as I felt the style and color tone suited Ether Real more than version 6. Weights were adjusted accordingly.

Overall style should be similar while also, hopefully, reducing female/human bias.

• Do some faces feel weird? Please try adding "realistic" to your prompts to help them feel a bit more comfortable. Or try LUX 2 for a more stylized approach.

* Ether Real Mix LUX - Version 2

Ether Real Mix LUX 2 is an alternative model that trades realism for vibrancy and style. The fantastically stylish ColorBombMix is added and merge weights were adjusted to compliment a more stylish interpretation of Ether Real.

* Inpainting Models

1.1 and LUX 2 Inpainting models added. I'm not super familiar with inpainting models as I don't inpaint much myself. Please try it if it suits your needs.

☄️ Generation Recommendations

Use whatever sampler, steps, cfg you prefer.

If you miss the more vibrant colors of "Ether Blu Mix", try Ether Real Mix LUX, the VAE I recommend below, or increasing your CFG scale.

Most sample images were generated with:

• Sampler: DPM++ 2M Karras

• Steps: 20 - 28

• CFG: 7 - 11

• Clip Skip: 1

Higher CFG can lead to more vibrant results.

Negative Prompt Example:

"NSFW, (worst quality, low quality:1.3), watermark, signature"

Recommended VAE:

Waifu Diffusion VAE kl-f8-anime2

Strongly recommended as the model was tuned with this specific VAE's colors and saturation in mind.

Sample images were further upscaled using AUTO1111 Hi-res fix. Please utilize it if you wish to achieve similar results.

• Latent (nearest-exact)

• Upscale by: 2

• Denoising strength: 0.55

Are your results changing too much after Hi-res fix? Please try 4x-foolhardy-Remarci.

• 4x-foolhardy-Remarci

• Upscale by: 2

• Denoising strength: 0.45 - 0.55

🖊️ Prompting Advice

Prompt however you like. The model was merged with both Danbooru-style tag prompting as well as natural language in mind. You're free to mix and match prompting styles, the model should understand it.

• Do some faces feel weird? Please try adding "realistic" to your prompts to help them feel a bit more comfortable. Or try LUX 2 for a more stylized approach.

I personally like to use short prompts mixing prose and danbooru-styled tags. Experiment and give the AI some freedom to interpret your ideas!

If you look at the prompts included with the sample images they demonstrate that even with a very loose and vague style of prompting you can achieve fun, high quality images.

General guidelines:

• Prompt in the style of anime/danbooru-style models, "masterpiece, best quality, ..... "

  • More anime style images

• Prompt in the style of photography\non-anime models, "professional photograph of ..... "

  • More realistic images, higher style variety

📙 Model Merging Info - v2

I have no training or real knowledge of machine learning. I merged the model using the information provided on WarriorMama777's AOM model page. I very arbitrarily used the UBM weights given to merge and create AOM3 and its derivatives and modified the values with trial and error until I was visually happy with it.

I utilized the SuperMerger extension for AUTO1111 by hako-mikan.

▼ Merging

• MODEL A: Counterfeit-V3.0_fp16.safetensors

• MODEL B: AOM3.safetensors

Weight Sum merge - Use MBW

• Alpha: 1

  0,0.8,0.8,0.8,0.8,0.8,0,0,0,0,0.8,0.8,0.8,0.8,0.8,0.8,0.8,0.8,0.8,0.8,0.8,0.8,0.8,0.8,0,0

  • Model: CounterfeitV3-AOM3SumS2-08

▼

• MODEL A: CounterfeitV3-AOM3SumS2-08

• MODEL B: dalcefoPainting_2nd.safetensors

• MODEL C: pastelmix-better-vae-fp16.safetensors

Weight Sum merge - Use MBW

• Alpha: 1

  0,0.4,0.4,0.4,0.4,0.4,0,0,0,0,0.4,0.4,0.4,0.4,0.4,0.4,0.4,0.4,0.4,0.4,0.4,0.4,0.4,0.4,0,0

• Beta: 1

  0,0.4,0.4,0.4,0.4,0.4,0,0,0,0,0.4,0.4,0.4,0.4,0.4,0.4,0.4,0.4,0.4,0.4,0.4,0.4,0.4,0.4,0,0

