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.
This merge was created by chance. It is a merge of 4 photorealistic model files. Have fun to testing
Merge various checkpoints
A very simple merge model between
privateRefslave and Store Bought Gyoza
I did it a while ago and forget the exact formula
uploading this just for fun
used some sample prompts from other models so you can see the difference
As always, the example images I've posted have NO postwork done to them beyond the facial fix (in some cases) and upscaling. The point is to show how well it works out of the box - if you take the time and create really good prompts and use good negative prompts (an example is at the end of this post) you can get even better results.
Rebuilt from the ground up... got rid of some garbage (and pruned it down to half its original size) tweaked some weights that were bothering me, and generally got things cleaned up. I'm not quite happy with the style consistency, yet - but this is a good clean start on things.
NOTE: The trigger words listed are just the ones that were specifically added on top of the SD Base Model - and really only the ones I've found useful to make good tweaks and adjustments. This model is great at knowing art styles, people, and concepts that you might love (and/or hate) from the base model.
I also forgot one ingredient when adding hyperfusion - so it tends to go porny/nude when you start playing with breasts. I won't have time to update/fix until this weekend so... expect to have to do some work to add clothes if you're playing with breast sizes. Sorry about that.
Normally, I wouldn't put out a new version so quickly, but I wasn't really happy with the faces on v3.4 - they would often look flat and washed out compared to the depth of the rest of the image. I also tweaked the color levels a bit to make things more colorful - though I may have gone a bit overboard. We'll play for a few days and see.
This update attempts to fix that a bit, nothing else, really. Just a bit of rebalancing.
Merged in several western art styles (American Comic and Jim Lee Style) along with a smidge of the Mistoon Emerald checkpoint to enhance the outlines without changing the styling all that much.
Keywords "Masterpiece" and "Jim Lee" will enhance (or back down if negative levels are used) the American and Jim Lee styles respectively.
All previous triggers and keywords will still work, too. (See older version notes and trigger lists for details).
As was mentioned very early on here - I'm not looking so much for characters to look real or even necessarily look exactly like the actor or actress whose name we put in the prompt. I want something that might be close, but that is consistent in composition, style, and overall appearance. Ideally, this model should be set up so that a person can make multiple images of the same person to be used for games or story telling purposes.
Updated to Babes 2.0 (the original had v1.1).
Because of the nature of that update, this tends to push the style much further back toward realism and away from the art style. I wasn't happy at first, but then realized that simply adding "digital art" and/or "cartoon" to the prompt pushed us right back to close to the style I am going for. To get more of the outline style, you can also add "warlockandboobs"
This also responds to the Hyperfusion triggers (see version 3.2 notes) as well as all the custom art styles from Babes. (Plus many many more - but the Babes trained styles are ones likely not to be found in many other models).
Important Note: I'm not entirely happy with this result - in many areas I feel it's a great step forward, but in others... well... not so much. Faces tend to have less detail on wider shots and scenes with a lot of things going on (i.e. not simple portraiture) take a lot more heavy prompting. Now, most folks are used to dealing with heavy prompting, so I'm putting this up as a beta for some feedback - but the real point of this was to be able to use fairly simple prompts to get results that satisfy your desire when you came up with the prompt. So... anyway... this needs some work. Eventually I'll either end up rolling back and remixing or finding a way forward that brings us more back on track.
Your thoughts and feedback are appreciated.
This update doesn't change the styles very much (though it's enough that you can't replicate older renders on the new version). It mainly incorporates things from Hyperfusion and Bigger Breasts. Hyperfusion is great, but it tends to sluttify the outfits, even at very low levels. By mixing in Bigger Breasts (which tries not to change up the clothing too much) and finding the right balance, it works pretty well.
A bonus is that it also lets you accomplish making breasts smaller - something very difficult to do on most models without bringing in a lot of extra help. With this "flat_chest:1.4" (or thereabouts) will do a nice job of shrinking things down in most cases. You can also use all the triggers from hyperfusion to make the breasts, butt, and belly do all sorts of things - and putting in weights there brings varied results too.
NOTE: At low levels, most of those calls don't go crazy by sexing everyone up. The higher your weights, the more likely that is to happen, so you may need to declare SFWs and even call a specific outfit in some cases. (I had to do that in the big bust sample image).
MILFY BONUS: While this isn't so much of an update as it is a little trick I learned, it is pretty cool and works well, so I thought I'd pass it along. So many models make it hard to control the age of folks - no matter what you do, the subject ends up looking under 20 (and sometimes even younger). To age folks up, use "caricature" in your prompt. The higher the weight, the older, the lower, the less aging affect it has. When adding this to your prompt, though - it will tend to push the image toward headshots - so if you're looking for something else, you'll need to call your shot and angle.
This really jumped up to the next level with a few extra tweaks to the LoRa styles plus Merging in Galena. The example images are all done with NO negative prompt and just a handful of words in the prompt - usually just a name and a quick description of what they are doing.
This also takes LoRa's and TIs a lot better than the original. For version 1 I needed to back down the weights quite considerably, for this version leaving them at the default 1.0 (or the values recommended by the creator) tended to work really well.
You can get some cool looks and variations when combining TI and LoRa triggers with the names of known celebrities, too.
