LORA

V2 DescriptionJust a quality upgrade for an older model :) and unintended side effect is that I think it resembles manga style more now. It's not perfect since I can still see ...

中国传统山水国画风格这是一个用来生成山水风景景观的Lora模型推荐权重：0.8 描述: 训练词语: ...

This LoRA is trained with 151 images, varying from cosplays to fan arts, of StarCraft 2's Nova.Simply load up your favorite model and use <lora:starcraft2Nova_20:1> for t...

This is a work in progress, try to archive good results with a hard concept for realistic results.Quality is a bit of a mess but i'm still learning this Lora thing a bit late.U...

This is a work in progress, try to archive good results with a hard concept for realistic results.Quality is a bit of a mess but i'm still learning this Lora thing a bit late.U...

Since the IllustriousXL model can already draw perfect feet, I decided to focus on trying to train a cute style lora.SD1.5 Version:https://civitai.com/models/54451/better-white...

I changed my training parameters for this one so it might perform slightly differently than before. However, I manage to reduce the size to 36MB for file size.If you want her t...

Trained on Pony Diffusion XLA collection of Art Styles I've trained from different places.Used ADetailer.No Trigger Words needed.Consider leaving a review!Check out Custom Pony...

The LoRA created from the artworks of Josan Gonzalez aka Deathburger.Recommended weights 0,7 - 1,0.••••••••••••••••••••••••••••••••••••••••••••••••••••••"Your support, can go a...

Trained on Pony Diffusion XLA collection of Art Styles I've trained from different places.Used ADetailer.No Trigger Words needed.Consider leaving a review!Check out Custom Pony...

?If you like???, welcome to leave a post and comment. Thank you!??It is recommended to use controlnet-tile_resample+ultimate SD upscale or Hires. fix.?Training model：AnythingV...

This LoRA is trained on photos taken with a fisheye lens.The base model is Suzumehachi. 描述: 训练词语: fisheye ...

2in1 v3f:I kept some tags in training so that it will be more flexible.保留了一些tag，会更灵活,When you choose one costume, it's recommend to add the other costume's main trigg...

This LoRA was trained on the works of German art nouveau and symbolist painter and illustrator Hugo Reinhold Karl Johann Höppener (1868 - 1948), better known as Fidus ("The Fai...

Blue Archive Toki modelthe model needs to enter the prompt of the detailed characterAOM3 And Powercolor2 are recommended for this Lora23/03/09The previously uploaded page was d...

need the prompt "robot"my training for this is 1e3, unet only, dim and alpha 1.cosine with restart /12 cycles.10 repeats /20 epochs.tips or requestshttps://ko-fi.com/luisapingu...

Version 2 is here and it comes with these improvements!Improved trainingNow when generating the image it no longer generates blur as in version 1.Much easier to generate screen...

Use to 1 ~ 0.8You can create a total of 11 outfits.She can change into different outfits and hairstyles by filling out the prompts!The keywords are '(costume), silver_hair'.If ...

A hairstyle that can show a woman's short wave cut, LoRA <lora:shortHairStyle_v10:0.8>Trigger word is 'short hair'.Male is also possible, but not recommended.I hope you e...

prompt : ffm threesome, group picture, double girls, love triangle, size difference, handjob : nsfw, cooperative handjob, handjob, testicles, negative : pov, multiple boys wei...