VAE

游戏《碧蓝档案》中的角色白子/砂狼シロコ/shiroko这个lora是为了更好的换装，因此我没有把他和官方的服装绑定在一体,建议权重：0.6~0.8普通形态的prompt：1girl,shiroko (blue archive),ha...

<lora:kalo_kolodi_v2:0.75> 描述: 训练词语: ,Kalo_Kolodi,,dress,pantyhose,hat,medium_breasts,white hair,Suspender black stockings,highl...

Say it 3 times.Spoken Unbroken.Also included is the whole meme TI of "The first verse of the whole being dead thing"Yea, we have a hilarious habit of prompting for song lyrics,...

Say it 3 times.Spoken Unbroken.Also included is the whole meme TI of "The first verse of the whole being dead thing"Yea, we have a hilarious habit of prompting for song lyrics,...

Deep AnimePatreon - Open Commissions - Newest Patreon Realease: Breat Helper 2.0 Alpha 2After months of LoRA training, I decided to try my own model. After several hours, this ...

Deep AnimePatreon - Open Commissions - Newest Patreon Realease: Breat Helper 2.0 Alpha 2After months of LoRA training, I decided to try my own model. After several hours, this ...

Another merge. this time it's designed to make sonic styled characters. not just furries tho! but also human-ish characters in the furry style! (sounds cursed, but it's not as ...

Miniaturus Potentia is my sd 1.5 family of models using my main acheivements discovered and first implemented within SDXL/Proteus.trained on 220k GPTV captioned images and than...

Hello all! This is my first attempt at a merged model. It combines many of my favorite anime style models. Some suggested settings:Sampler: DPM++ SDE KarrasSteps: 30Size: 512x7...

I have personally have discovered it works best when using Euler a - 720 x 720 - and some prompts commonly used to improve quality (primarily this negative prompt ->(worst q...

在融合模型的时候，意外得到了这个画风,尝试用这个模型来生成颜色鲜艳、背景唯美的日系动漫风插图，将会是一个绝妙的选择,另外，有些2D模型似乎会破坏角色LoRA中的特征，这个模型似乎不太会...

描述: Baked VAE: MoistMix 训练词语: 名称: vae-ft-mse...

Just a merge I have some reasonable use of. (Break Domain + Based 65 + Richy Rich mix) 描述: 训练词语: ...

This is a very versatile 1.5 mbw model merge. My preferred sampler is 2M Karras and i usually use clip skip 2. Play with different negative embeddings as it might change the st...

Just another pointless merge that no one will ever use.It would be nice if you could show me something made by this model. 描述: 训练词语: ...

continuation of the LarosBell-2,5 with various adjustments to tidy up the lineartParameter recommendationsRecommended sampling method: Euler A, DPM++ 2M KarrasRecommended Upsca...

Like it? Buy me a coffee :)---With Stable Cascade released and SD3 imminent, it seems like the era of SD1.5 is ending. Here is a model showcasing what SD1.5 architecture is cap...

This is a very versatile 1.5 mbw model merge. My preferred sampler is 2M Karras and i usually use clip skip 2. Play with different negative embeddings as it might change the st...

✨✨Want your personalized LoRA or illustrations? Click here✨✨? Instagram http://instagram.com/tsumasaky? Twitter https://twitter.com/tsumasaky? Pixiv https://www.pixiv.net/en/us...

torino老师是我很喜欢的一位画师，由于过于喜欢torino老师作品角色的头发光泽和眼睛，于是练了这个模型，希望各位喜欢，如果觉得模型太亮，生成图像太乱的话可以将Clip Skip改为3，Clip Ski...