少女歌劇塔羅牌風(fēng)格LoRA模型,雙版本


開頭致謝@秋葉aaaki 的懶人包合集以及LoRA訓(xùn)練腳本。如果你也有興趣訓(xùn)練自己的LoRA模型的話,建議觀看以下視頻配置基礎(chǔ)環(huán)境。訓(xùn)練要求顯卡顯存6GB以上。?


模型發(fā)布地址:
Civit
https://civitai.com/models/15332/revue-starlight-cg-tarot-style-lora
抱臉(huggingface)
https://huggingface.co/bdsqlsz/SD-LoRA-RevueStarlight-Anime-Style

模型介紹:
少女歌劇塔羅牌風(fēng)格LoRA模型
包括普通LoRA版以及卷積Locon版,對(duì)比圖


Locon是卷積技術(shù)在LORA模型上的新應(yīng)用,使用說(shuō)明看這里
https://github.com/KohakuBlueleaf/LoCon
光使用的話,直接用webui安裝下面這個(gè)插件,然后就像LORA一樣用就行了。
https://github.com/KohakuBlueleaf/a1111-sd-webui-locon

模型參數(shù):
訓(xùn)練圖共100張,其中25組每張兩組,由寬圖(768X512)、長(zhǎng)圖(512X768)各一組組成,寬圖為CG級(jí)人物圖,含背景。長(zhǎng)圖為獨(dú)立人物塔羅牌。重復(fù)次數(shù)5,批次16,訓(xùn)練共計(jì)8000步。
和青龍上個(gè)模型一樣,同時(shí)有兩種尺寸圖可選,長(zhǎng)圖512X768以及寬圖768X512


背景最終色彩根據(jù)明暗程度自適應(yīng)調(diào)整,可和其他人物L(fēng)ORA組合使用


基礎(chǔ)模型:?SD1.5
推薦權(quán)重:0.5-08
你可以使用以下關(guān)鍵字控制效果
→正位
→逆位,效果不好建議改成negative prompt
→顯示羅馬數(shù)字
→顯示卡牌名框,可改成negative prompt

效果圖:
以上為測(cè)試效果圖所加通用prompt,用于所有miku的測(cè)試圖,后續(xù)不再寫出。?

prompt:
arcana_style\(starlight\),(1girl),hatsune miku, roman numeral,??
Negative prompt: english text,?
參數(shù):Steps: 20, Sampler: DPM++ 2S a Karras, CFG scale: 11, Seed: 123934855, Face restoration: CodeFormer, Size: 768x512, Model hash: 1d1e459f9f, Model: anything-v4.5, Clip skip: 2, ENSD: 31337, Eta: 0.67, Script: X/Y/Z plot, X Type: AddNet Weight 1, X Values: 0.4-0.8(+0.2), Y Type: AddNet Model 1, Y Values: ", arcana_style(starlight)_locon_V2(d63c605155f1), arcana_style(starlight)_lora_V2(f0924ca529a2)"

prompt:arcana_style\(starlight\),makima \(chainsaw man\), 1girl, absurdres, bangs, indoors, black necktie, black pants, braid, braided ponytail, collared shirt, cowboy shot, highres, long hair, long sleeves, necktie, red hair, ringed eyes, shirt, sidelocks, solo, uniform, white shirt, yellow eyes, small breasts? <lora:arcana_style(starlight)_lora_V2:0.7>?
Negative prompt: (painting by bad-artist-anime:0.9), (painting by bad-artist:0.9), watermark, text, error, blurry, jpeg artifacts, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, artist name, (worst quality, low quality:1.4), bad anatomy
參數(shù):Steps: 20, Sampler: DPM++ 2M Karras, CFG scale: 7, Seed: 185906338, Face restoration: CodeFormer, Size: 512x768, Model hash: 5493a0ec49, Model: AOM3A1B, Denoising strength: 0.58, Clip skip: 2, ENSD: 31337, Hires upscale: 1.25, Hires steps: 10, Hires upscaler: R-ESRGAN 4x+ Anime6B