This version tends to go a bit more Porny/NSFW than the original, but a lot of that is keyed into the source of the training. Celebrities who tend to not do the sexy stuff aren't as likely to default to sexy stuff - while a porn star or nude model are more likely to default to nudity and sex. Call your shots and it works out well either way, though.
Upscale is always a good thing (though in these, I just did latent) while Face Restoration is often better to leave off (but not always).
Body types tend to always be similar - but you can call them using various bodyweight/style prompts.
I wanted a model or workflow process that allowed me to quickly and easily churn out art for games and/or photo stories. I didn't want long complicated prompts to create a certain art style, but I also didn't want to be forced to use LoRa's and TI's for every character. Unfortunately, most of the models where I loved the art styles didn't do so well of loading characters (celebrities for mixing, fictional characters, etc.) and the ones that knew tons of famous characters and people tended not take to the art styles I was going for (at least not without complex prompts).
There are some great Anime style art prompts that did a nice job, but I didn't really want Anime faces (big eyes, heart shaped head with pointy chin, etc.). A wanted more of a western style, with a hint of caricature in the faces, and a consistent look from a basic <character> is wearing <outfit> at <location> type prompt.
Unfortunately, since I didn't really expect this to work, I didn't start taking notes on what all went into this until I was fairly well along. It started with a Mega Model (either SD's AIO or Clarity - I forget) and then I merged Rev Animated and Babes into that.
To my surprise, it knew LOTS of characters and celebrities (even some obscure ones that I was surprised about) and it spit out a pretty consistent style - even though it was still a bit more realistic than I wanted. It took LoRa's and style tokens well, though... so I moved to the next phase.
First I added several LoRa styles that I liked the looks of and tweaked the weights on each. They were styles that needed no triggers - so hopefully once I merged them in, then my default prompt would spit out that style every time. (Fingers crossed). I set the values so they showed up, but were low enough that the style didn't affect the clothes or other compositional elements much (if at all). The styles and the weights I ended up at are as follows: <LuisapNijijourneyLORAV2_v2:0.7>,<bootyFarmStyleLora_v10Dim128:0.4>, <lora:hungryClickerStyle_v20:0.6>
To my shock and amazement - it worked spectacularly. It wasn't quite the style I wanted, but adding simply: (bold lines:1.1), (high color), ((smooth skin)), (Masterpiece Digital Artwork:1.3), to the start of the prompt got me there. I can handle a 4 token seed prompt.
Some notes on the model:
It "mostly" defaults to SFW out of the box. i.e. If you just type in a person's name or character description with no clothes - it'll tend to put them in clothes - or at least a swimsuit. That said... with proper prompting, does nudes and porny stuff just fine, too.
I didn't care so much about making sure resulting characters look "exactly" like the person you're calling out so much as wanting to make sure that if I called out that name/person again - they'd be consistent in the way they look from image to image. So, in other words, it's not so much about "accuracy" as it is about "consistency" - and that seems to come through. (This works well for my needs to create stories and whatnot)
Depending upon the distance from camera (i.e. Closeup head shots vs. full body shots) the weight of the "bold lines" in (many of) my example prompts can be tweaked. The further back, the lower that should go and the closer in, the higher it can go.
This model (probably due to one of the LoRa styles I added) tends to want to add tattoos - even for those characters who don't have them. Adding that to the negative prompt can help (see below). Don't forget to remove those if you actually want the tattoos there.
I've added some comments to several of the example images - especially the ones without generation data.
For the sample images I used the Anything VAE (though it works fine with both the default and Anime VAEs that I tried with it). No textual inversions or LoRa usage in them - it's all coming from the checkpoint. Base images at 384x512, Euler a at 20 steps, clip skip 2, face restoration, and scale fix (2x size using latent bicubic/antialiased). The first few examples are pure raw with just a character name and/or character name + general outfit description.
Those first few examples have no negative prompt, either (just to show how well it generally behaves without them). A good neg prompt helps with various things like extra fingers/bad hands, various defects and so on. The one I use most often is: (snagged from a sample image somewhere at some point)
canvas frame, 3d, ((disfigured)), ((bad art)), ((deformed)),((extra limbs)),((b&w)), blurry, (((duplicate))), ((morbid)), ((mutilated)), [out of frame], extra fingers, mutated hands, ((poorly drawn hands)), ((poorly drawn face)), (((mutation))), (((deformed))), ((ugly)), blurry, ((bad anatomy)), (((bad proportions))), ((extra limbs)), cloned face, (((disfigured))), out of frame, ugly, extra limbs, (bad anatomy), gross proportions, (malformed limbs), ((missing arms)), ((missing legs)), (((extra arms))), (((extra legs))), mutated hands, (fused fingers), (too many fingers), (((long neck))), ugly, tiling, poorly drawn hands, poorly drawn feet, poorly drawn face, out of frame, mutation, mutated, extra limbs, extra legs, extra arms, disfigured, deformed, cross-eye, body out of frame, blurry, bad art, bad anatomy, Scribbles, Low quality, Low rated, Mediocre, 3D rendering, Screenshot, Software, UI, watermark, signature, distorted pupils, distorted eyes, (distorted face), Unnatural anatomy, strange anatomy, things on face, ((tattoo)), ((tattoos)),
Obviously, some of those may want to be removed if you're going for something that has been excluded.