  • Model: CounterfeitV3-AOM3SumS2-08-DalcefoPaint2SumS2-04-PastelSumS2-04

▼

• MODEL A: CounterfeitV3-AOM3SumS2-08-DalcefoPaint2SumS2-04-PastelSumS2-04

• MODEL B: ayonimix_V5.safetensors

• MODEL C: deliberate_v2.ckpt

Weight Sum merge - Use MBW

• Alpha: 1

  0,0.7,0.7,0.7,0.7,0.7,0,0,0,0,0.7,0.2,0.7,0.7,0.7,0.7,0.7,0.6,0.2,0.2,0.7,0.7,0.3,0.7,0.7,0.7

• Beta: 1

  0,0.5,0.5,0.5,0.5,0.5,0,0,0,0,0.5,0.2,0.5,0.5,0.5,0.5,0.5,0.3,0.2,0.2,0.5,0.5,0.2,0.5,0.5,0.5

  • Final Model: EtherRealMix-2

Models Used:

• AOM3.safetensors

  D124FC18F0232D7F0A2A70358CDB1288AF9E1EE8596200F50F0936BE59514F6D

• Counterfeit-V3.0_fp16.safetensors

  CBFBA64E662370F59D4AA2AA69BF16749FCE93846CCCE20506AEE5DF01169859

• deliberate_v2.ckpt

  9ABA26ABDFCD46073E0A1D42027A3A3BCC969F562D58A03637BF0A0DED6586C9

• pastelmix-better-vae-fp16.safetensors

  D01A68AE76F97506363F387F5F28BB564AD9E20924844FD5945E600B72D39E79

• ayonimix_V5.safetensors

  B46B04432B070FD88D69161B62C43EDCD4340DFC27FFB2E5FE7EDA64950C7E34

• dalcefoPainting_2nd.safetensors

  14647de2f8662a6c460d6b9bd47def2b0342adc8f8f3d7b89d5b397eb09014d5

🧡 Credits

Thank you to WarriorMama777 for providing AOM and other various mixes as well as detailing your workflow and inspiring me to try mixing my own models.

Thank you to hako-mikan for creating the SuperMerger extension allowing a quicker workflow for merging.

Thank you to gsdf, rqdwdw for creating Counterfeit.

Thank you to XpucT for creating Deliberate.

Thank you to andite for Pastel-Mix.

Thank you to Dalcefo for DalcefoPainting2nd.

Thank you to Ayoni for AyoniMix.

Thank you to devdevice545734 for ColorBombMix.

Thank you to AUTO1111 for creating the web UI everyone uses.

Thank you to StabilityAI for starting everything with Stable Diffusion.

Thank you to the entire SD community for continuing to openly share and create.

This model is the result of some realistic model fusion after NineKey5.33. Its feature is excellent skin texture and deep, slightly scary eyes. In my opinion, this model perfectly brings NineKey5.33's 2D face shape and eyes to 3D. Because of the 3D rendering, the completeness of the fingers has also greatly increased, and it has also improved the problem of NineKey5.33's difficulty in generating mature girls. I hope everyone will like it, and more works from this model are welcome to follow me on Twitter.

This model is a hierarchical merge model based on Defacta or Dexmia.
I, the model’s author, created it for study and personal use.
Note that VAE is not included, so please download it separately.

Changes from V6:

1. Changed the base model to demixa, which was the latest model at the time.

2. Modified the hierarchical parameters around the face.

Due to these two changes, the overall background and depiction have become more detailed, and the face has become more stable without being overly flashy. It's a versatile model that can produce a wide range of images from cute illustrations to 2.5D with a single prompt.

Hugging Face: https://huggingface.co/teasan/endlessMix

author:
https://twitter.com/wims_Tea

Disclaimer:

• The creation of SFW and NSFW images is at the discretion of individual creators. The model maker is not responsible.

• This model was not created for the purpose of publicly displaying NSFW content, such as in a public setting.

