My models
Support
Place bid in the Auctions section for availability in the generator
Pony model
At this point I feel like there's not much reason to keep using the SD 1.5 models since the pony models have better understanding of pretty much everything. And since I can only have 2 models for on site generation I'll see if this one gets added instead of the SD1.5 v1.3.
Prompt
score_9, score_8_up, score_7_up, (anywhere in your prompt)
Negative Prompt
score_4, score_3, score_2, score_1, (or empty)
Sizes / Resolution
A baseline of 1024 x 1024 should give good results
896* 1152 for ~3:4 aspect ratio
Everything bellow is for SD1.5 verions
Lore / Backstory
I just wanted a model that could generate high quality art and hentai and that actually followed the prompt. Couldn't find one so I made it myself. Hope you like it and share your generations with everyone!
I hope this model doesn't become just another pointless merge that no one will ever use.
Using the model
The best advice I can give you is to experiment for yourself and see what works for you. So you are encouraged to completely ignore this and use the prompts/settings you like and find ways to get the best results out of this and any model.
Like Danbooru's Rule of thumb "Tag what you see, not what you know", don't use words that should not be visible in the final image.
IE: Don't use words for shoes if you are making a portrait or upper body image
Prompt
Use danbooru tags or sentence-based prompts.
You can use any generic filler prompts like: masterpiece, best quality, high quality, highres, etc..., or none.
Extension for tag autocompletion tagcomplete
Prompt Order for good composition
Tags at the start have more influence than the ones at the bottom.
The 7 blocks template (Work in progress):
participants, sex acts, view angle
posture, positions and secondary actions
secondary actions,
head orientation (looking back, looking at viewer, etc...),
body
breasts size, stature (petite, tall female, etc...),
age (mature woman, old woman, etc...),
body fat (skinny, curvy, plump, fat, obese, narrow waist, etc...),
hair
clothing or lack of clothes
face expressions, cum location and eye color
scenery and others
furniture and objects that should be visible,
styles
character (probably only if it was released / popular before early 2023)
(hatsune miku, ganyu \(genshin impact\), etc...)
You don't need to fill in every category, it's just for reference.
Negative prompt
You can just use EasyNegative or some of the generic prompts:
worst quality, low quality, bad quality, normal quality, bad anatomy, monochrome,
And whatever you don’t want to be on the image
Some people use the standard (worst quality, low quality: 1.4) + negative embeddings with good results too.
If you use too much emphasis, like (worst quality:2.0) you'll start getting burned images.
Samplers
You can use any sampler. Some samplers converge at a defined image, others keep changing with each step. You can find better explanations here and here.
I'd say the top choices are:
DPM++ SDE Karras (slow)
DPM++ 2M Karras (fast)
Euler a (fast)
DPM adaptive (slow)
DPM++ 2S a Karras (slow)
DDIM (fast)
Steps
25 - 50
CFG
7: standard
3–15: working range
Lower cfgs don’t follow the prompt as much. Higher cfgs will make “burned” images
The extension sd-dynamic-thresholding can play around with different CFGs at different steps
Sizes
1:1 [512, 512], [768, 768]
2:3 [512, 768]
3:2 [768, 512]
You can use Hires fix to get a bigger picture with more details
Upscaling
I'm getting good results with Hires fix enabled.
Upscaler: Latent nearest-exact
Hires steps: 20 - 50
Denoising Strength: 0.5 - 0.55
Upscale by: 1.5 - 1.875
Denoising at 0.5 seems the most stable for preventing duplicate body parts and body horrors
Latent upscalers tend to create more detail while upscaling, the rest of the upscalers don't add too much to the base image with the same settings.
VAE
There are many VAEs out there. These are the 3 most popular.
kl-f8-anime2 for vibrant colors and anime face/eyes
orangemix.vae for muted colors and anime face/eyes
vae-ft-mse-840000-ema-pruned for vibrant colors and real face/eyes
Baked VAE for each version.
v1.0 has vae-ft-mse-840000-ema-pruned.VAE baked in.
v1.1 has vae-ft-mse-840000-ema-pruned.VAE baked in.
v1.2 has vae-ft-mse-840000-ema-pruned.VAE baked in.
v1.3 has kl-f8-anime2 VAE baked in.
The [no VAE] variants don't have any VAE baked in.
Permissions
Just use the model and share your generations here or wherever you want
I’d appreciate if you link to this model page when sharing your generations 😊
I made a patreon if you want to support me https://www.patreon.com/TianChimp
Please share your generations!
Tag considerations
I've noticed some tags having too much influence over the entire image resulting in a loss of style and quality, but sometimes they are necessary for your target composition. This is probably only noticeable on <75 token prompts.