digital artwarlockandboobscartoonmasterpiece BREASTS ass belly hyperbreastshyperassflat chest
Beautifull Cute Girls Asian
hahahahahahahahahahahaha
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 :)
sks woman
1girl, breasts, nipples, solo, tongue, armpits, maid headdress, heart, tongue out, collar, blonde hair, long hair, heart-shaped pupils, blush, blue eyes, looking at viewer, red collar, open mouth, large breasts, halo, symbol-shaped pupils, sweat, nude, arms up, upper body, bangs, black background, saliva, collarbone, simple background, arms behind head, teeth, nose blush, completely nude, belt collar, hair between eyes
Negative prompt: ng_deepnegative_v1_75t, badhandv4 (worst quality:2), (low quality:2), (normal quality:2), lowres, bad anatomy, bad hands, normal quality, ((monochrome)), ((grayscale)), bad-hands-5, bad-picture-chill-75v, badv4,
ENSD: 31337, Size: 512x768, Seed: 423821374, Model: XXMix9realistic_v40, Steps: 25, Sampler: DPM++ 2M alt Karras, CFG scale: 8.5, Clip skip: 2, Model hash: b394832bf0, Hires steps: 10, Hires upscale: 2, Hires upscaler: 4x-UltraSharp, Denoising strength: 0.25
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
I made a neat 2D model with animation style. As a model suitable for detailed expression, it can do good art design.
Patreonも始めました。 よろしければマージモデルリリースの活動を支援して下さい！
I've started a Patreon. If you'd like, please support my efforts for the release of the merge model!
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 V8:
This time, I have released 3 models.
The characteristics of each are as follows:
V8
配合するモデル・パラメータ、その全てを一新した新しいendlesssMixです。
A new endlessMix with completely renewed model compositions and parameters.
V8 kawaiiFix
通常版の派生タイプで、より可愛いキャラクターが出やすいモデルです。
A derivative type of the regular version, this model is more likely to produce cute characters.
V8 old
V7までのモデル構成・数値パラメータを継承したタイプ。
以前までのモデルと使い方は同じです。
A type that inherits the model structure and numerical parameters up to V7. The usage is the same as with previous models.
Hugging Face: https://huggingface.co/teasan/endlessMix
author:
https://twitter.com/wims_Tea
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.
This model is merge of Realistic vision V2 and Deliberate V2
Sometimes you can get even better results than with Realistic vidion/Deliberate. You definetly need to try it.
This model is good at creating SFW and NSFW images.
Can't wait to see you generations.
Since version v20, models will be renamed to indigo_Furrymix.
UPDATE:
For v20_realistic:
This is just a improved version of v4.1, if you don't like the style of v20, you can keep using v16.
This version is intended to generate very detailed fur textures and ferals in a realistic style.
Usage is similar to v16. (can't do kemono style)
Doing better ferals than v16. (maybe xd)
The anthro dragons generated in this version will have a bit of feral features.
Like v16, this version can do females.
Can do aquatic furries.
More unstable than v16, and doing worse hands.
------------------------------------------------------------------------------------------------------
For v16_hybrid:
This is a hybrid model, all in one. Use 'kemono/anime' in prompt to generate anime content, 'chibi/cute' to generate very 'kemono' content, and use 'realistic' to generate realistic content. This model generates bara kemono.
This model is very sensitive to the prompts you write. Add artists to prompt can significantly affect the outputs.
Can do proper ferals now. (May not be perfect xd)
More non-dragon male furries support.
More sex/duo content support. (Which had none before xd)
The style is mostly determined by the prompts you wrote.
Can do females.
Still can't do aquatic furries.
Still has no eastern dragons support. (Unable to solve, may have to use lora)
------------------------------------------------------------------------------------------------------
Old versions:
Description below is for v4.1 and v12
v8 is trash.
For v12_anime/v4.1_realistic:
Hello everyone! These two are merge models of a number of other furry/non furry models, they also have mixed in a lot of my own LoRAs. And they're all about male anthro dragons.
These models are heavily bara oriented, the training dataset is mostly male NSFW, so it's easier for them to generate male nudity, no clothing and NSFW content.
They mainly use e621 tags, but also support danbooru tags, and already baked in vae so you don't have to use any.
Although they are 'doragoon' mix, they can generate other male furries.
They are not specially trained for anthro females. I didn’t try a lot, but I think these models can do females, and they are okay for females.
There are two types of them that are mixed with different models to generate different outputs.
It's used to generate anime style dragons or kemono dragons. It's also good at generating other furry male anthros. Recommended sampler: DPM++ 2M Karras and Euler a.
It's used to generate realistic or photorealistic style anthro dragon males and other furry males. Recommended sampler: DPM++ SDE Karras and also Euler a.
Example images are slightly curated and they are direct outputs without inpainting.
For both:
Struggling with wings and tails, because they are anatomically complex. May needs a little inpainting.
Inpainting is always good.
Without Hires Fix, both of them tend to generate blurry faces and eyes, so I recommend using Hires Fix for the whole time.
Latent, ESRGAN_4x or Anime6B.
Can not do aquatic anthros.
Getting no better results when using male dragon related LoRAs.
No eastern dragons support yet.
For the anime one:
it has noise offset issue, it generates very bright characters in dark scenes, so use ContrastFix to fix it.
https://civitai.com/models/8765?modelVersionId=10638
Select SD1.5 version.
