It is a general NSFW Ref2VA LoRA for 2D/3D animation. So missionary, BJ, titfuck, cowgirl, handjob. Detail comes from your reference images. If they don’t include a detailed penis, you won’t get one, and the same goes for other anatomy.

Ref2va version for minimax is finally done! Minimax version was not trained on eros, the LTX version was but minimax version works just fine on eros. This took so goddamn long to complete. Really don't know what it is with minimax but it is hard as fuck to train right. Maybe its a skill issue on my part idk. Anyways with minimax the prompt is the most important thing! You cannot caveman prompt minimax and get a good result. Minimax likes to take what you say literally so saying bounce too many times or describing her hips moving at the same time as you describe his hips moving will cause either stutters or them moving at the same time which then causes shallow penetration or both. Ive noticed this on every NSFW lora/model ive tested minimax is super sensitive to prompting. Which means for the best results you need a strong LLM. Qwen 3.8 27b does just awful at it IMO in my testing so I stick with something like Grok fast or GLM 5.3 flash NVFP4 for prompt writing. Just give them a proper system prompt. Grok is really good at prompt writing. This version has been through several rounds of DPO RL to get it to behave nicely. And that took a month to figure out how to do right. This version is also trained on over 3k vids like the LTX version was. Its trained for ref2va but you can use ref2va with a single input image as well if you like and IMO it works better than fl2va at i2v. TURBO LORA'S AND ATTENTION SPEEDUPS WILL NERF QUALITY! With minimax its either quality OR speed not both. Trained on sound but sound is not perfect.

Pairs great with my NSFW motion enhancer lora. I usually do AIO lora 1.0 strength and motion enhancer 0.7.

____________________________________LTX VERSION INFO BELOW_________________________________

The model pairs well with the OmniNFT RL lora it helps the sound a lot and improves texture quality | There should be at least 6 videos up if not then Civit is being slow with the rating system | If this model does well with everyone then there will be future versions for the new LTX model light tricks is making I think its named LTX next | This lora is my largest NSFW training run trained on 3775 videos and keeps character identity well. Trained on oral, missionary, titfuck, doggy, cowgirl etc pretty much all NSFW positions. Its been trained on both 2D and 3D, furry and standard NSFW animations. It handles these all very well but has not been created to replace all other loras. Even Sulphur 2 requires extra loras for most things and its a FFT. It was trained on 10eros 1.4 but videos are generated with 10eros 1.2 because I did not have much luck getting good gens on 1.4 with the DMD lora or normal distilled lora not really sure why but could just be a skill issue on my end. The lora has not been overtrained on the dataset so you should not have any style bleed if your doing videos that do not involve any anthro. It does well with not contaminating 2D generations with 3D look which is something I notice most loras will do to 2D since most training data is not 2D. If you train with too much 2D relative to 3D it will cause issues like frame drops and smearing, I think that has something to do with the VAE's compression not playing well with just pure 2D. But if you have a good ratio of 2D to 3D data preferably much more 3D than 2D it turns out well. Most of the training data is 3D animation with only about ~10% of the training data being 2D

It wasn't trained on audio since most videos either had no audio or low quality audio so you may need to use the NSFW furry lora by mylo for audio only. If 10eros 1.4 works well for you then this lora will likely work even better if you use it but if not use something like 10eros 1.4.

Has some known issues like random music and not perfect audio.

You can make money with my models. Sell what you generate, use it in paid work, run it on paid services, merge it, sell the merge all of it, no permission needed. Credit is appreciated but never required. New releases might have a short early access window behind Buzz, then go free and free is permanent. Once a model is free, I will never re-paywall it or pull it for a paid platform, and you're welcome to mirror, archive, and rehost it so it stays free no matter what happens to any one site.

Feel free to mirror any of my loras to HuggingFace

Disclaimer & Terms of Use

This model is provided "AS IS", without warranty of any kind, express or implied, including but not limited to the warranties of merchantability, fitness for a particular purpose, and noninfringement.

IN NO EVENT SHALL MisticRain69 BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH USE OF THIS MODEL OR ANY OUTPUT GENERATED WITH IT.

18+ only. You, the user, are solely responsible for anything you generate with this model and for ensuring your use complies with all applicable laws and the CivitAI Terms of Service.

You may not:

produce anything illegal, non-consensual, defamatory, or used for harassment, deception, or fraud;

create any content depicting, or appearing to depict, minors (real or fictional) in a sexual context — no exceptions, ever;

use this model to depict any real, identifiable person — celebrity, public figure, or private individual — in any context, SFW or NSFW. No likeness use, period.

If you post outputs to the gallery that violate the CivitAI TOS, you'll be blocked and reported. Don't do this shit. Don't be fucking sus.