前言

今天要测试的是来自木人又大佬的盲盒lora，这是一款可以让一切都变成盲盒画风的神奇lora。不论是写实风格还是卡通风格，甚至于真人，都可以通过他完成盲盒化，实现真正的盲盒自由。

这位lora作者在b站也有号，推荐大家也可以去关注一下他。

之前也测试过盲盒风格，不过当时只是简单的分享了一些做的好看的图，并没有做过比较详细的对比测试，这次分享主要是测试各种环境下的盲盒风格表现效果，便于大家自行使用时有个参照。

下载链接

CKPT大模型：

链接：https://pan.baidu.com/s/1daM5c-TWHR-CaQoDcOlW5w?pwd=70kq

提取码：70kq

盲盒lora：

链接：https://pan.baidu.com/s/1DpaOk0WXuVZbl_W6JJx_Jg?pwd=e5hy

提取码：e5hy

交流群

qq群：697080799

微信群:

先说结论

盲盒lora作为一款独特画风的lora，展现了惊人的兼容性素质。它几乎可以与所有人物和服装类的lora完美兼容。虽然在CKPT大模型方面，这款极度类似照片的大模型兼容性较差，但对于其他的3D或2D画风的大模型，甚至是一般的写实风格模型，均可以与之完美兼容，从而诞生出有趣的风格。在实际使用过程中，我也发现它的可能性远远不止于盲盒。在一些大模型环境下，它可以变成2D大头娃娃的卡通风格，在Chilloutmix环境下又能诞生这种类似BJD娃娃画风。虽然已经测试过很长时间，但我仍然感觉它依然还存在未被发现的可能性。

在图生图情况下，盲盒lora也有着不俗的风格迁移能力。但并不能把图里的人物特征保存然后生成一个动作完全不一样的小人偶，更像是为真人照片赋予手办一样的塑料质感。

和群友沟通的过程中，我意外地发现一个用自己孩子照片训练成lora模型并且配合盲盒lora使用的案例，效果非常不错。这方面展现出了不俗的商业可能性，大家也可以在评论区分享一下自己对盲盒lora商业化方面的想法。

这里是我尝试过后比较适合搭配盲盒lora的通用提示词，但这些提示词仅适用于稳定的基础风格，不能直接用于生成。生成作品时还需要搭配其他内容相关的提示词。

使用建议

日常使用时，

盲盒lora权重建议:0.4~1

注意，盲盒lora的权重与生成模型的身体比例有直接关系，在下面的测视里会直观展现。

搭配盲盒的人物lora建议按照其官方指导权重进行配置，最大权重尽可能控制在1.2以内。

并且，在使用写实风格大模型时（例如chilloutmix），盲盒lora需要搭配一些人物lora使用，面部效果会更好。一定程度也能解决恐怖谷问题。

实际使用案例

CKPT模型： revAnimated_v11

lora：blindbox

lora：amberGenshinImpact_flexible

Steps（采样迭代步数）: 25, Sampler（采样方法）:DPM++ SDE Karras, CFG scale（提示词相关性）: 7, Seed（随机种子）: 3697197302, Size（分辨率）: 728x728

正：

(masterpiece, best quality, absurdres, foreshortening), photo of a highly detailed,(full body:1.2), smile,cute face , goggles on head, amber \(genshin impact\), brown eyes, brown hair, long hair, red hair ribbon, brown short shorts, leather gloves, pouch, thighhighs, white boots, medium breasts, cleavage cutout, shrug \(clothing\) full body,<lora:amberGenshinImpact_flexibleV1:1> ,(studio background),(clean background),(blurry background), 1girl, chibi, (beautiful detailed face), (beautiful detailed eyes),standing in chinese garden, rendered in blender ,

负：

(low quality:1.3), (worst quality:1.3),pointy ears, animal ears, watermark, logo, text, badhandv4

CKPT模型： revAnimated_v11

lora：blindbox

lora：duoliGenshinImpact_visionGenshinImpact

Steps（采样迭代步数）: 25, Sampler（采样方法）:DPM++ SDE Karras, CFG scale（提示词相关性）: 7, Seed（随机种子）: 3697197308, Size（分辨率）: 728x728,