And I don't think it's 'anime' enough for now. Its style is somewhat fixed, and it's a little overfitting.
Can be unstable.
Also anime one is worse at hands.
Can not do ferals.
(Can do a weird type of ferals: anthro feral xd)
For the realistic one:
generated characters' eyes will be blurrier in full body portrait.
Can do just a little bit of ferals.
(The images generated by AI are currently in a gray area. Since the training dataset has not been authorized, the dataset is not so clean. These generated images are for personal usage only. Please do not use them for commercial purpose, thank you！)
(English is not my native language, please forgive me if I make mistakes. ）
2023.5.12
Changed recipe and added colorbox. Made results more colorful and background more detailed.
Newly used model in this version.
Loli_A. ninekeymix. holokuki. Wonton ColorBox. Rikose Style V2.
2023.4.30
version 2.0 updated.
Reduced model size. Made it cleaner and brighter than V1.0.
ckpt version here.
2023.4.27 Change model to safetensor.
Click here if you want ckpt version.
This model is created by merging many LoRa and other models to produce pictures of cute furry girls. I hope you like it. (*^▽^*)
融合了一些模型和Lora得到的模型，可以生产可爱福瑞图。希望各位用得开心。(*^▽^*)
Recommend settings:
512×768, DPM++ 2M Karras, Steps: 20-30, and add “furry, animal ears, tail, " to prompt.
Used models:
MIX-HIRES
Used Loras:
This is anime-based semi-realistic mix of checkpoints and loras tweaked for good results on simple prompts.
Model is fully compatible with all LoRA that I made and will make in the future.
All the content I make is and will be completely free on CivitAI.
But if you want to support me with a coin, then you can do it here.
The model itself can provide muted tones, high detail, and ease of use.
My regular settings:
Clip Skip 2
VAE: kl-f8-anime2
Sampler: DPM++ 2M Karras or DPM++ 2M alt Karras
ENSD: 31337
Hires.fix: x1.5 and higher
Upscaler:
Option 1: 4x UltraSharp, 4x Valar or any like (Denoising strenght 0.35-0.5)
Option 2: Latent (any) or Lanczos (Denoising strength 0.5-0.6)
But you may feel free to experiment.
Please note that this model is ̶v̶e̶r̶y̶ horny, so I strongly recommend to tag some clothes (pants or something) and using these tags in a negative prompt to avoid NSFW: nsfw, naked, nude
Useful tags (not necessary, just minor tweaks): volumetric light, realistic, dark atmosphere, volumetric light, caustics, absurdres, eye focus, contrast, dark scene, bright scene
1. easynegative
2. bad-hands-5
3. badhandv4
I merged my favorite model.
It's a model to make a romantic couple. It is possible to express a very delicate character.
Merge Material
Glow 2.5D
Victorian Mix
Detail Tweaker LoRA
Recommended Sampler
DPM++ 2M Karras or DPM++ SDE Karras
Recommended Upscaler
Latent (Denoising 0.5 ↑)
Recommended Prompt
(masterpiece, best quality) or (absurdres, highres, ultra detailed)
After he tested nearly 900 models, this is a merge of Shonin's 10 favourite photo-realism models, mixed in with the Envy Good Hands and Detail Tweaker LoRAs to give you fantastic images.
As always, these models are properly pruned fp16 and fixed with the 840k VAE baked in.
The front image is made using a "universal prompt" with no embeddings/LoRAs/weightings so should be replicable across any UI
Scarlet Mix is a mix of 9 models carefully balance for image quality and details. It does not need any quality prompts to provide high quality artwork and it plays well with many LoRas. It can also make quality faces even with cowboy shot or full body composition.
Image types the model excels at:
Food
Men
Women
NSFW
Vehicles
Weapons
Armor
Landscapes
Abstract Concept Prompts
Architecture
The VAE is baked in.
This is an attempt to make a free/open available model.
The following models are used by PoV Skin Texture - r34 Lucid Black (this model is used by the ChilloutMix as described)
All models have merged with the SuperMerger extension
pyro's_pov models - (pyro_pov_a + pyro_pov_b)
F222 (Fp32) see also F222 at https://rentry.co/sdmodels
Merging steps: (please see also https://rentry.org/hdgrecipes recipes.)
Merging Steps: (modified recipe of https://rentry.org/hdgrecipes#instructions_4)
pyro_pov_a + pyro_pov_b = pyAB
analogDiffusion_10 x 0.85 + pyAB x 0.15 = MERGE1
MERGE1 x 0.95 + v1-5-pruned-emaonly x 0.05 = MERGE1Fix
MERGE1Fix+ (F222_v1 - v1-5-pruned-emaonly) x 1 = MERGE2
MERGE2 x 0.75 + r34_e4 x 0.25 = MERGE_BASE
Now we can get MERGE_BASE named ChillySauceBaseV0.
but, the ChillySauceBaseV0 model alone is not good enough to use. It produces overfitted results sometimes. To remedy this issue, simply merge a good model like the NED(NeverEndingDream - NO VAE version).
ChillySauceBaseV0 x (1 - alpha) + neverendingDreamNED_noVae x alpha
the alpha could be 0.4 ~ 0.6 value.
alpha = 0.6 is chosen and named ChillySauceMix.
