NSFW Lora for Qwen Image 2.1 (V2 OUT NOW)
In my opinion this is currently the best NSFW Lora out there for Qwen Image 2.1!
What i recommend for the best results:
25+ steps
3-5 cfg
0.8 for lora strength
er_sde for sampler (if i dont use this i get very bad results! This is kinda a must...)
beta scheduler
qwen3vl_8b_int8_convrot text encoder (smaller sizes can't really understand things like doggy in my experience)
qwen_image_2.1_int8_convrot diffusion model
detailed prompts work better...
Lora (v2) is mostly trained on:
Blowjobs
Cowgirl (reverse cowgirl)
Cum
Vaginas
Anal
Penis
Doggystyle
Missionary
Dildo
Pussy Licking
If you want to support me: https://ko-fi.com/thesealpacas
(This is not at all required, but this really helps me make more free loras!)
I made my own discord server where i post tips, updates and extra models!
Please let me know what works and what i should try to improve! :D
Description
Better anatomy, Better prompt following, Better detail/quality, Better realism, Trained on a more diverse dataset.
FAQ
Comments (24)
Loading the v2 LoRA gives me a “LoRA key not loaded” warning. Any idea why?
--edit--
ok after using "SamplerCustomAdvanced" native node instead the ksampler node the warning is gone and can load the lora.
Will it work If I use an anime input? If so, what strenght do you suggest to avoid getting a realistic output?
lora is trained on realistic images only so idk. maybe if u include a reference of the style as a image in edit?
@TheseAlpacas i will test after work tonight but yeah basicaly want to edit anime references.
@KiraNugget i just posted 2 of my generations using my lora in a edit workflow. it seems to work as long as the reference is the same style u want to generate.
@TheseAlpacas nice thank you!
I don't know why I see comments saying people are having problems; it works perfectly for me for image-to-image and text-to-image.
tysm for letting me know!
so true :D
So what's happening? Are we ditching Krea2 and embracing Qwen 2.1? If so, which one is better? If someone has tested both and can share some insights on them, like prompt adherence, quality, realism, etc., please reply.
i think krea2 still has better and more loras. i think qwen 2.1 is also very good, they are pretty close in my opinion...
Qwen has edit and reference capabilities.
Who is 'we'?
I'd never ditch Qwen for Krea currently. Krea is superior, what Qwen does have the advantage with for some things it editing and it is a different flavour, it will replace Klein for me which I used for editing stuff that Krea edit couldn't do (and tbh as good as Krea edit is it's still just a community project, Krea3 will blow away Qwen and Krea2 in all departments)
Overall I'd pick Krea2 if editing isn't that important to you but ultimately both are great. I'd spend the majority of time with Krea2 and get Qwen with a few lora's for editing or for when I want a different flavour/vibe from Krea.
I will be moving to Qwen2.1 as more lora and community support catch up with Krea2; Not because I think its superior, but having one model that 'does everything' is hugely convenient and saves on HDD space :)
Qwen 2.1 is massively superior to krea 2 (I say this as someone who loved Krea 2, & used it 90% of the time before Qwen 2.1 came along).
It has a much higher skill ceiling to get good results back from presently, however; though it can generate hardcore nsfw images right out the box, & with nothing other than the base model. It's edit capabilities are especially first class (though totally confusing relative to what everyone is used to).
Qwen 2.1 is going to have some real growing pains with the workflow regarding how Alibaba expects it to be used...but the community will accept it when they realise what it's capable of, or the rest of the community dumbs the workflow down to get it to that level. For right now; you're pretty much forced to to use their accompanying LLM models that released with it to get anything good out of it though (that, or a whole load of patience lol).
Once a good 4/8 step lightning LoRA comes along for it, & more LoRAs in general, then I think it'll really take off.
I've been around the generative AI community since early SD.
After spending a lot of time messing with it, I feel that Qwen 2.1 is objectively superior by nearly every metric. Krea 2 was hands down the best of the last generation of local i/t2i but Qwen 2.1 feels more like the first of the next gen.
It does love verbose prompting though, lol. There's a reason that the devs don't recommend using it without a PE LLM. That's likely going to be the case for all generative AI models going forward though.
For prompt writing, I'd highly recommend the HauHau version of qwen3.5 9b on HF instead of the official version of the same model that they just released. I was already using it for Krea 2 and other models as a PE so I wasn't too surprised when Q3.5 9b was officially recommended for use with Qwen 2.1. It's a prompt writing wiz but the two new variants that they released in the main Qwen 2.1 repo are a little wacky unless you're fluent in Chinese.
Also, both Qwen 2.1 and Krea 2 use Qwen VAEs which means they really need a nyquist notch node for higher resolutions. That just removes the noticeable 'screen door' effect without blurring or harming the image.
The best nsfw for qwen by far. I have one suggestion to improve anatomy of vagina and anus (without inserted/penetrated). Thank you
the golden era of hentai and s.. is here qwen, krea2 , anima, minimax xd
Can I use this with Viggle?
I have posted a comparison workflow. In that post i show some comparisons of viggle and this model.
@TheseAlpacas Thank you
FINALLY! only took the community a whole week to find its hero.
Mate! This is great work, very cool in 90% of my cases.
If you have the opportunity to enhance the dataset with deepthroat scenes, gaped anal, and generally more consistent anal content, that would be super cool!
@TheseAlpacas any chance of you making a NSFW edit lora for qwen2.1? The type of lora to fix or change genitals for example.