TechnoMonkey
MUST INCLUDE THESE AT BEGINNING OF PROMPT FOR BEST RESULTS
Positive Prompt: futanari, no_testicles, erection, long penis, pussy
Negative Prompt: (testicles:1.2)
Clip Skip 2 with HighRes-Fix recommended @ 0.3-0.5 denoising ratio seems to work best. Higher denoising tends to close up the pussy and replace it with balls again.
Also works great for inpainting on existing images with ONLY the recommended prompt
I was very frustrated with the fact that there were no real TRUE futanari models out there, specifically where the subject has both a penis and a vagina (preferably without balls). All existing models are just various kinds of trans women, and while that is perfectly fine, it's not what I would consider a "futanari".
The "Tamanashi (no testicles)_futanari" lora exists but it tends to COOK images at high weights and doesn't work in many more realistic/3D looking models. So I went on a quest to selectively combine it and other good NSFW models together in various ratios until I came upon one that could CONSISTENTLY make good looking True Futa's while still being able to use other Textual Inversions and Lora's on-top without ruining the look or losing the effect.
This model is capable of making Solo Futa and also multiple futa engaging in various sexual positions.
What is True Futa - Penis + Pussy + No Balls?
True Futa - Penis + Pussy + No Balls is a highly specialized Image generation AI Model of type Safetensors / Checkpoint AI Model created by AI community user TechnoMonkey. Derived from the powerful Stable Diffusion (SD 1.5) model, True Futa - Penis + Pussy + No Balls has undergone an extensive fine-tuning process, leveraging the power of a dataset consisting of images generated by other AI models or user-contributed data. This fine-tuning process ensures that True Futa - Penis + Pussy + No Balls is capable of generating images that are highly relevant to the specific use-cases it was designed for, such as anime, girl, hardcore.
With a rating of 4.55 and over 11 ratings, True Futa - Penis + Pussy + No Balls is a popular choice among users for generating high-quality images from text prompts.
Can I download True Futa - Penis + Pussy + No Balls?
Yes! You can download the latest version of True Futa - Penis + Pussy + No Balls from here.
How to use True Futa - Penis + Pussy + No Balls?
To use True Futa - Penis + Pussy + No Balls, download the model checkpoint file and set up an UI for running Stable Diffusion models (for example, AUTOMATIC1111). Then, provide the model with a detailed text prompt to generate an image. Experiment with different prompts and settings to achieve the desired results. If this sounds a bit complicated, check out our initial guide to Stable Diffusion – it might be of help. And if you really want to dive deep into AI image generation and understand how set up AUTOMATIC1111 to use Safetensors / Checkpoint AI Models like True Futa - Penis + Pussy + No Balls, check out our crash course in AI image generation.
Popularity
Info
Latest version (v1.5 + Baked VAE): 1 File
About this version: v1.5 + Baked VAE
New Mix Recipe
==============
Stage1A = gape60-fp16 + tamanashiNoTesticles_v09:0.3,mLegGestureUltimate_v51:0.35,realSpreadPussy_sppSpreadpussyV3:0.35
Stage1B = GooeyMix + tamanashiNoTesticles_v09:0.3,mLegGestureUltimate_v51:0.35,realSpreadPussy_sppSpreadpussyV3:0.35
Stage2 = Stage1A + Stage1B @ 0.5
Stage3 = Stage2 + (BastardLiveV5 - v1-5-pruned-emaonly) @ 0.15
Stage4 = Stage3 + PerfectWorldV1 @ 0.3
Stage5 = Stage4 + showpussy_v10:0.3
Stage6 = Stage5 + GooeyMonsterCock @ 0.1
V1-5 = Stage 6 + CustomFutaLora @ 0.3
==============
Not sure if this one is better or worse than the original release, it can do some prompts better and some turn into disasters. I tested training my own Lora with some hand sorted Booru images specifically narrowed down to Futa without testicles and a visible pussy. As a result it can do some positions MUCH better than the previous version, and also can do darker skintones without the need for a Lora, but more testing is needed. I will release the Custom Lora once I've had a chance to refine it further and increase the dataset.
Using "no_testicles" instead of "no testicles" is recommended in the positive prompt, as that was trained in the merged custom lora and should get better results
3 Versions
Go ahead and upload yours!