正：

(masterpiece, best quality, absurdres, foreshortening), photo of a highly detailed,(full body:1.2), smile,cute face , hat, barefoot, pants, feet, shoes, holding, sunglasses, toes, shirt, sitting, bangs, ring, jewelry, pince-nez, bag, sidelocks, midriff, navel, sleeveless, blush, beret, purple headwear, pink hair, tinted eyewear, crop top, looking at viewer, long sleeves, harem pants, detached sleeves, puffy long sleeves, shoes removed, sleeveless shirt, red-tinted eyewear, black shirt, purple pants, bare shoulders, vision (genshin impact), hair between eyes, full body, hair ornament, yellow eyes, gold trim, multiple rings , <lora:duoliGenshinImpact_visionGenshinImpact:1> ,(studio background),(clean background),(blurry background), 1girl, chibi, (beautiful detailed face), (beautiful detailed eyes),standing in chinese garden, rendered in blender

负：

(low quality:1.3), (worst quality:1.3),pointy ears, animal ears, watermark, logo, text, badhandv4

CKPT模型： revAnimated_v11

lora：blindbox

lora：fischlGenshinImpact_fischlGenshinImpact

Steps（采样迭代步数）: 25, Sampler（采样方法）:DPM++ SDE Karras, CFG scale（提示词相关性）: 7, Seed（随机种子）: 3170149272, Size（分辨率）: 728x728,

正：

(masterpiece, best quality, absurdres, foreshortening), photo of a highly detailed,(full body:1.2), smile,cute face , eyepatch, bow, gloves, breasts, bowtie, bangs, ribbon, fishnets, bodystocking, green eyes, long hair, blonde hair, hair ribbon, purple bow, bare shoulders, black gloves, purple bowtie, detached sleeves, hair over one eye, elbow gloves,<lora:fischlGenshinImpact_fischlGenshinImpact:1> ,(studio background),(clean background),(blurry background), 1girl, chibi, (beautiful detailed face), (beautiful detailed eyes),standing in chinese garden, rendered in blender

负：

(low quality:1.3), (worst quality:1.3),pointy ears, animal ears, watermark, logo, text, badhandv4,(naked/nude, )

CKPT模型： revAnimated_v11

lora：blindbox

lora：ganyuGenshinImpact_v20

Steps（采样迭代步数）: 25, Sampler（采样方法）:DPM++ SDE Karras, CFG scale（提示词相关性）: 7, Seed（随机种子）: 1232920822, Size（分辨率）: 728x728

正：

(masterpiece, best quality, absurdres, foreshortening), photo of a highly detailed,(full body:1.2), smile,cute face , <lora:ganyuGenshinImpact_v20:1.1>,hair ornamen, gloves, (ganyu \(genshin impact\), ), ganyu, twin horn, bare shoulder, ,(studio background),(clean background),(blurry background), 1girl, chibi, (beautiful detailed face), (beautiful detailed eyes),standing in chinese garden, rendered in blender

负：

(low quality:1.3), (worst quality:1.3),pointy ears, animal ears, watermark, logo, text, badhandv4,(naked/nude, )

CKPT模型： revAnimated_v11

lora：blindbox

lora：huTaoGenshinImpact_v12

Steps（采样迭代步数）: 25, Sampler（采样方法）:DPM++ SDE Karras, CFG scale（提示词相关性）: 7, Seed（随机种子）: 1196454241, Size（分辨率）: 728x728,

正：

(masterpiece, best quality, absurdres, foreshortening), photo of a highly detailed,(full body:1.2), smile,cute face , hu tao (genshin impact), boo tao,hat, red eyes, twintails, brown hair,symbol-shaped pupils, long hair,bangs, black shorts , chinese clothes, <lora:huTaoGenshinImpact_v12:0.7> ,(studio background),(clean background),(blurry background), 1girl, chibi, (beautiful detailed face), (beautiful detailed eyes),standing in chinese garden, rendered in blender

负：

(low quality:1.3), (worst quality:1.3),pointy ears, animal ears, watermark, logo, text, badhandv4,(naked/nude, )