Like as ChillyMix, its license is almost free:
This model permits users to:
✔Use the model without crediting the creator
✔Sell images they generate
✔Run on services that generate images for money
✔Share merges using this model
✔Sell this model or merges using this model
✔Have different permissions when sharing merges
画面没有好的质感可以尝试增加对应Lora:https://civitai.com/models/64030/shahua-lora-lora
===============
The picture doesn't have a good texture, you can try adding corresponding Lora:https://civitai.com/models/64030/shahua-lora-lora
v2这个版本改善了远景构图以及远景的梦幻感，里面加入了我经过调试的新的lora-cinematic的参数，以及一些其他的辅助lora，而近景变化不大（手好像没那么稳定了= =）
This version of v2 improves the composition of the vista and the dreaminess of the vista, adding my new debugged Lora-Cinematic parameters, as well as some other auxiliary LoRa, while the close-up scene doesn't change much (the hand seems to be less stable = =)
v3改善了脸部和手部，以及一些肢体结构，还改善了画面精细度。泛用性提高了不少，现在能兼容更多lora了，污染也减少了。
The V3 improves the face and hands, as well as some limb structure, and also improves the fineness of the picture. Versatility has improved a lot, more LoRa is now compatible, and pollution is reduced.
v3.5这个版本改善了偶尔会有的眼睛和脸部的崩坏问题，使得脸部更美型了
This version v3.5 improves the occasional eye and face breakdown, resulting in a more beautiful face
'Creativity is not just creating works of art, but the need to express one's uniqueness and leave a mark on the history of mankind.'
\(￣︶￣*\))
For best result use this negative prompt:
(worst quality, low quality:1.4), (bad_prompt:0.7), simple background, multiple ears, muscles
And "Euler a" sampler.
All models after v3 are my experiments. For best results I recommend downloading v3
Infinity ver: Use Crosskemono vae and set the CFG to 4
RuviMix_V1 ✔ - Pastel colors, smooth texture 🍥
RuviMix_V2 ✔ - Strong line art, darker texture 🍪
Negative Prompt: rMadaNegative4 (SD 1.5) | Stable Diffusion TextualInversion | Civitai
VAE: stabilityai/sd-vae-ft-mse-original at main (huggingface.co) or Cold VAE: https://civitai.com/models/62741/rmada-cold-vae
** v8-cold-vae: No VAE needed. Built-in rmada-cold-vae
Optional: rMadArt3_NoiseOffset (SD 1.5 Lora) | Stable Diffusion LORA | Civitai
This merge use Figma Anime Figures LORA and bunch of other checkpoints to create a doll looking anime. Works best for close up picture. In the examples I Use hires. fix, upscale latent, denoising 0.5, hires steps 20, upscale by 2 . Clip skip 2
I use night sky yozora VAE in the examples https://civitai.com/api/download/models/14459?type=VAE
if you like the models, you can support me on https://ko-fi.com/promptsharingsamaritan
Wolf Boys 2D is a model that makes mature and manly male characters.
The model's rather rugged face is rather attractive.
Do you want a wild sexy guy? Here's what you want!
***
If you support me, I will make many AI male models and try to improve them more beautifully.
This was supposed to be an update to SR-Alpha, but the style of this merge's outputs was way too different to be classified as such, as, in my opinion, the images generated with this merge have drastically more realistic proportions compared to the older model.
This merge is a combination of the following models/mixes below:
V1:
V2:
V3:
I highly recommend inpainting for best results and to unlock the full potential of the merge. Separate inpainting model not required. Face restore (GFPGAN) has been used to just bring out a bit of realism to the outputs. I have not tested using Codeformer as it doesn't seem to work on my current set-up (3050 - 4GB VRAM). This does not have a significant impact when inpainting is integral to the workflow, but it does allow for better outputs from raw txt2img, though your mileage may vary.
Sampling Method: DPM++ 2M Karras, DPM++ 2S a Karras, or Euler A
Sampling Steps: 30
CFG = 10
Denoising Strength = 0.3-0.5 (img2img/inpainting)
*I only use denoising strength values greater than 0.4 if I want to drastically change the appearance of a particular feature/region of the image. I mainly use this if I want to fix hands that seem to be too deformed to be saved with lower denoising strength values.
https://civitai.com/models/17083/bad-picture-negative-embedding-for-chilloutmix
https://cdn.discordapp.com/attachments/1032948846197747731/1069660323709190195/bad-hands-5.pt
Deep Negative V1.x - V1 75T | Stable Diffusion Textual Inversion | Civitai
Bad artist Negative embedding - Bad artist | Stable Diffusion Textual Inversion | Civitai
Credits to the respective original creators of the resources used.
realisticphotrealistic
1.Do not use to create NSFW images of minors.
2.Do not use for criminal purposes.
3.Please create images at your own risk.