You can try setting lower influence with parentheses IE 0.5 - 0.9 Needs more testing but I'll keep a list of potential suspects.
fellatio (tends to put hand around the penis)
cum (variations)
multiple boys
FAQ - Frequently asked questions
My images look desaturated, with dim colors
Your software is probably missing/not using a VAE. The main model v1.1 doesn't include one, so you can use any VAE you want. The model v1.1 [VAE] comes with the standard VAE baked in, so it uses that VAE and ignores the selected one.
Different interfaces have different ways of selecting the VAE. In Automatic1111 you can set a VAE selector next to the model selector by going to Settings > User Interface > Quicksettings list, and adding "sd_vae".(Apply Settings and Restart UI)
That'll result in your interface looking like this:
Your vae selector will look for files located in your VAE folder, like "SD-1.6\models\VAE", so you have to download the VAE files you want and place them there.
Description
FAQ
Comments (19)
Is there a good way to make a woman lay flat on her back? All attempts lead to them kind of being arced or tilted, but I think there should be enough flat-on-back images in the training data for it to be able to do it well and cleanly if I knew the preferred wording.
Why do futa always have larger cocks than mine? Those are 13” cocks at least, there should be a dedicated hermaphrodite lora with average cock size like 6-9”. Also an optional no-balls in the lora.
Strange model. In 1 of 50 I am get good or very good image. Other 49 of 50 just full crap. Deformed, merged, manga-style multipanel, full of "text" or something else. Negatives like "manga, text, multiple panels" do nothing.
You can refer to examples like prompts. Specifically, if you add 'tiling', the 'multipanel' effect will be removed.
May I have a look at some prompts you've tried?
The flat shading in hentai makes these types of models prone to making limb splits. You need a lot of negatives and a relatively high count of steps. Show preview images every five steps to get a better impression of where and when things are going wrong with deformities.
Better to run in batches of 10. Some will be bad but that's the current state of these models.
anime merges often do strange outputs very frequently
Yeah, I am having the same issue, it's creating nightmarish abominations.
@megaman93249 tested it by myself - and unfortunately = AGREE
Why are animated pictures deleted? Are they forbidden?
I'm not sure, the TOS have not changed I think.
You should only be careful with depictions that resemble any of the points below.
TLDR: No minors in sexual/provocative contexts, rape, bestiality, drugs, photorrealistic minors regardless of context, and poop.
Though I can attest that these rules are not rigorously enforced, nor enforced equally.
Or maybe they just want to save some space lol.
"Content depicting or intended to depict real individuals or minors (under 18) in a mature context. For a more detailed explanation, please review our guidelines on depicting the likeness of real people and depicting minors.
Content promoting illegal or violent activities, including, but not limited to:
child abuse and exploitationrape and domestic abuseillegal substances or product sales requiring permits/licenses (e.g., pharmaceuticals, narcotics, pets, firearms)fraud, deception, or false impersonationbrutal fights, graphic injuries, or human deathgraphic violence or bestiality
"Loli", "lolicon", "shota", "shotacon" content
Content depicting or intended to depict photorealistic minors, regardless of context. For a more detailed explanation, please refer to our guidelines on depicting photorealistic minors.
Content depicting the excrement of "scat" or fecal matter.
Content that is disrespectful, offensive, or promotes hate speech, discrimination, or harassment based on, but not limited to:
Religion or religious beliefsNationality, ethnicity, or raceGender or sexual orientationDisability or medical conditions
Content Duplication and false impersonation.
Content falsely labeled as having been created or endorsed by another creator, or impersonates another creator on the site."
I hope that a girl with a normal breast size does not count as a minor. And I can see these images on my profile page. Just all animated images were deleted from the model's page. Not only mine. Thanks for your answer.
May I ask what models you merged to make this?
Great model! Works perfectly and has the best backgrounds ive seen in any model! Even works surprisingly well with non-hentai prompts!
The 7 prompt block method works really great. Is there any way to describe the boy as well though? I want both to be depicted a certain way but it always gives me the "default guy" sniff
Once you start describing clothing, body for the male, they are applied to the girl as well and it starts conflicting with the positions/actions etc..., so I don't think you can do it at generation.
Depending on the composition you can add more generic tags like old man or something
@TianChimp I thought as much T_T I hope technology will advance soon until then I have to be patient. Thanks for replying.
@TianChimp @Kikushi You may be able to use Regional Prompter to achieve what you're looking for. It allows you to specify prompts only for specific parts of the image. It takes a bit of practice but once you've got it under control, it will give you much greater control over the results
@haniasita731 thank you so much. I do have it for testing but like you said it is a bit tricky to get used to :D