Model

?????? is a high quality anime merge model, with the focus of creating pleasant anime style art.This model was designed to be slightly different from 2D anime models by having ...

How to usePos: masterpiece, best qualityneg: (worst quality, low quality:1.4)Done.I prefer DPM ++ 2M Karras as main sampler, seem to work best in most cases. 12-20 steps.Hires ...

Taiwan Metal Steel Building LikenessKey word: metal steel buildingIt makes the photo look more like it was taken in Taiwan. 描述: 训练词语: ...

Base model:Anything4.5Recommend Weight:0.6~1※This is not a 3 in 1 lora, the characters are separated, check the version tag at the top of the pageTrigger word:takane manakaaneg...

UPDATE:v5: New training methodFull changelog belowThis lora has been trained with images of weird fashion trends and random futuristic artists renditions of clothing that will ...

?️Welcome to try out the open-source GPT4V-Image-Captioner, developed by my friend and me. It offers a one-click installation and comes integrated with multiple features includ...

Rikku FFX & FFX-2 | Character LoRAV3:Now trained properly, finally.Weight can go from 0.8 up to 1. I recommend 1. Works with almost every Style, every Character and Photore...

Gustave Doré was a French artist and illustrator known for his remarkable talent and prolific body of work, which encompassed a wide range of subjects and styles.His style can ...

UPDATE: Following the common practice, the most recent version is trained on NAI with clip skip 2The advantage of my models is clearly the ability to put multiple characters in...

PLEASE READ:AVOID using negative prompts like bad quality or bad hands - you'll just be wasting token space. Use ERA09NEGV1 instead. This will solve 90% of your problems.Good w...

My first LORA, Japanese idol Anju Kozuki (香月杏珠).The training data consists of 19 recent images of Anju, captionned through deepdanbooru, then manually adjusted (Some captio...

THIS LORA IS ONLY FOR TEST, PLEASE DO NOT PUBLISH NSFW IMAGES TO THE COMMUNITY!!!The weight of Lora = 0.8-0.9Please heighten your steps to 40 more or less to generate good imag...

Modern interior style Lora modelLiving room only 描述: First edition 训练词语: medieval architecture inspiration,contemporary architecture,ro...

SDXL:Trigger word: epoxy_skullSampling Method: DPM++ 2M SDE KarrasSD1.5:Trigger word: epoxy_skullSampling Method: Euler and Euler a☕ Buy me a coffee: https://ko-fi.com/ralfinge...

俺瞎练的，大家图一乐就好用的真人模型，权重0.9左右最好，喜欢的请来小红书多多支持，小红书唯一账号122766380，快手唯一账号:3368453928，不定时更新，后续系列lora会慢慢上传~各位大哥可...

How to usePos: masterpiece, best qualityneg: (worst quality, low quality:1.4)Done.I prefer DPM ++ 2M Karras as main sampler, seem to work best in most cases. 12-20 steps.Hires ...

沒事就多畫小鴨鴨Prompt:1girl,bronya,herrscher_of_reason,grey eyes, grey hair,drills,hair_ornament, earrings,gloves,elbow gloves,layered dress, jewelry,small breasts,white thigh...

good work with animal LoRA&furry kemono HypernetworksCaracal cat LoRA :https://civitai.com/models/92559/caracal-cat-loraCanada Lynx LoRA:https://civitai.com/models/91874/ca...

Anisphia Wynn Palettia from Tensei Oujo to Tensai Reijou no Mahou KakumeiFor best results use:anisphia_wynn_palettia, blonde short hair, pink skirtSee also: https://civitai.com...

LoRA is generated entirely from anime images.-----------------------------------Check samples for prompts :)Chara collection here: https://civitai.com/collections/76071--------...