CKPT模型： revAnimated_v11

lora：blindbox

lora：kleeGenshinImpact_kleeGenshinImpact

Steps（采样迭代步数）: 25, Sampler（采样方法）:DPM++ SDE Karras, CFG scale（提示词相关性）: 7, Seed（随机种子）: 3871065983, Size（分辨率）: 728x728

正：

(masterpiece, best quality, absurdres, foreshortening), photo of a highly detailed,(full body:1.2), smile,cute face , <lora:kleeGenshinImpact_kleeGenshinImpact:0.8>,blond hair, red dress,stuffed animal, backpack pendant, hat , ,(studio background),(clean background),(blurry background), 1girl, chibi, (beautiful detailed face), (beautiful detailed eyes),standing in chinese garden, rendered in blender

负：

(low quality:1.3), (worst quality:1.3),pointy ears, animal ears, watermark, logo, text, badhandv4,(naked/nude, )

CKPT模型： revAnimated_v11

lora：blindbox

lora：keqingGenshinImpact3in1_v10

Steps（采样迭代步数）: 25, Sampler（采样方法）:DPM++ SDE Karras, CFG scale（提示词相关性）: 7, Seed（随机种子）: 3764070961, Size（分辨率）: 728x728

正：

(masterpiece, best quality, absurdres, foreshortening), photo of a highly detailed,(full body:1.2), smile,cute face , <lora:keqingGenshinImpact3in1_v10:1>,keqing (piercing thunderbolt) (genshin impact), keqing (genshin impact), pantyhose, hair bun, purple hair, gloves, twintails, long hair, purple eyes, diamond-shaped pupils, bare shoulders, hair ornament, black pantyhose, cone hair bun, detached sleeves,dress, jewelry, medium breasts, earrings, bangs, frills, purple dress, black gloves, braid, skirt, ,(studio background),(clean background),(blurry background), 1girl, chibi, (beautiful detailed face), (beautiful detailed eyes),standing in chinese garden, rendered in blender

负：

(low quality:1.3), (worst quality:1.3),pointy ears, animal ears, watermark, logo, text, badhandv4,(naked/nude, )

CKPT模型： revAnimated_v11

lora：blindbox

lora：genshinImpactNoelle_nV1

Steps（采样迭代步数）: 25, Sampler（采样方法）:DPM++ SDE Karras, CFG scale（提示词相关性）: 7, Seed（随机种子）: 4122304707, Size（分辨率）: 728x728,

正：

(masterpiece, best quality, absurdres, foreshortening), photo of a highly detailed,(full body:1.2), smile,cute face , <lora:genshinImpactNoelle_nV1:0.8>,noelle_\(genshin_impact\),(green_eyes:1.2//),silver hair, short_hair, medium_breasts, ,(studio background),(clean background),(blurry background), 1girl, chibi, (beautiful detailed face), (beautiful detailed eyes),standing in chinese garden, rendered in blender

负：

(low quality:1.3), (worst quality:1.3),pointy ears, animal ears, watermark, logo, text, badhandv4,(naked/nude, )

CKPT模型： revAnimated_v11

lora：blindbox

lora：kamisatoAyakaGenshin_kamisatoAyaka

Steps（采样迭代步数）: 25, Sampler（采样方法）:DPM++ SDE Karras, CFG scale（提示词相关性）: 7, Seed（随机种子）: 2669810022, Size（分辨率）: 728x728

正：

(masterpiece, best quality, absurdres, foreshortening), photo of a highly detailed,(full body:1.2), smile,cute face , <lora:kamisatoAyakaGenshin_kamisatoAyaka:1>,arm guards, armored dress, breastplate, japanese armor, hand fan, fingerless gloves ,(studio background),(clean background),(blurry background), 1girl, chibi, (beautiful detailed face), (beautiful detailed eyes),standing in chinese garden, rendered in blender

负：

(low quality:1.3), (worst quality:1.3),pointy ears, animal ears, watermark, logo, text, badhandv4,(naked/nude, )

