only in certain countries I've heard in England they are actual gentlemen clubs where guys go grab a warm beer and bullshit similar to sports bars in the USA except guys only.
while i'm not british, this is correct. what we americans call that sorta thing is like the golfing or yacht club. sometimes even adventurer's club if it were closer to 100 years ago
Magister Crudi
Member
- May 23, 2023
- 266
- 184
- 109
Geez Aunt Becca. Maybe next time take your dentures out before you give me a blowjob.
AccidentalGadgeteer
Active Member
- Oct 8, 2020
- 815
- 1,150
- 267
Magister Crudi
Member
- May 23, 2023
- 266
- 184
- 109
Well spotted.
That sort of thing is a reminder AI is only 'intelligent' when compared to the marketers who first applied the term to digital parrots and the suckers who'll be left holding AI startup shares when the bubble bursts.
Still, according to Terry Gilliam even human artists have problems drawing hands.
Last edited:
I downloaded you suggestions but what do I run them in? Is there a software I should use?
My goal is to create the images but animate them for the sexual activities.
johnysanchez01
Member
- Dec 26, 2018
- 115
- 576
- 160
Unless you're using tightly managed ComfyUI workflows Stable Diffusion models will result in various noticeable defects. It's just how SD-based models are. Yeah you can get really high quality images out of SDXL but it takes a lot of work to get it right. But I understand why people use SD and its variant models, they're relatively easier to run and generate images faster with compared to the likes of Flux and Wan.
I think the path forward for this kind of integrated AI image generation in games is with image editing models like Gemini-2.5-Image-Flash (Nano-Banana) and Qwen-Image-Edit, but decensored of course.
Nano-Banana in particular can generate realistic images based on 3-D models very quickly (check em out below) so it makes me think even if it'll never be open-sourced we'll have an editing model like this open-sourced in the next year or so. Of course even the image-editing models that are open-sourced from China will come with extensive censorship because no one wants take heat for being able to create deepfake porn of real people so easily, which is understandable.
Qwen-Image-Edit isn't as good as Google's model and the requirements to run it properly are kind of steep but it's still very impressive + you can use LoRAs with it. The Qwen team is updating their vision-language model from 2.5 to 3 and they're also making an omni-model so I'm pretty excited to see what the next version of Qwen-Image-Edit will be like. If the next iteration of Qwen-Image-Edit becomes easier to run locally I think I a lot of people will be making NSFW LoRAs for it.
I tried Flux-Kontext-Dev and it was alright. Flux has the easiest to run image editing models and they have better prompt adherence than Stable Diffusion models, but they still have that plasticky look to them from all the synthetic data they used. Hopefully newer Flux models will come out that look better and are easier to run.
I tried the Seedream 4 model but it didn't give me good results at all. It's weird cause Seedream 4 can give better results than Nano-Banana in a lot of cases.
I think the path forward for this kind of integrated AI image generation in games is with image editing models like Gemini-2.5-Image-Flash (Nano-Banana) and Qwen-Image-Edit, but decensored of course.
Nano-Banana in particular can generate realistic images based on 3-D models very quickly (check em out below) so it makes me think even if it'll never be open-sourced we'll have an editing model like this open-sourced in the next year or so. Of course even the image-editing models that are open-sourced from China will come with extensive censorship because no one wants take heat for being able to create deepfake porn of real people so easily, which is understandable.
Qwen-Image-Edit isn't as good as Google's model and the requirements to run it properly are kind of steep but it's still very impressive + you can use LoRAs with it. The Qwen team is updating their vision-language model from 2.5 to 3 and they're also making an omni-model so I'm pretty excited to see what the next version of Qwen-Image-Edit will be like. If the next iteration of Qwen-Image-Edit becomes easier to run locally I think I a lot of people will be making NSFW LoRAs for it.
I tried Flux-Kontext-Dev and it was alright. Flux has the easiest to run image editing models and they have better prompt adherence than Stable Diffusion models, but they still have that plasticky look to them from all the synthetic data they used. Hopefully newer Flux models will come out that look better and are easier to run.