4.This model follows creativeml-openrail-m.
this model includes
https://huggingface.co/cafeai/cafe-instagram-sd-1-5-v6
https://huggingface.co/acheong08/f222
https://huggingface.co/sakistriker/Koji_V1
https://huggingface.co/unkounko/BalloonMix
https://huggingface.co/Kotajiro/kisaragi_mix
https://huggingface.co/naclbit/trinart_stable_diffusion_v2
https://huggingface.co/Vsukiyaki/ShiratakiMix
https://huggingface.co/dwarfbum/Hassaku
https://huggingface.co/deadman44/SD_Photoreal_Merged_Models
https://huggingface.co/scriche/AIOMonsterGirls
and some self-made Low-Rank Adaptation.
gg
To use Diffusable, you need to enter the "diffusable" prompt and then provide a description of the female character you want to create. After that, the model will start working to produce a realistic image with a very high level of detail.
The images produced by Diffusable fall into the character category, as these models are specifically designed to produce realistic images of female characters. Thus, you can use it to create drawings of female characters for animation, gaming or even personal purposes.
With Diffusable's impressively realistic rendering capabilities, this model can be an excellent choice for anyone who needs high-quality images of female characters.
Follow us for the latest models.
diffusable
Seraph_Mix is meant to be a beautiful and colorful/bright hentai mix.
When I was creating this, I really liked 2 models in specific, but wondered what happened if i mixed them both, and honestly, I was not disappointed. It is really colorful, and amazing and doesn't even require much describing for it to be amazing.
-
Checkpoints involved in Seraph_mixV1 :
Checkpoints involved in Seraph_mixV2 :
Checkpoints involved in Seraph_mixV3 :
Version 4 and 5 are my secret!
baked in :
-
It is recomended to use (512x768), (Euler A), and a (CFG Scale of 7)
(768x768) images are still good and possible :
Example Generation
Positive prompt: 1girl[mature woman], [extremely detailed:1], [medium-small boobs:0.2], [blush, black hair, medium-long hair], bedroom, [sexy black panties, sexy black bra], nice hands, perfect hands], <lora:GoodHands-beta2:1>
Negative prompt: (worst quality, low quality:1.4), EasyNegative, bad anatomy, bad hands, cropped, missing fingers, missing toes, too many toes, too many fingers, missing arms, long neck, Humpbacked, deformed, disfigured, poorly drawn face, distorted face, mutation, mutated, extra limb, ugly, poorly drawn hands, missing limb, floating limbs, disconnected limbs, malformed hands, out of focus, long body, monochrome, symbol, text, logo, door frame, window frame, mirror frame, flat chest,
Steps: 30, Sampler: Euler a, CFG scale: 7, Seed: 2490512948, Size: 768x768,
-
LORA's from "ddp12" are pretty cool.
I also recommend using this LORA : "BetterHands" - By Envy
-
Thank you to the creators of both Yesmix, and AOM3, without them i would not have been able to create such a beautiful checkpoint merge.
Thank you the creators and mods of Yodayo, AI generation website, as without them i would not be here today making good images and checkpoint merges.
-
Special thanks to you, for downloading! : D
NSFW is supported,I think it's good, it's a good way to give back to the website, thanks to the resources of the website.
2.5D!You can read the introduction!
sampler:DPM++2M Karras
Latent (nearest-exact)
CFG:10
Sampling steps:35
Hires steps:30
Denoising strength:0.5
https://huggingface.co/embed/EasyNegative/tree/main
yesyeahvh/bad-hands-5 · Hugging Face
veryBadImageNegative - veryBadImageNegative_v1.3 | Stable Diffusion Textual Inversion | Civitai
VAE:ClearVAE - Main | Stable Diffusion Checkpoint | Civitai
Join LoRa:Shiny oiled skin 2.0 LyCORIS/LoRA - V1 LoRA | Stable Diffusion LyCORIS | Civitai
(Remember use V1！V1！)
It is recommended that everything in the introduction be installed！
If there are any questions, welcome to comment, I will improve.
I hope you all like it.
Meanwhile,welcome everyone to showcase their works and discuss and learn together!
At the same time, thank you to the two teachers of pixiv (YUMA, Toai R) for their guidance!
Trigger Words : painting, drawing, flat color, limited palette, low contrast
without trigger words : Polaroid, masterpiece, dark background
VAE : orangemix, clearvae
If you want to support me ko-fi
This is the counterpart to my Drawn Mix, with a more realistic, rendered style, though it can go in a lot of different directions via prompting. Very loosely based on Hassaku(NSFW). Though the style has been almost entirely swapped out, it retains a lot of the vibrancy of the base. I've added a lot of control over hair and bodytypes, along with refining a lot of concepts already present in the base model.
The most exciting addition to it is that I've trained it to do guns well. At the moment it handles assault rifles and scifi guns well, often not needing any inpainting. For rifles, sniper rifles, and submachine guns, it's a bit shakier, though it can usually do them if you're willing to inpaint. Pistols are still a roll of the dice and something that is a priority to improve.
Tips for use:
It requires a slightly higher step count than most models. A minimum of 32 steps for Euler A, though I prefer 36. Fewer steps mostly results in issues with eyes and other intricate details.
I had some trouble with the EasyNegative embedding, but can't reproduce the issues. if you're using it and get muddy indistinct faces, you may want to try removing it from the prompt.
Do use one of the badhand negative embeddings.
It will do portraits with no inpainting of faces, but when zoomed out, I highly recommend giving the faces a quick inpaint at .35 to .5 denoising strength and enough buffer to get the neck into the inpainting canvas. It vastly improves the faces. This may be less necessary if you're capable of generating at higher resolutions.
