My models are just a mix of everything that you yourself can find on this wonderful site. I'm not chasing fame, I don't need your money, I just sometimes spend a few hours of my free time experimenting with my favorite models. The page with this model exists on this site only because once my friends asked me to share their mix. And because it's just damn convenient. Please don't accuse me of stealing someone's property. Considering what we're all doing here, that's a little ironic. In my mixes, I use such checkpoints as Luma, RevAnim, DDosmix, Perfect World, GalenaRedux, DarkSushi, CosmicBabes and so on. I don't even remember all the model names. I don't do anything that you can't do yourself.
Try, experiment, enjoy!
Here is the workflow for my pictures:
Sampler: DPM++ 2M Karras (because it runs faster on my weaker hardware, while giving a good result)
Base image size: 512x768 (because I don't have enough VRAM for more).
CFG Scale - 7. Steps - 30.
Default negative line: EasyNegative, drawn by bad-artist, sketch by bad-artist-anime, (bad_prompt:0.8), (artist name, signature, watermark:1.4), (ugly:1.2), (worst quality, poor details:1.4), bad-hands-5, badhandv4, blurry, child, loli, kids
Then I generate 5 pictures to identify any obvious problems, after that I make another 10-20 pictures, choose the best one from them and proceed to the upscaling stage.
I turn on the option Hires.fix
Upscale by - 2 (because I don't have enough VRAM for more)
Upscaler - 4xUltraSharp
Haires steps - 15 (half of the steps from the first stage)
Denoising strength - from 0.3 to 0.6 (the larger this value, the more detailed the picture will be, but the greater the risk of getting artifacts and distortions in those places that the neural network considers doubtful or incomprehensible)
Turn on ADetailer. The 1st is - face_yolov8.pt, the 2nd is the mediapipe_face_mesh_eyes_only. If necessary, I fill in its positive and negative lines, but more often this is simply not necessary.
PROFIT!
Description
This version is my attempt to make a checkpoint that can create futanari pictures a little easier without any LORA. I can’t say that I succeeded, but I liked the result, so I decided to post it.
But then suddenly it turned out that this version copes well with everything else!
FAQ
Comments (21)
The Futa version is not working. When I try to create an image there's no futa. They have to have both a vagina and a penis to be futa.
Could you add some explanation on your new model's focus, the best ways to use it, etc? The samples are varied, some are more normal sized tgirls, one is big, just in general a bit of info would be helpful :D
In fact, the new model simply perceives LORA, designed for drawing dickgirls, a little better. And in some individual cases it even copes without LORAs at all.
Iris posted a futa version of Darksun!???!! It isn't even my birthday! Hot diggity dog, I can't wait to try it. Thank you Iris!!!
Thank you, @ttb2112! Enjoy!
Gorgeous models! Great work, and thanks for adding a futa version! It's very easy to use. Question: what model do you recommend for inpainting on pics made by this model?
I have immediate plans to make an inpaint model for Dark Sun 4.1 and Dark Sun 4.0.
Iris, I'm loving FutaSun! I've generated almost nothing else since you released it. I do have a couple of requests if you choose to work further on it. Please add some penis size control. Even though I prompt for small medium large or huge, it doesn't listen very well. Also, it doesn't seem to understand flaccid. :( You can rarely get a flaccid one, but its random and rare. Lastly - sorry, this is a wish list, so please don't take it as criticism - the model really doesn't understand "tucked penis" for those rear views. Is there another term I should be using?
On the up side: I love the way it easily handles having the futa wrap a hand around their own penis. That's pretty rare in the other futa models, and hard to get to work. But yours does it out of the box. Nice!
Anyway, I want to thank you for this model. It's fantastic and I'm a huge fan. Thanks again!
Hello! FutaSun was created as a necessary measure, since I noticed that the original DarkSun does not always work perfectly with loras trained on futa and other types of penises. That is, the checkpoint itself is not independent for drawing futanari. At least for now. I have distant plans to fix this, but for now my GPU is too weak to bother with it.
@Iris_DS Mind if I ask what GPU you're using?
@ttb2112 2070RX
@Iris_DS Ah, OK. I had a previous GPU lying around that I thought I might send you, but it's older than yours, so won't do you any good. :(
I recommend the VAE MSE-840000
Using exactly the same data:
Improves the finish of both hair and eyes, as well as the rest of the clothes.
Visually it does not modify the colors.
Hello.
All the latest versions of my checkpoints already have backed VAE and do not need it by default. Or are you talking about using VAE additionally?
[@Iris_DS]
I always check the model if it needs VAE.
I should have indicated that I was using version 4.1
─
But I didn't know until recently that all the comments are mixed together.
It's a bit confusing XD
DarkSun is the repeat ex-girlfriend of Checkpoints! Some are more beautiful than her. Some are more adaptable than her. Some are the type you take home to momma. But none are as gritty, naughty, sensual, primal or gratifying as her!
DarkSun doesn't claim to be the best... Because she knows you're going to come crawling back begging for her to do those things that only she can do... The things that you keep behind closed doors and drawn curtains. The things that make your knees weak and your heart thump.
DarkSun is that checkpoint that you are guilty to love but can't quit!
<3 <3 <3
In one of your futa images I see you're using <lora:flaccidv2>, I can't seem to find this lora, could you point me to it please?
https://civitai.com/models/203199
You can take it here
Sorry to bug you. I was looking at the comments and didn't see anyone not understand the hires.fix part in your overview. I googled and there's an issue with hires.fix? When I go to extras, I don't see any of the options to select on my UI.
it is under the sampling methods
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.