CKPT模型： revAnimated_v11

lora：blindbox

lora：lumineGenshinImpact_lumineGenshinImpact

Steps（采样迭代步数）: 25, Sampler（采样方法）:DPM++ SDE Karras, CFG scale（提示词相关性）: 7, Seed（随机种子）: 954436155, Size（分辨率）: 728x728

正：

(masterpiece, best quality, absurdres, foreshortening), photo of a highly detailed,(full body:1.2), smile,cute face , <lora:lumineGenshinImpact_lumineGenshinImpact:1>,lumine_/(genshin_impact/), short hair, short hair with long locks, blonde hair, bangs, sidelocks, hair between eyes, yellow eyes, orange eyes, medium breasts, hair flower, white flower, lily (flower), hair ornament, gold trim, blush ,(studio background),(clean background),(blurry background), 1girl, chibi, (beautiful detailed face), (beautiful detailed eyes),standing in chinese garden, rendered in blender

负：

(low quality:1.3), (worst quality:1.3),pointy ears, animal ears, watermark, logo, text, badhandv4,(naked/nude, )

CKPT模型： revAnimated_v11

lora：blindbox

lora：lumineGenshinImpact_lumineGenshinImpact

Steps（采样迭代步数）: 25, Sampler（采样方法）:DPM++ SDE Karras, CFG scale（提示词相关性）: 7, Seed（随机种子）: 1540513666, Size（分辨率）: 728x728

正：

(masterpiece, best quality, absurdres, foreshortening), photo of a highly detailed,(full body:1.2), smile,cute face , <lora:eulaGenshinImpact_eulAV4000082:0.8>,(black thigh boots), close-up, (short_blue_hair), (eula),blue eyes, Asymmetrical hairstyle ,(studio background),(clean background),(blurry background), 1girl, chibi, (beautiful detailed face), (beautiful detailed eyes),standing in chinese garden, rendered in blender

负：

(low quality:1.3), (worst quality:1.3),pointy ears, animal ears, watermark, logo, text, badhandv4

CKPT模型： chilloutmix

lora：blindbox

lora：hanfu_v29

Steps（采样迭代步数）: 25, Sampler（采样方法）:DPM++ SDE Karras, CFG scale（提示词相关性）: 7, Seed（随机种子）: 3602092719, Size（分辨率）: 728x728

正：

(masterpiece, best quality, absurdres, foreshortening), photo of a highly detailed,(full body:1.2), smile,cute face , hanfu

负：

(studio background),(clean background),(blurry background), 1girl, chibi, (beautiful detailed face), (beautiful detailed eyes),standing in chinese garden, rendered in blender Negative prompt: (low quality:1.3), (worst quality:1.3),pointy ears, animal ears, watermark, logo, text, badhandv4,(naked/nude, )

CKPT模型： kawaiDiffusionSD15

lora：blindbox

lora：hanfu_v29

Steps（采样迭代步数）: 25, Sampler（采样方法）:DPM++ SDE Karras, CFG scale（提示词相关性）: 7, Seed（随机种子）: 1981080875, Size（分辨率）: 728x728

正：

(masterpiece, best quality, absurdres, foreshortening), photo of a highly detailed,(full body:1.2), smile,cute face , hanfu ,(studio background),(clean background),(blurry background), 1girl, chibi, (beautiful detailed face), (beautiful detailed eyes),standing in chinese garden, rendered in blender

负：

(low quality:1.3), (worst quality:1.3),pointy ears, animal ears, watermark, logo, text, badhandv4,(naked/nude, )

参与测试的模型

CKPT大模型

abyssorangemix2SFW

kawaiDiffusionSD15_v32

revAnimated_v11

realisticVisionV20

chilloutmix

Lora

blindbox

盲盒关键词权重对比测试

测试”CHIBI“的权重和盲盒lora的权重，对生成的人物身体比例的影响。

基础信息

Steps（采样迭代步数）: 25, Sampler（采样方法）:DPM++ SDE Karras, CFG scale（提示词相关性）: 7, Seed（随机种子）: 2552029887, Size（分辨率）: 720x720,

