赤倉 Style LoRA V4
简体中文 | English 使用前阅读 | Read before use
--

--
主要针对技法进行训练。
Mainly for the training of painting techniques.
--
仿赤倉的作画风格的LoRA模型。
权重建议值:0.8 (or 0.5~1.2)
The LoRA model mimics Akakura's painting style.
Recommended weight value: 0.8 (or 0.5~1.2)
--
任何问题,欢迎反馈,问题不提出就不会得到解决。如果你创作出了好作品,欢迎分享它。如果它无法满足你的需求,我是说,我的朋友,请不要给出一星好评。
Any questions are welcome for feedback, as problems will not be solved without being raised. If you have created a great work, please feel free to share it. If it cannot meet your needs, my friend, please do not give a one-star rating.
Description
完全重置。
FAQ
Comments (7)
您好,按照您的触发词一模一样却出不来相应的图,请问是有哪里缺失了吗?出来的风格和您发出来的完全不同,同样的基础模型,跑出来类似于Q版,看起来差别极大,请问您是否还同时使用了其他LORA?我更喜欢您的第一个版本,希望可以得到解答,谢谢!
如果参数条件完全一致,比如种子、图幅等等,那就不会有问题,我也没有使用其他lora,所有用到的东西都写在上边了,我没有对图片的元数据做任何改动。不过,第一个版本和第二个版本我都觉得还有点缺陷,今晚看看有没有空更新V3版本,感谢你的反馈。
我特意翻到了V2封面图的元数据,你也可以对照一下,就在刚才,我重试了一次出图是基本一致的。
1girl, <lora:style_Akakura:1>
Negative prompt: EasyNegative
Steps: 20, Sampler: DPM++ 2M Karras, CFG scale: 12.5, Seed: 3906224112, Size: 672x1056, Model hash: 1065c5d2e0, Model: CreationMixV1, Denoising strength: 0.5, Clip skip: 2, Hires upscale: 1.6, Hires steps: 16, Hires upscaler: Lanczos
已更新。
@Chanter 非常感谢,很喜欢您的作品,尤其是V1,V1版本的后面几张图,非常有插画风的感觉,超级喜欢,可惜我怎么也跑不出来,也不知道问题出在了哪里QAQ
@Chanter 1girl, bandaid, bangs, blue_eyes, bow, brown_bow, candy, chocolate, closed_mouth, diagonal_stripes, dress, drill_hair, eyepatch, food, gift, gift_box, gloves, hair_ornament, hair_over_one_eye, hairclip, hat, hat_bow, heart, heart-shaped_box, holding, holding_gift, long_hair, long_sleeves, looking_at_viewer, pink_background, pinstripe_pattern, red_background, ribbon, signature, simple_background, smile, solo, striped, striped_background, striped_bow, striped_bowtie, striped_dress, striped_headwear, striped_legwear, striped_ribbon, stuffed_animal, stuffed_toy, teddy_bear, top_hat, twin_drills, twintails, upper_body, valentine, vertical-striped_legwear, vertical_stripes <lora:style_赤仓:1>
Negative prompt: lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name,
\(low quality:1.3\), \(worst quality:1.3\),\(monochrome:0.8\),\(deformed:1.3\),\(malformed hands:1.4\),\(poorly drawn hands:1.4\),\(mutated fingers:1.4\),\(bad anatomy:1.3\),\(extra limbs:1.35\),\(poorly drawn face:1.4\),\(signature:1.2\),\(artist name:1.2\),\(watermark:1.2\),long neck,blurry,\(watermark:1.3\) badhandv4 EasyNegative
Steps: 28, Sampler: DPM++ 2M Karras, CFG scale: 7, Seed: 2347785033, Size: 512x512, Model hash: 1065c5d2e0, Model: creationmixV12DStyle_v1, Clip skip: 2, ENSD: 31337
这是我的数据,您看是哪里有问题呢?是第一版本中红色背景的那张图,我试图发图片但不知为何不能选择公开,可以的话能不能麻烦您帮我看一下呢?实在很喜欢这个画风,跑不出来很难过呀QAQ
@suibianzhuce2022704
1girl, bandaid, bangs, blue_eyes, bow, brown_bow, candy, chocolate, closed_mouth, diagonal_stripes, dress, drill_hair, eyepatch, food, gift, gift_box, gloves, hair_ornament, hair_over_one_eye, hairclip, hat, hat_bow, heart, heart-shaped_box, holding, holding_gift, long_hair, long_sleeves, looking_at_viewer, pink_background, pinstripe_pattern, red_background, ribbon, signature, simple_background, smile, solo, striped, striped_background, striped_bow, striped_bowtie, striped_dress, striped_headwear, striped_legwear, striped_ribbon, stuffed_animal, stuffed_toy, teddy_bear, top_hat, twin_drills, twintails, upper_body, valentine, vertical-striped_legwear, vertical_stripes <lora:style_赤倉:1>
Negative prompt: lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name, \(low quality:1.3\), \(worst quality:1.3\),\(monochrome:0.8\),\(deformed:1.3\),\(malformed hands:1.4\),\(poorly drawn hands:1.4\),\(mutated fingers:1.4\),\(bad anatomy:1.3\),\(extra limbs:1.35\),\(poorly drawn face:1.4\),\(signature:1.2\),\(artist name:1.2\),\(watermark:1.2\),long neck,blurry,\(watermark:1.3\) badhandv4 EasyNegative
Steps: 28, Sampler: DPM++ 2M Karras, CFG scale: 10, Seed: 2347785033, Size: 960x960, Model hash: a611cf9c19, Model: cetusMix_Version35, Denoising strength: 0.48, Clip skip: 2, Hires upscale: 1.5, Hires steps: 12, Hires upscaler: Latent
注意CFG(提示词引导系数),Size(初始图幅),Model(模型,其实CreationMix也行,那张图是用cetus跑的),Denoising strength(重绘幅度),Hires upscale(放大倍数),Hires steps(高清修复步数)。
此外,lora:后的名称要对应文件名。希望能帮到你。
@Chanter 非常感谢!按照您的指导,已经找到原因,将底模换成cetus后就可以出到差不多的图,虽然还有些区别,但已经不像之前一样差别巨大,很开心!再次感谢!
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.





