Model

v2.0Trained by 60k images from Danbooru and Gelbooru + 8k AI-generated images.・UNet lr= 5e-6 ~ 3e-6・Text Encoder 1 Lr = 3e-6 ~ 1e-6・Text Encoder 2 Lr = 2e-6 ~ 7e~8To prevent...

Recently I released my embedding toolkit which has a variety of tools and fixers I've come up with over the past 6 months. I considered adding my emotion embeds to that listing...

Deep Blue XLJust keep mixing the successive BluePencil XLAboutThis model is a illustration merge model.このモデルはイラスト系のマージモデルです,simply a model that repeatedly m...

For business inquires, commercial licensing, consultation and large scale image captioning for datasets contact me under [email protected], for custom LoRAs visit my ko-fi...

我的其他检查站和Lora,My other checkpoints and Lora.此版本过于老旧，不建议继续使用，请使用新版本:PornMaster-Pro or PornMaster-Amateur.This version is too old and is not recommen...

Recommended SettingsVAE : kl-f8-anime2Steps : More than 30 stepsCFG scale : 6-8Sampler : DPM++ SDE Karras /DPM++ 2M Karras /DPM++ 2M SDE KarrasHires upscaler : 4x-AnimeSharp /L...

Lora trained on 235 images of Milim Nava.Prompts:def1, rnd1,Prompt meanings:default outfit, randomShould be more flexible nowTrained on NAI, gen'd on AOM2 nsfw ...

EnvyMix is an anime and semi-realistic model that is a cosine merge of several merges of high quality models. It's reasonably good at hands, it does nice backgrounds, and it c...

这篇帖子是一些偶像打歌服服饰合辑This post is a collection of some idol costume.FLUX Version: [Flux.1 D][Realistic] Idol costume | 偶像打歌服触发词/Trigger word:请参考各个版本的...

EnvyMix is an anime and semi-realistic model that is a cosine merge of several merges of high quality models. It's reasonably good at hands, it does nice backgrounds, and it c...

NEWEST: ACTUALLY COMPETENT TAGGING. ALL EXAMPLE IMAGES ON COMBINED V2 ARE RAW GENSTHESE ARE LORAS FOR THE MAIN SIX SPLATOON CHARACTERS: CALLIE, MARIE, PEARL, MARINA, SHIVER, AN...

Right now there is a very popular style for cartoonish emotes in twitch. I made a LORA sampling 100+ emotes from many channels.This LORA is a little hard to tame, but it works ...

简述 - sketch欢迎使用武墨模型，这是一个武侠与墨风交融的Lora==========Welcome to the Wumo model, which is a Lora that blends martial arts and ink style注意1 - Attention 1注意1！...

AnE v5 is out,Featuring a semi-realistic art style, the newest edition in my Anything and Everything series is here!Keeping with the style of my previous versions, this one has...

NEWEST: ACTUALLY COMPETENT TAGGING. ALL EXAMPLE IMAGES ON COMBINED V2 ARE RAW GENSTHESE ARE LORAS FOR THE MAIN SIX SPLATOON CHARACTERS: CALLIE, MARIE, PEARL, MARINA, SHIVER, AN...

Negative Prompt: rMadaNegative4 (SD 1.5) | Stable Diffusion TextualInversion | CivitaiVAE: stabilityai/sd-vae-ft-mse-original at main (huggingface.co) or Cold VAE: https://civi...

I created 'SimpleNegative' because there are too many repetitive responses influenced by 'EasyNegative,' and it's becoming boring. Please place it in NegativePrompt in the same...

About the model:My goal with this mix was to create a mostly 2d anime style model that responds well to varied prompts, including a relatively wide range of existing characters...

ABOUTThis is an attempt to create a more "western" character look, as I've grown a little tired of seeing the same anime faces. Still very much a NSFW-prone female focused mode...

mooncryptowow's "wowifier" is an easy way to add some wow to your images.Version 3 of the "wowifier" was trained on an expanded and refined dataset at 1024,1024 (V2 is 768,768)...