Model

You can join my discord server here!You can also find me on Patreon and Ko-Fi!A weight of ~1.0 is recommended (You might want to adjust the weight depending on your model).Feel...

Hello thank you for taking an interest in my model ♥I do plan to update this : ) Version2made it more simple and more 2d.can do NSFWbaked in VAETools used:Easynegative - https:...

I found that images generated with my LoRA appear bit more amateur and less like the puppy "model_flux" style.In Better Faces, I aimed to include a diverse range of cultures an...

第二个不加tag，不进行裁切的实验输出,可以稳定生产类似游戏素材的图片（只是类似，达不到可用水准）推荐权重1The second untagged, uncut experimental output.- Stable production of ima...

My Links: discord, twitter/igSupport my efforts at @ patreonCheck IG for more content like this below.View my article on checkpoints - here. (HUGE ANIME UPDATE)Image Gen series...

This Lora represents a concept of lip biting. I've never been able to make it with any model I have before. This Lora gives a pretty decent results, but it's not very stable an...

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International Licensetwitter(@ihtke)05/14/23 updatesee About this versionQueen Marika...

If you want to know the story of these monsters, please read <about this version> I wrote the background and my review in it.如果想看一下背景故事，以及为什么我要把它们弄...

<游戏图标研究所-Dadabang>"AI-Game Icon Institute"We are a group of dreamers trying to generate icons through AI technology. This is a large-scale testing game icon model ...

Osorubeshi -> anime-like models trained on SDXLIf you like my work you can tip me on - patreon.com/Natakaro or buymeacoffee.com/natakaro :)Feel welcome to join my (still in ...

A friend wanted to have black as obsidian skin, this LORA acts as an helper to thatOr alternatively leave me a review and check out my other stuff ! 描述: ...

多concept人物训练教程https://www.bilibili.com/read/cv22050074 描述: I add 170 pictures(500 in all) in the train set which is different from the official setti...

微调了人物模型，V3的人物模型整体偏少女感，画风偏动漫感,V4减少了少女感，泛化可能有所降低，和V3相比画风偏向写实一些,每个版本都有各自的特点，可以根据自己的喜欢进行选择,负面词：(wo...

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International Licensetwitter(@ihtke)05/14/23 updatesee About this versionQueen Marika...

Realistic Zero-two from darling_in_the_franxx, Trained by ChilloutMix-Ni.All samples generate with Ulzzang-6500" embeddings, "vae-ft-mse-840000" VAE. 描述: ...

Check out my other models: https://www.shakker.ai/userpage/b8d88126d5db4bc9b8b9033f634d85fe/publishhttps://www.liblib.art/userpage/2468f25fc6e24ad09160ed9955af2016/publish·····...

即使在一片灰暗的世界中，也总有那么一束光为你而闪烁,生活不总是充满着悲伤与不幸的，希望每个人都能坚强的活下去,（如果搭配日影Lora，那么这束光可能会闪瞎你的眼）建议开启Hires fix，...

UPDATE 1.0!1.0 does not change the checkpoint style too much (I hope so)focused more on tape bindings than previous version (put rope on negatives if rope appears)strength 1.0 ...

Join me on Patreon for exclusive perks and early access to unique resources.To discuss custom LoRa's or models, feel free to connect on Discord.For Best Results Try using My Ne...

NOTE - This model was developed using UniPC sampler for 90% of my testing, occasionally DPM++ 2M or SDE. If you want realistic results, these are your best options, Euler work...