Trained with primarily booru tags. If you're having trouble getting a result, figuring out what it would be on danbooru may help.
Image workflow and settings for examples:
Euler A generating at (usually) 512x512 with 36 steps at CLIP SKIP 2
Upscaled 1.5x using the 4x-UltraSharp and Hires. fix
Quickly inpainting faces that required it using the method above, and in a couple cases a second pass to fix a wonky eye or small detail
No inpainting of hands or held objects was performed.
Nerdy stuff you may or may not need to know:
WD-VAE-v1 is baked in, inherited from Hassaku. I may experiment and upload a version without a VAE.
Trained at CLIP SKIP 2
I made models of Baroque and Victorian styles based on famous paintings from the 18th and 19th centuries. I hope you enjoy it together.
Do not use it for commercial purposes.
我以18-19世纪的名画为基础，制作了Baroque和Victorian风格的模型。
希望你也一起享受。
请勿用于商业用途。
25% anything-v5 + 25% HD-22 + 50% Defmix-v2.0 + Baked-In LoRA: 0.25 Detailed Eyes + 0.5 NoiseOffset
Combining the knowledge of Anything & the clarity of Hentai Diffusion & the artstyle of Defmix, while producing beautiful eyes with HDR feels!
50% anything-v3.0 + 50% HD-22 + Baked-In LoRA:0.5 Detailed Eyes
Combining the knowledge of Anything & the artstyle of Hentai Diffusion, while producing beautiful eyes!
Both have the one from HD-22 baked in.
Yes, the name is a wordplay/joke. At least it's not called some randomly-smash-the-keyboard-Mix.
这是我日常使用的融合模型。它有：
非常好的光影
比较好的手部
简单的用色，在使用画风LoRA的时候不会冲突、产生杂乱的颜色
非常少的污染，尽量减少提示词中没有的物品
我认为基础模型需要简单、少污染、会画各种概念。这样使用人物、画风LoRA的时候的可以更加好地还原。
建议负面：
(worst quality, low quality:1.4)
我的一些画风LoRA融合都是在这个模型上调试的，有兴趣也可以尝试一下：
https://civitai.com/models/53642/silvermoonmix01-or-delicate-skin-and-hair-texture
https://civitai.com/models/50232/cute-gothic-fashion
This is my everyday use model. it is aimed to:
Getting great light effects
Improving hands
Being simple in coloring, so that it won't conflicts with style LoRAs
Minimize objects that are not in prompts
I believe a good model should be simple, accurate, knowing many concepts. These are keys to make other LoRAs work well.
Suggested negative prompts:
(worst quality, low quality:1.4)
My style LoRA mixes are fine tuned on this model. Appreciate if you can give them a try:
https://civitai.com/models/53642/silvermoonmix01-or-delicate-skin-and-hair-texture
ADream Mix Style No.01（A梦二次元画风）
尝试画风风格模型的制作，喜欢的话留下您的小星星。
Try the production of painting style models, and leave your little star if you like.
Lysergic. This model is the lightest of heart among the trinity. It’s cartoonyer style shrugs off a lot of the darker aspects of its siblings and instead brings more vibrant and dynamic style to the table.
The darker older sibling: https://civitai.com/models/56061/narco
All preview images are done without embeddings and with Hires. fix: upscale 2. Steps 20. Denoising 0.5. Latent. All are cherry picked from batches of three.
All images are made in A1111. Many of the prompts are the same as my other model to give a feeling of the differences, and similarities, between each. Due to time constraints I won’t be uploading previews from InvokeAi, at least until after the third model, Opiate, is released.
If you appreciate what I’m doing feel free to https://www.buymeacoffee.com/Uzia or not of course.
A pruned photorealism stable diffusion model trained using Dreambooth. I recommend placing "PiroxiumRealism style," At the beginning of your prompts.
For example,
PiroxiumRealism style, portrait, night time, urban environment, detailed background, photorealism
Negative prompt: out of frame, low quality, duplicate, ugly, pixelated, pixel art, blurry
Steps: 100, Sampler: DPM++ 2M Karras, CFG scale: 8, Seed: 3140421720,
Face restoration: CodeFormer, Size: 512x512
PiroxiumRealism style
➡️A model I made using some custom training and merge with other popular models. I wanted a model capable of easily generating good consistant 2.5D style images with simple prompts.
🔞NSFW capable.
👩One disadvantage of this model is that it might be less efficient for some specific characters.
📝The recipe is quite complex so I don't remember all the models used. Sorry.
✔️Feel free to use the VAE you want. I personnaly use ClearVAE, and sometimes Blessed2 VAE.
🛠️Recommended tools : A1111 WebUI upscaler and After Detailer.
realistic3d facelustrous skin
Appreciate my work? Can you buy me a coffe please :) , If you want to know any of my models visit me at here
This model was trained from scratch, taking into account multiple concepts of illustrations of sexy women and as a result the following model of the most sensual tone of beautiful women.
I would like to see some of your creations if you like me as much as I do.
Find the model too huggingface: -> AdonisDreamBazal
I recommend some vae to improve the color of the images: orangemix vae
QR to my page buymeacoffee
If you love my work you can buy me a coffee : ko-fi.com/tauron you dont have to, but if you want, it helps me stay awake until midnight (which is the only time im able to work on these stuff lol) and cope with life..
a little background on why I'm making my own model...