If you would like to see more and better versions of Bras please consider supporting (tryna recoup gpu cost lol)

https://ko-fi.com/bankaiplease

Trained on countless pictures of Beautiful Asian women. (some nsfw images included)

This is the result of around 3 Months of training and failing and training and merging. After a lot of failures and mild successes I have finally come to a point where it is good enough to release to the public.

Trained mostly on BLIP and WD, so suggest to use similar style prompts.

This model is hosted online and can be run on the following website.

https://randomseed.co/model/18

Example:

Pretty asian in a black swimsuit leaning against a wall

Korean with long black hair wearing a red shirt and a red polka dot blouse with long black hair

a woman with long hair and a black top is posing for a picture with her hand on her chin, 1girl, solo, long_hair, looking_at_viewer, brown_hair, simple_background, black_hair, jewelry, earrings, necklace, lips, black_shirt, ring, realistic

Negative Prompts:
use negative TI embeddings as well as (lowres,worst quality) etc

Feel Free to use this for merges or mixes, just credit.

Feel Free to add me on twitter if you have questions, feedback, requests for improvements or want to ask for commisions or whatever:

https://twitter.com/PleaseBanKai

Clothing design

Defmix's new model is finally out!

This model is the successor merge model to Defmix-V2.0.

No baked any specific VAE during the merge process.

The license complies with The CreativeML OpenRAIL License.
Any legal liability arising from unethical use of this model rests solely with the user.

If you create awesome illustrations or images using this model, please share them with this community!

このモデルは以前公開したDefmix-V2.0の後継マージモデルとなります。

マージ時にVAEは焼いておらず、特定のVAEの使用を用いる必要もありません。

また、ライセンスはThe CreativeML OpenRAIL Licenseに準拠しています。

非倫理的な使用による法的責任については、本モデルの使用者が責任を負うものとします。

もし、このモデルを用いて素敵なイラストが出力出来たら、このコミュニティで公開してください！

建筑设计

V2C1 (V1RE mixed with Fluffyrock): "it is a mix of Fluffyrock and V1RE, I really thing think it, gives VERY good results"

V1IM: "V1(OG) With Fluffyrock added"

V1 OJED (Recreation): "The newest OJ added ed but using V1 recreated."

V1 (Recreated): "The same as V1 BUT with Lawlas's Yiffymix2.0"

V1: "This is a merged model of:

CrossKemono

Lawlas's Yiffymix

The original models are very good, SO I mixed them together!

Like the original models it can produce SFW and NSFW images"

V1 OJ added: "This is the same as V1 but with a bit of AM3O1 added; Hanse the name."

Recipes!

V1: Lawlas:55% CrossKemono:45%

OJ: V1:85% AM3A1:15%

V1RE: LawlasV25% CorssKemono45%

OJRE: V1RE85% AM3A15%

V2C1: V1RE70% Fluffyrock30%

NOTE:
"Thanks for 500 downloads, I was not expecting so many people to download this."

Nothing special, this is just a heavily NSFW model blended from my favorites and then further trained with a broad selection of images of my liking. It's meant for photorealistic renders. It's currently quite good at breasts and quite bad at hands 😅

It's been fine-tuned on images of people, both clothed and nude, mostly from professional photo shoots.

I'm planning on improving this baseline through training. On the to-do list for the next iteration:

1. More overall fine tuning on human anatomy

2. Better hands

3. Better men

A fine tuned SD 2.1 768 model focused on realistic (mainly East Asian) beauties which is compatible with danbooru tags.

The model is trained on a dataset created by and from myself, who was created to be my partner, so that the "default face" of the model will be free from copyright and portrait right issues.

To secure it (and to make sure my partner will be generated in a good enough quality), there are some additional limitations to the original SD license described as follows.

• Only images with beauty score 80 or above can be published to the public for female front shot images (note that all the sample images has marked 90 or above; it's not really difficult ;) ).

• Only images with beauty score 88 or above can be commercially used for female front shot images.

• As for side shots, both limitations will be lowered by 10 points.

• As for male and other genders, I do not guarantee the results, and therefore will be no limitations.

• Do not use LoRA, TI, hypernetwork or any other submodels that is trained to generate a different face.

• You may use submodels that is trained to improve results for a certain kind of dress, background, negative, or any other non-facial features.