正：

(best quality,masterpiece, absurdres, foreshortening), photo of a highly detailed, (chibi:1.7),(full body:1.2), (studio background), (clean background), (beautiful detailed face), (beautiful detailed eyes), rendered in blender, 1girl,solo, strong rim light,Soft Lighting,Moody Lighting, smile,cute, bangs,frills, petals, center_frills, bonnet, dinopika, green hoodie, sharp teeth, hood, teeth, hoodie, blonde hair, tail, open mouth, smile, multicolored hair, looking at viewer, ((eyes closed)), blush stickers, bright pupils, smile , green nails, hair between eyes, twintails, long sleeves, hood up, bangs, indoors,

负：

(low quality:1.3), (worst quality:1.3),pointy ears, animal ears, watermark, logo, text, badhandv4

总结

可以很明显的看到，盲盒lora权重越大，人物比例越接近二头身Q版，而提示词”CHIBI“在权重大于1.1时候，身体比例也发生了改变。所以，在不适合调整盲盒lora权重时，调整这个提示词的权重也是个不错的选择。

大模型对比测试

基础信息

Steps（采样迭代步数）: 25, Sampler（采样方法）:DPM++ SDE Karras, CFG scale（提示词相关性）: 7, Seed（随机种子）: 1074158309, Size（分辨率）: 512x512

正：

(best quality,masterpiece, absurdres, foreshortening), photo of a highly detailed, (chibi:1.7),(full body:1.2), (studio background), (clean background), (beautiful detailed face), (beautiful detailed eyes), rendered in blender, 1girl,solo, strong rim light,Soft Lighting,Moody Lighting, smile,cute, bangs,frills, petals, center_frills, bonnet, dinopika, green hoodie, sharp teeth, hood, teeth, hoodie, blonde hair, tail, open mouth, smile, multicolored hair, looking at viewer, ((eyes closed)), blush stickers, bright pupils, smile , green nails, hair between eyes, twintails, long sleeves, hood up, bangs, indoors,负：

(low quality:1.3), (worst quality:1.3),pointy ears, animal ears, watermark, logo, text, badhandv4

总结

除了D模型之外，其他模型的生成表现都还不错。除了官方推荐的C模型之外，A模型在盲盒风格的表现也非常不错。B模型则变成了非常可爱的二头神平面卡通风格，E模型则呈现了一种毛绒玩具般的质感，不过在这次测试之外，用E模型搭配人物Lora，也是一种很独特的风格。

兼容性测试

人物lora对比

Steps（采样迭代步数）: 25, Sampler（采样方法）:DPM++ SDE Karras, CFG scale（提示词相关性）: 7, Seed（随机种子）: 1249858550, Size（分辨率）: 720x720

正：

(best quality,masterpiece, absurdres, foreshortening), photo of a highly detailed, chibi,(full body:1.2), (studio background), (clean background), (beautiful detailed face), (beautiful detailed eyes), rendered in blender, 1girl,solo, strong rim light,Soft Lighting,Moody Lighting, smile,cute, (black thigh boots), close-up, (short_blue_hair), (eula),blue eyes, Asymmetrical hairstyle, <lora:eulaGenshinImpact_eulAV4000082:0.6>

负：

(low quality:1.3), (worst quality:1.3),pointy ears, animal ears, watermark, logo, text, badhandv4

服装lora测试

Steps（采样迭代步数）: 25, Sampler（采样方法）:DPM++ SDE Karras, CFG scale（提示词相关性）: 7, Seed（随机种子）: 1965895119, Size（分辨率）: 720x720

正：

(best quality,masterpiece, absurdres, foreshortening), photo of a highly detailed, chibi,(full body:1.2), (studio background), (clean background), (beautiful detailed face), (beautiful detailed eyes), rendered in blender, 1girl,solo, strong rim light,Soft Lighting,Moody Lighting, smile,cute, hanfu,song, wind, autumn, maple leaf, falling leaves, blurry background, day, ginkgo leaf, depth of field,负：

(low quality:1.3), (worst quality:1.3),pointy ears, animal ears, watermark, logo, text, badhandv4

