LORA

这个模型只能用rev做底模，过拟合训练出来的,出图效率不高需要反复roll,过拟合的一个好处是不用分区控制就可以出自然的多角色图,技术尝试和纪念用，不是好使的通用lora,doesnt work well wi...

this model was finetuned based on sd 1.5 and used 100 public building renderingstrigger words：archiaerialview, architecture, time：sunset, morning, daystyle：line, curve ...

LCM-LoRA - Acceleration ModuleStep 1) Download LoRAStep 2) Add LoRA alongside any SDXL Model (or 1.5 model, if using the SD 1.5 version)Step 3) Set CFG to ~1.5 and Steps to 3St...

TQ - Realistic CryingLora Weight: 0.5-0.6Share your beautiful photos on Reviews or Comments! Thank you! ? 描述: Better Tears 训练词语: Crying...

这次的资源找了好久才找到的，中国的牡丹和芍药花，可能不是很全，但是总共有300张花图生成的，有二百张山水画，我应该会再找其他花来生成一下如果国内下载可以在88ai (czclub.club) 88a...

I found a new AI tool Shakker, a best image to image tool. You can try it via https://www.shakker.ai 这是一个关于3D渲染宣传产品的Lora模型在调用触发词后能够展现3D渲染宣传产品模...

Recommend Lora weight(推薦lora權重/おすすめの Lora ウェイト)0.6~0.9Recommended prompt(推薦提詞/おすすめのプロンプト):<lora:bayonetta_v1:0.8>,bayonetta,1girl,solo,large_br...

Help fuel my passion! Even $1 makes a difference. ☕ https://ko-fi.com/citronlegacy?Gerudo Princess Riju ⚜️Strong and noble, beautiful and wise, the princess of the sands is the...

Model: chilloutmix_NiPrunedFp32FixRes: 512 x 832DO NOT check "Restore faces"大家有喜欢的明星或者网红评论区告诉我 我有空炼一下You have a favorite celebrity or Internet celebrity...

一个表情Lora，做着玩的，效果一般般，谨慎使用它至少需要1以上的权重才能生效，所以会带来一些过拟合或者风格污染的问题,不需要提示词，但是如果没生效你也可以加上 (ᗜ ‸ ᗜ)，An expressio...

Form for requests.I also sometimes do polls on my Patreon for the next LORA (no payment required).I am using AbyssOrangeMix3 (AOM3)The LORA should work just fine with a weight ...

Volume 1 (20 models)The United Nations of sensuality. Each model was been crafted combining features from various LoRAs around Civitai. All characters are of legal age and do n...

KeiKomori - Artist StyleThis Lora is trained in the art style of KeiKomori.Some notable games where this artist served as the main illustrator include "ワルキューレロマンツェ ...

All the content I make is and will be completely free on CivitAI.But if you want to support me with a coin, then you can do it here.Trained on AbyssOrangeMix2 with clip skip 2....

Each version is a unique mix and will give you a different consistent face, they are not building upon the last.These are my Nobodies from SD1.5 retrained to be on SDXL.Please ...

Works best around 0.8All my models are free, but if you would like, you can support my work via Buy Me a Coffee or Ko-fi! 描述: 训练词语: ko...

Round 2: Forms are open again!Your characters may have insufficient training data! Click here.Weight: 1.0Trigger: cassandra alexandraDefault Outfit: hairband, armor, dress, nec...

Additional Information:No trigger word needed but cinematic, cinematic still image can helpTrained on landscape images❤️ SupportIf you use the site generator, you can support m...

看着像PVC，但是又没有那么像PVC）如果你喜欢这种风格，点个赞叭~(Looks like PVC, but not so much like PVC)If you like this style, give it a like! 描述: ...

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...