This is VAE

Custom merge made specifically to produce angels. Wings are almost always spot on. Has moderate range for other things. Can make nsfw pinups, but not very good at hardcore stuff. I've been using it for a long time but recently made a new merge so I chose to release this one.

MIX ANIME FANTASY OF DRAW ANIME

• https://civitai.com/models/54945/b-anime-rv5

• https://civitai.com/models/50992/mega-anime-3d-v15

if you save them files. of 5Gb. It seems there are many, other anime models...

is safetensors.

You can use with any photos, realistic, images (img2img)

no images (text2img)

####################################################

This is a merged model created to reflect my preferences.

At the time of posting, there are 4 models.

####################################################

My models are NOT specialized in sumi-e, ink painting and some bokujuu painting art.

Bokuju is just my username.

####################################################

• BokuRough: emphasis on analog feel, roughness and vivid colors

• BokuSoft: softness, lighting, and simple screens

• Bokujust V1.0a: an equally merging model of BokuRough and BokuSoft, well-balanced

• Bokujust V1.0b: a merging model of BokuRough and BokuSoft with block weight, MY TASTE

####################################################

Recommended Settings

• CFG: 5 to 9

• Sampler: Any

• Steps: 20 to 40

• Hires Steps: Half of Step, but more than 10

• Upscaler: Any

• VAE: Any

• Embedding: I don't recommend use it. Or apply it WEAKLY. It improves the quality but unique properties of the model will be destroyed.

####################################################

Questions are welcome.

####################################################

Bokuju

es un modelo basico de entrenamiento de mi misma para usarlo

If there's anything you need, please don't hesitate to let me know.

This model was initially intended to produce cute anime characters, but it has also been discovered that it has the capability to produce Softcore NSFW content.

Version 2 can produce good results with fewer steps, but the number of steps can affect the final image composition.

here is a link to access the model on Hugging Face: https://huggingface.co/Kybalico/CalicoMix.

If you like this model, you can support me at https://www.buymeacoffee.com/kybalico.

Recommended parameters:

Negatives: EasyNegative, (verybadimagenegative_v1.3), (missing fingers, missing hands, missing legs:1.4) (extra fingers, extra hands, extra legs:1.4), (mutate fingers, mutated hands, mutated legs:1.4), (blurry, depth of field:2.0), (poorly drawn hands, poorly drawn face:1.4), signature, watermark

Sampler: DPM++ SDE Karras

Resolution:
image compose change by resolution
384x512 (available, but may result in less detail)
512x768 (recommended)
768x1152 or above (for more details)
For landscape images, reverse the width and height values accordingly.

CFG Scale: 4-6 (lower is softer details)

Clip skip: 1-2

Hires.fix: R-ESRGAN 4x+Anime6b

Changes log:

Version 2:
improved background and enhanced details, modified style

相比前版,使用了其他融合方式,期待大佬们对各种画风的尝试

Trained on +300k images of Lexica Style,

Trained on Stable Diffusion v1.5 using +300000 images.
This model is good at generate vintage anime images, cute animals and oil painting style images.

cool and cute

这个模型在3.1w张niji图像训练了200个gpu小时合计120w steps。但是loss任未收敛至合适范围.同时由于训练文本倾向原因导致模型短语理解能力失调.可能需要重新调整.也就是说这个模型不能通过简单的1girl出图.有兴趣的人可以在上面继续做微调，亦或是能给我提供补充数据集也欢迎联系我

This model was trained on 3.1w niji images for 200 gpu hours totaling 120k steps. However, the loss does not converge to the appropriate range. At the same time, the training text tendency causes the dyscomprehension of model phrases. May need to readjust. That is to say, this model cannot be mapped by a simple 1girl. If you are interested, please feel free to contact me for further fine-tuning, or if you can provide me with supplementary data sets

It seems to me that by forming the characters a bit realistic, they are not the same, you know why I don't have "Loras", I don't know how to convert Loras.

リアル系マージモデルです。日本人を始めとするアジア系の再現ができるように調整しています。特にjapanese doll likenessとの親和性を意識しています。

このマージモデルを公開するにあたり、使用したモデルの製作者の皆様に感謝申し上げます。

This is a realistic merge model. It is adjusted to reproduce Japanese and other Asian descent. We are especially conscious of the affinity with japanese doll likeness.