I tried the Seedream 4 model but it didn't give me good results at all. It's weird cause Seedream 4 can give better results than Nano-Banana in a lot of cases.
If I want to make realistic NSFW pictures and video which software/pipeline do you recommend?
AxelVieyra
Member
- Jul 10, 2021
- 301
- 70
- 152
Guys, what are your genAi version, mod settings and "presets?" ( dont know the word for the models) because the one I have takes like 7 minutes each image even if the resolution is low.
Magister Crudi
Member
- May 23, 2023
- 266
- 184
- 109
johnysanchez01
Member
- Dec 26, 2018
- 115
- 576
- 160
When it comes to getting high quality nsfw pictures you can pick 2 of the 3: Ease of Getting High Quality Outputs, Lower VRAM Requirements, and Lack of Censorship (usually tied to amount of LoRAs available).
I'm no expert at generating AI images but I'd say the best methods are as follows:
A) Use Flux models with tools like
You must be registered to see the links
or
You must be registered to see the links
. Flux models are a great place for beginners to start since they have better prompt adherence than Stable Diffusion models and have quite a few tools that will give you NSFW outputs without steep VRAM requirements. Flux Kontext will also let you iterate on existing images through text-prompts. The only problem is they won't give you the most high quality images, but it's an acceptable tradeoff for many since Flux outputs often have less defects than SD outputs.B) Get good at learning how to use Stable Diffusion models like SDXL or a SD variant like Pony Realism with
You must be registered to see the links
workflows. This is the most time consuming and difficult path, but done properly it will give you excellent results that are on par with or better than SOTA image models without needing as much VRAM thanks to the extensive tools and LoRAs available for them.C) Learn to use Wan 2.1/2.2. While technically a video model, people realized quickly that generating 1 frame with Wan models was a great way to generate high-quality, prompt adherent images. Middling requirements for VRAM as well, especially if you're going for single-frame images. Something about it being a video model gives it really good understanding of where things should belong in a picture. Unfortunately it's harder to get really nsfw outputs from it due to the lack of LoRAs
D) Use SOTA models like Gemini 2.5 or ChatGPT5 to generate good sfw starting images and then iterate on those images using their inbuilt image editing tools, then modify those pictures using local AI tools that allow for inpainting and your own editing skills.
*A note about VRAM requirements: While you will see people claim to be able to run more powerful models on lower VRAM with quants, remember that without pictures their claims of "good" outputs should be taken with a grain of salt. Lower quants will result in lower quality images and/or lower prompt adherence most of the time, and you'll have to get creative with your ComfyUI workflows to make up for that. Even if you get a good workflow going, without a powerful GPU you will be waiting a lot for these images to generate.
If you want something where you can just get hardcore nsfw images of good quality by just prompting, you'll just have to keep waiting for now. That doesn't exist yet, and there's a lot of incentive to not make generating hardcore nsfw content easy and accessible with AI. Those AI image generation websites that offer subscriptions or token-based pre-payments? Don't use them, they're ripoffs and are bound by censorship rules. Learn ComfyUI. There's no better alternative.
Last edited:
I'm running the latest development version with the new Nora path and I can't get the event that unlocks the Tier 2 serums with Nora, only the "pay 2,000 for the prototype" option. In my previous save (again, with the new Nora path) I was able to get the four Nora Traits in the good old way, so I guess there are some specific requirements that I haven't met yet?
elfelganor
Member
- Jun 19, 2017
- 153
- 144
- 217
I am not sure, but I think that route got divided. In her Love route, she asks for a bunch of unstable research for money.
maybe it's bugged because i used in-game cheats? what is her threshold to advance her story? i can roll it back with same cheats (i think i can)
After choosing Erica's girlfriend path instead of FWB path, her storyline seems to be stucked in "try getting to know Erica better" and I think I've missed the yoga class scene or something. Even if I keep selecting "get to know her" in the gym, there wasn't any new content coming up. Is there anyways to fix this problem?