总结

盲盒lora的兼容性非常好，在搭配原神人物lora时，只要人物lora权重没超过1，都能保持画风的稳定，从个人使用体验出发，如果感觉人物还原度不够，权重设置完全可以超过1，只要同时抬高盲盒lora权重，依然可以保持风格稳定。不过依然不建议权重超过1.3，可能会与其他的提示词互相干扰。

汉服lora与盲盒lora的兼容性则一目了然，好的我甚至怀疑是测试的时候没有设定好参数。在0.2~1.0的区间里表现都非常不错。不过考虑到与其他提示词的互相干扰，依然不建议权重超过1.3。不过考虑到测试中的表现，在与汉服lora配合时通过权重来控制身体比例，可能难度会较大。

图生图风格迁移测试

特写

Steps（采样迭代步数）: 20, Sampler（采样方法）:DPM++ SDE Karras, CFG scale（提示词相关性）: 7, Seed（随机种子）: 971984781, Size（分辨率）: 823x512,

正：

(best quality,masterpiece, absurdres, foreshortening), photo of a highly detailed, chibi, (clean background), (beautiful detailed face), (beautiful detailed eyes), rendered in blender, 1girl,solo, brown hair, long hair, collarbone, bare shoulders, smile,hands on own chin, strong rim light,Soft Lighting,Moody Lighting,

负：

(low quality:1.3), (worst quality:1.3),pointy ears, animal ears, watermark, logo, text, badhandv4

重绘幅度超过0.8的时候动作就走行了，保持动作迁移画风的话需要控制在0.7以内，以0.45~0.6最佳。若是无法使用提示词清晰描述的话，可能需要更低的重回幅度与更高的lora权重。

半身

Steps（采样迭代步数）: 20, Sampler（采样方法）:DPM++ SDE Karras, CFG scale（提示词相关性）: 7, Seed（随机种子）: 1299204800, Size（分辨率）: 823x512

正：

(best quality,masterpiece, absurdres, foreshortening), photo of a highly detailed, chibi, (clean background), (beautiful detailed face), (beautiful detailed eyes), rendered in blender, 1girl,solo, full body,brown hair, long hair, collarbone, white undershirt, cutoffs, arm support, on side, strong rim light,Soft Lighting,Moody Lighting, garden,flower,

负：

(low quality:1.3), (worst quality:1.3),pointy ears, animal ears, watermark, logo, text, badhandv4

全身

Steps（采样迭代步数）: 20, Sampler（采样方法）:DPM++ SDE Karras, CFG scale（提示词相关性）: 7, Seed（随机种子）: 565988298, Size（分辨率）: 715x780

正：

(best quality,masterpiece, absurdres, foreshortening), photo of a highly detailed, chibi, (clean background), (beautiful detailed face), (beautiful detailed eyes), rendered in blender, 1girl,solo, full body,brown hair, long hair,Colorful dress,standing, indoors, on floor, wooden floor, near wall,

负：Negative prompt: (low quality:1.3), (worst quality:1.3),pointy ears, animal ears, watermark, logo, text, badhandv4

总结

简单来说盲盒lora的图生图模式就是给照片内的元素赋予一种粘土玩具的质感。五官比例则明显开始倾向Q版，与前面测试的chilloutmix的人偶娃娃不同，图生图模式并没有产生太强的恐怖谷效应。

从特写的对比可以看出，基础构图在任何情况下都没有发生大幅度的改变，风格则随着重绘幅度的增加与权重的增加越来越明显。

半身图的测试中带有了部分场景元素，在高重绘幅度的情况下也会对周身场景有一定的影响。另外，过高的重绘幅度也会导致动作还原程度降低。

在全身图测试的表现，相较于之前测试的其他lora的全身图，已经好了非常多。

重绘幅度低的情况下面部比较模糊，稍大的权重幅度则会创造一个相当稳定的面部，不过肢体动作依然会出现一些问题，搭配openpose之类的工具可能能进一步解决这个问题。至于服装问题，在高重回幅度的情况下会按照AI自己的意思换衣服。不过这部分的问题也可能与提示词不够有关，作为一个不太关心服装的直男，我并不知道这位姐姐身上的衣服应该如何描述。。