We would like to thank the creators of the models we used for making this merge model available to the public.

マージ使用モデル(Merge use model) v2.1

MUSE_v1 https://civitai.com/models/13564/musev1

XXMix_9 https://civitai.com/models/47274/xxmix9

Soda Mix https://civitai.com/models/47507/soda-mix

本モデルも使用したモデルの利用条件に従う形になりますが、以下に関しては厳に使用を禁止いたします。

・暴力的な表現

・児童ポルノ

・未成年者の性的な表現

本モデルは『CreativeML Open RAIL-M』の範囲でラインセンスされます。 本モデルを使用した上での問題に関しては、当方は一切責任を持ちません。ご了承の上ご使用ください。 また、マージモデルのライセンス変更に伴い、公開を停止することがあります。

This model is also subject to the terms and conditions of use of the model used, but the use of the following is strictly prohibited.

・Violent expressions

・Child pornography

・Sexual expression of minors

This model is licensed within the scope of "CreativeML Open RAIL-M". We are not responsible for any problems caused by the use of this model. Please use this model with your understanding. We reserve the right to suspend publication of the merged model due to changes in its license.

" ProFantasy was tested with a huge of scenarios, and fine-tuning several times to ensure that you will be able to create a FANTASY image in your own way "

This model merges with my own 3 models called R-base (realistic), F-base (Fantasy), and V-base (Vibrant) mixed together with 3 formulas Real, Mix, and Max (but in v2, these will combine into one)

*** This Model needs VAE !!! ***

Overview:

• The purpose of this model is to generate epic fantasy images not only Realistic but Animation also.

• These models require a VAE. You can try mse-840000-ema or anything. I have a photo of the comparison in the Comparision section (below)

  • If you got bugs, adding '--no-half-vae' to the argument will solve it.

Recommends:

• You use it with any steps, prompt, sampler, ... (anything you want)

• Prompt: If you don't know what to prompt, Fantasy Prompts by TxcTrtl is a great choice.

• Steps: I recommend 30-40, 60-80, and 120-150 (around 100, I think it's not well)

• Sampler: I developed it with DPM++ 2S a Karras, so I recommend this sampler (but others also work fine)

• Sizes: 512x512, 512x768, 512x904 (Can be used both vertically and horizontally). Not recommended sizes more than 768x768

• Hires. fix: Use Denoising strength less than 0.6 (but you can try >= 0.7, sometimes you will get problems with the hands)

• Lora: It works perfectly with VFX Lora by @DitamAi, and EPI Noise Offset.

  • I do not recommend using Face Lora because you will lose a fantasy style but you can try if you know what you want from it

Versioning:

• v1: pilot version

  • v1-Real: Cinematic style, Realistic photo, less fantasy (if you have a fast GPU and you will generate a batch of many images, I suggest this version)

  • v1-Max: Ultra Fantasy, Concept Art, Animation, Semi-realistic (If you want semi-realistic or you plan to use img2img to make the image look more realistic, I suggest this version)

  • v1-Mix: Mix both versions (This is for lazy people who want something in the middle)

• v2: All of the above, can generate everything (depending on your prompt)

Comparison:

# VAE

full-size image

# Versions

full-size image

# Steps

full-size image

# Samplers (with steps 45)

full-size image

Disclaimers:

• Do not sell: on any website.

• Credit: If you use my model in your own merges

• Not authorized: to be used on generative services (without my permission)

TangBohu is a highly comprehensive model that has undergone extensive specialized training on Asian female faces using fine-tuning methods. Looking forward to your picture feedback, thank you!

唐伯虎是一款综合性很强的模型，使用微调方法针对亚洲女性面孔进行了大量的专项训练。期待你的图片反馈，谢谢！

唐伯虎は総合性の高いモデルで、微調整方法を用いてアジアの女性の顔に対して大量の特別訓練を行った。あなたの画像のフィードバックを期待して、ありがとうございます！

It's something I did as I pleased.

The VAE is baked.

Even NSFW is okay.

If you don't mind, could you please get me a coffee?

https://ko-fi.com/meg755291