Short answer is to better integrate with my own lora.
If you are aware i really love fantasticmix & henmix model, both are very great in creating the style i really like, and especially realism for henmix, be sure to check their models as well. I've been using their model alot and i love it, but i encountered these:
Since I'm starting doing my own lycoris, problems starts to arise like overbaking, distorted hands, multiple limbs, even with negative prompts and negative Ti already in place. especially with NSFW prompt, vagina & nipples gets really bad.
another reason is that Im quickly filling up my disk drive, with so much models that i ended up not using or having to test, i decided to just really make one that suits my taste & style and mix nicely with my own locon.
I like to have versatility in my model, i often switch between models because i want to go for conceptual art with realistic subject, other time i want to go for complete realism, this model tries to achieve that in a single model, while maybe its not perfect.
I like concise prompt, and not having to put too many enhancer prompts such as: photorealistic:1.4, ultra-hires, hi-res, hyperrealistic, masterpiece, 4k, 8k, rawphoto, cinematic lighting, absurdres , etc, etc, i just want to write realistic, and i want it to get there, so i can focus more on prompting the subject / environment / action instead of focusing too much on that part.
I use alot of 2:3 ratio instead of 3:2, so i need the model that is kind of optimized for this ratio.
If you ever watch kimi no nawa or suzune, it kinds of describe the anime style that i like. a very detailed environment, with a crisp outline. the anime version of this model achieved that with NSFW capabilities.
All in all basically i just want less headache and focus on creating beautiful stuff.
Style —> realistic , realistic details, detailed for realism / anime for anime / masterpiece , best illustration for conceptual art.
Subject —> describe your subject can be anything. 1girl, solo, cute, beautiful, slender, etc. if you use my character lora this should be where you put trigger words of the character
Attire —> describe the outfit of your subject. If you use my attire lora this is where you should put trigger words
Background / Context —> describe the context or the scene
You can follow your own prompting method, this guide only serves as a convention when you are having trouble producing similar results with my lora.
2M Karras provides good result with faster baking time.
CFG Scale
Lower CFG Scale means AI gets more creative and less overbaking problems. the down side is that the results tends to get a plasticky view.
Higher CFG Scale means results get more realistic, and very accurate with training sets and more prone to overbaking problems.
Dynamic CFG Threshold ( only use when necessary ) -- using this method allows you to bump up quality and achieve photorealistic easily, so you basically get both Lower CFG & Higher CFG Advantage and eliminate both problems, the downside is that sometimes it doesn't work with specific lycoris for some reasons. The settings that i most often use: Mimic CFG 5-10 , Clamp 99.5 Percentile, 2nd weight slider = 0 - Cosine Up, third weight slider = 15 Half Cosine Down (sorry i kinda forgot the name)
Repeats & Hi Res Fix
Higher repeats means your Ai has more time to generate the image, resulting in better result. generally 50 is enough, with 1/2 value for high res fix repeat.
I use 512 x 768, with ERSGAN_4x+ at 2x upscale. which then i will send to extras with upscaler to further 2x again with ERSGAN_4x or 4xUltraSharp (for anime). the settings i find superior are : GPFGAN @0.25, Codeformer @0.3 & weight 0.15
The rule of thumb is that there are no constant equation, you need to find one your own that suits what you are aiming, and sometimes you change these value on the fly depending on your goal. its better to know what these parameters do to your results rather than copying values from people's post.
几个常用模型都升级了，于是稍微升级了下之前的 X-I-base
依旧使用的底模为 revAnimated 1.2.2
增加对比度使用了 Ally's mix IV
替换亚洲脸使用了 BRA V5
融入了自炼的 mj v5风格lora(locon)，本章会附带MjV5 locon(需安装locon或lycoris插件)
Several commonly used models have been upgraded, so we have slightly upgraded the previous X-I-base
The bottom mold still used is revAnimated 1.2.2
Added contrast using Ally's mix IV
Replacing the Asian face with BRA V5
Incorporating the self-developed mjV5 style Lora (location), this chapter will include the MjV5 location (which requires installation of the location or Lycoris plugin)
Introducing StokeMakesArt Illustration Model: Unleash Creativity with AI Masterpieces
Are you searching for the perfect AI model to enhance your illustrations? Look no further than the StokeMakesArt Illustration Model. Designed to meet the needs of artists, this model is an ideal choice, even for low-spec systems like my ex Monero mining rig with a 1080ti.
While it may not excel in photographic quality, this model truly shines in the realm of paintings and illustrations. By harnessing the power of the Euler A technique, remarkable results can be achieved with just 8 steps and a CFG scale of 3.0. What sets this model apart is its efficiency – it consistently delivers impressive outcomes with minimal settings.
Many other models on the market require extensive steps to achieve similar quality, but the StokeMakesArt Illustration Model prioritizes both performance and remarkable results. It strikes the perfect balance, allowing you to unleash your creativity without overwhelming computational demands.
Feel free to experiment with different settings to find the sweet spot for your illustrations. The possibilities are endless with the StokeMakesArt Illustration Model. Download now and embark on an exciting journey of artistic exploration!
Stoke McToke
Pristhis model was mixed with a lot of models, i try to make it so it can produce photorealism and anime art.