User LoRA

SD
Other

Esthetic Futanari + Trap (TRv5.8R) (Patreon)

#Otokonoko

Cover Removed: Content Rules violation

  • re-upload a cover image
  • you can still search and use this model
Uploaded at
Jun 4, 2023, 1:57 AM
Uses
4.26k
Reviews
No reviews
Trigger Words

otoko no ko, Small penis, Small boobs, Trap, Girly, Delicate, Erection, Phimosis, Foreskin

Permissions
  • Allow image generation & sharing
  • Allow users to download this model
  • Allow commercial use of generated images

Description

PS: I have 1 Pixai account with 1 million credits for sale. Pm on Twitter or Instagram if you are interested.

Esthetic Futanari + Trap (TRv5.8R) (Patreon) post description: (2023-May-03)

"It was excruciating, considering that there are more and more arts, one training of this lora took 14 hours, not to mention the selection of prompts for new 134 images. Enlarging the image showed a positive trend towards diversity, without any loss in quality, now there are more poses and they have become more accurate (with the back pose, the same problems, unfortunately). In general, I am satisfied with this version, and although new updates to this my most popular lore are becoming more and more difficult for me in terms of effort, but I think there is still a lot to be improved, as always I have thoughts on how to do it.

Improved retro, which in combination with my 90s lora has become much, much better."

Civitai Author notes:

Aesthetically beautiful futanari and traps. Full remake on new settings, new model, improved detail, improved retro style, many small improvements, this version is EVERYTHING better than the previous one, I did not find any shortcomings. New version TR5.8R (more arts, more poses, more retro style) on Patreon

For many arts, combinations of my lore were used, such as: Esthetic 90s style, Esthetic Urushihara Satoshi, Esthetic Lina Inverse (but new version from patreon)

I made a video on how to achieve the same quality or just repeat my art

Lora trained on almost 300 images with manual promts settings. Few big cocks, mostly medium and small ones in the sample, because models like to make house-sized cocks, I don't like that.

Eta noise seed delta 31337

Use Abyssorangemix3aom3_aom3a3.safetensors model

VERSION 5.0R much better with low weights. Use a weight around 0.2-.0.6, 0.7 and up is too "stylized" and too one-sided. Below 0.3 often makes a pussy, but you can try and add some basic key prompts: penis, futanari, otoko no ko, female focus, frenulum, small penis, large penis (carefully, but work), medium penis flaccid, phimosis - helps with size reduction and do what they say

Negative promts: artist name (necessarily, most of the art with watermarks), (worst quality, low quality, extra digits:1.4), multiple penises, multiple hands, multiple testicles,

just use hires fix as much as your video card is capable of, so as not to give an error, with 8gb of video memory it is 512x768 with hires fix 2, upscaler Latent (nearest-exact) or just Latent (if there are problems with the image), the picture will be much more detailed.

CFG Scale - 5.5-7 (for some reason hands are a little better at 5.5)

I used arts mainly: exlic, tofuubear, personalami and many many others

The training took place at a resolution of 512x768, so it makes no sense to use 512x512

Combined with my other LORA

How to use LoRA's in auto1111:

Update webui (use git pull like here or redownload it)

Copy the file to stable-diffusion-webui/models/lora

Select your LoRA like in this video

Make sure to change the weight (by default it's :1 which is usually too high)

*Information taken from Lykon

page on Hugging Face https://huggingface.co/OneRing/TP3.7.safetensors

Please post your work with or without comments, it will help me improve. Thanks!

If you like my work, click on the heart above, I will be pleased :3

If you like this LoRa and want to support the author:

https://ko-fi.com/onering https://www.patreon.com/OneRing

Credits: Author LoRa: https://civitai.com/models/7327/esthetic-futanari-trap Author profile models: https://civitai.com/user/OneRing/models

Comments1