LORA

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...

该模型使用了超过100张高质量的原始图片进行训练,素材主要来自《电影少女》《I"s》、《D.N.A2》，接近其手绘复古画风,TV动画版图片素材没有混入其中，得到纯净的桂正和风格LORA,FLUX版本：h...

V2 comes with smaller size and updated datasetSo please tryp.s. It's not necessary but If you like my LoRAs please consider to support me to create more projects by donate in h...

This Lora helps with crossed legs.I want to create an ultimate crossed legs lora, that will help in every pose including legs up and lying on belly. For now it can work with fr...

(日本語説明は後半にあります)[ Update v2.0 : refined eye shape ]Reproduces smirking eyes. Slyly mouth LoRA is also available and will make a good combination.Suitable for anime-...

多concept人物训练教程https://www.bilibili.com/read/cv22050074 描述: trigger words:normal,luoxiaohei,yukibare,lostlands,holding_staff触发词:normal,luoxiaohei,y...

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...

The cute sdxl version is updated, mainly for the texture of the output model, the texture of hair, clothing and other materials; Greatly reduce the model memory; Among them, th...

FLUX 版本/Flux Version: [Flux.1 D] [Realistic] Jirai Kei fashion | 地雷系服装建议使用adetailer或者sd-face-editor来改善面部,例图使用了adetailer来修缮面部,It is recommended to us...

It's confusing that after I set training images larger to 640*704 and remained other settings like before, I thought I would get better results, but the outputs after hirex.fix...

V2 comes with smaller size and updated datasetSo please tryp.s. It's not necessary but If you like my LoRAs please consider to support me to create more projects by donate in h...

All eyes on her!===============V1.1:added several images from FLOWERtraining images resolution up to 1024 x 1024Trigger: JisooGolden weight: 0.85Denoising strength: 0.35Model: ...

Creating this lora is just to meet your own needs, and you can download and use it if you have the same needs.This is for helping change the style of clothing.The clothing styl...

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...

Glitching | Style/Concept LoRAWeight can go from 0.6 up to 1.1. I recommend 0.9. ControlNet will streamline full body shots much easier, or more complex poses. Works with almos...

My first LoRA, I used this for all a day, it's work well can produce «hair over eyes» and «hair over one eyes» i didn't tested on realist checkpoint. Use it as 1 strength. ...

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...

This is a V3 Qunqun, we have input some new image to makes it more better.煩請愛峮朋友不要再在我的圖按投訴，這對大家沒好處，大家都喜歡峮，想多做點美美圖出來，不要老投訴害大家都...

描述: 训练词语: 1girl, d.va (overwatch), solo, long hair, whisker markings, bodysuit, brown hair, facial mark, gloves, breasts, brown eyes,...

2 loras for various or hero outfits!Civilian LoRA:Trained on NAI with 45 pictures.Best result with weight between : 0.8-1.Prompt activator : violetparrBasic prompts : black hai...