P.S. If you want to support me, then you can subscribe to my Patreon and get builds earlier than they come out here (versions on patreon will always be newer by one than here) This will help me a lot in updating the video card over time to make models even better and faster (the main thing is better)
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 a weight around 0.3-.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 - 3.5 to 6, mostly use 3.5-5, occasionally 6
I used arts mainly: exlic, tofuubear, personalami and some 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
New version TR5.0 (full improved remake) on Patreon
About version 4.1 - now better in retro! This is my last attempt to teach lora into something unusual, like auto-fellatio or better rear poses, some are successful, some are not, the number of arts has been increased to almost 300, there is more variety, but the lore is already a little "burnt" , use CFG Scale 4-5, no higher. In the new version 5.0, I started everything from scratch and the results came out even better than I expected. There will be updates, so version 5.0 will be in the public domain, don't worry
Go ahead and upload yours!
Your query returned no results β please try removing some filters or trying a different term.