注意：本模型未经许可严禁转移至其他平台（liblib已进驻：https://www.liblib.art/userpage/a68d8219ddf245ecbd3e1da465409eaa/publish ），若发现会立刻联系平台相关方进行下架处理。

Notice: Unauthorized transfer of this model to other platforms is strictly prohibited (liblib has been authorized: https://www.liblib.art/userpage/a68d8219ddf245ecbd3e1da465409eaa/publish). If discovered, the relevant platform will be contacted immediately for removal.

免责声明：本模型的使用者需严格遵守所在地的法律法规，合法合规地使用ai技术。若使用者因违反所在地法律法规等原因所造成的各类不良后果本人概不负责。

Disclaimer: Users of this model must strictly comply with the laws and regulations of their respective locations and use AI technology in a lawful and compliant manner. The creator shall not be held responsible for any adverse consequences arising from users' violation of local laws and regulations or other reasons.

For Anima preview3 version 关于Anima preview3 版本

1：本模型是基于 Anima preview3 训练的 loha 模型（使用方法与普通lora相同）。 Anima模型的使用方法请参考下方项目链接：

https://huggingface.co/circlestone-labs/Anima

1：This model is a LoHA model trained on Anima preview3 (usage is the same as standard LoRA).

For instructions on using the Anima model, please refer to the project link below:

https://huggingface.co/circlestone-labs/Anima

2：Rules of trigger word: 模型触发词使用规则

触发词：@kuse_(0201)

trigger word：@kuse_(0201)

注意1：画师词前一定要加上 @ 前缀，否则画风的触发效果会弱很多

note1：Prefix artist with @. E.g. "@big chungus". You must put @ in front of the artist. The effect will be very weak if you don't.

注意2：由于当前高清放大会破坏眼部细节，因此当前版本的例图均为一次文生图直接生成，在Anima的高分辨率图像生成能力进步之后我会尝试进行高清放大。

note2：Since high-resolution upscaling currently damages the eye details, all example images in this version are directly generated from a single text-to-image process. I will attempt high-resolution upscaling once Anima's high-resolution image generation capability improves.

example：

[quality/meta/year/safety tags] [1girl/1boy/1other etc] [character] [series] [artist] [general tags]

（推荐 tag 顺序：[质量/元数据/年份/安全] [人数] [角色] [作品] [画师] [通用标签]）

score_9, score_8, masterpiece, best quality, absurdres, highres, rich details, suggestive, uncensored, 1girl, solo, vivian_banshee, @kuse_(0201), long hair,......

 3:generation data(example)(Comfy UI): 生成参数（Comfyui）

lora weight: 1

steps: 30

CFG: 4.0

sampler: er_sde

scheduler: simple

For NoobXL epsilon vpred1.0\epsv1.1 lokr v1.3关于NoobXL epsilon vpred1.0\epsv1.1 lokr v1.3版本

关于这个版本 About this vision

此版本（v1.3）重新调整了训练集，从而获得了对各时期画风更高的拟合度。

This version (v1.3) has readjusted the training set, resulting in a higher fit to the art styles of each period.

For NoobXL epsilon v0.75\v0.5 lokr v1.2 关于NoobXL epsilon v0.75\v0.5 lokr v1.2版本

关于这个版本 About this vision

此版本（v1.2）对各时期画风进行了特化以获得更好的生成质量。

This version (v1.2) has specialized the art styles of various periods to achieve better generation quality.

1:This model is a sdxl-lora based on NoobXL early access version.Using sdxl_vae as a vae.

1：本模型是基于NoobXL early access version底膜训练的sdxl Lokr模型，使用sdxl_vae作为vae。

ATTENTION ！As a kind of Lycoris model, most of times its usages are as same as the sdxl lora. However, lokr CANNOT be used on some batch nodes on Comfy UI (e: Lora stack). You can use the XYZ PLOT on Web UI to achieve similar functionality ！！！

注意！作为Lycoris模型系列下的Lokr模型，虽然在大部分情况下使用方法与普通lora无异，但部分ComfyUI 测试功能如（Lora堆节点（lora stack）等）是用不了的！建议使用Web UI的xyz图表功能来完成同类操作！！！

加注：本模型展示图仅通过文生图（832x1216）与高清放大（1664x2432）生成。

Tips: Pictures showed on the screen were only generated by t2i (832x1216) and hire-fix (1664x2432).

3:Rules of trigger word: 模型触发词使用规则

（1）：画风触发词格式与分类：kuse (0201) xxx

<1>早期（early）（2017.7-2021.6）：kuse (0201) 1

<2>中期（mid）（2021.6-2022.7？）：kuse (0201) 2

<3>晚期（latest）（2022.7？-2024.10）：kuse (0201) 3

example： <1girl/1boy/1other/...>,

<character>, <series>, kuse (0201) xxx,

<general tags>,

masterpiece,best quality,absurdres,highres,sensitive,newest,

4:generation data(example)(Comfy UI): 生成参数（Comfyui）

lora weight: 1

Using Efficiency nodes (restore Web UI usage)（使用效率节点还原Web UI参数，Web UI可无视）

Using PAG Node(default) 使用PAG节点（默认参数）

steps: 30\28

CFG: 5.5

sampler: dpmpp_2m (Web UI: dpm2p_m karras?)

scheduler: karras

The following is the effect of not using Lokr, only inputting the corresponding artist prompt word into the noob model for t2i, and using Lokr with kuse_ (0201) 3 as the trigger word for text generation. (Both use the same prompt and seed)

noob xl 0.75直出t2i（artist tag kuse_(0201) only）

使用lokr后t2i效果图 (lokr used, trigger word kuse_(0201) 3)

noob xl 0.75直出t2i（artist tag kuse_(0201) only）

使用lokr后t2i效果图 (lokr used, trigger word kuse_(0201) 3)

For NoobXL early access lokr v1.0 关于noobxl lokr v1.0版本

1:This model is a sdxl-lora based on NoobXL early access version.Using sdxl_vae as a vae.

1：本模型是基于NoobXL early access version底膜训练的sdxl Lokr模型，使用sdxl_vae作为vae。

ATTENTION ！As a kind of Lycoris model, most of times its usages are as same as the sdxl lora. However, lokr CANNOT be used on some batch nodes on Comfy UI (e: Lora stack). You can use the XYZ PLOT on Web UI to achieve similar functionality ！！！

注意！作为Lycoris模型系列下的Lokr模型，虽然在大部分情况下使用方法与普通lora无异，但部分ComfyUI 测试功能如（Lora堆节点（lora stack）等）是用不了的！建议使用Web UI的xyz图表功能来完成同类操作！！！

加注：本模型展示图仅通过文生图（832x1216）与高清放大（1664x2432）生成。

Tips: Pictures showed on the screen were only generated by t2i (832x1216) and hire-fix (1664x2432).

2: tag rule tag排布规则：

推荐设置/Recommended settings

prompt:

<1girl/1boy/1other/...>,

<character>, <series>, <artists>,

<general tags>,

masterpiece,best quality,absurdres,highres,sensitive,newest,

negative prompt (short) :

lowres,low quality, worst quality, normal quality, text, signature, jpeg artifacts, bad anatomy, old, early, multiple views, copyright name, watermark, artist name, signature

negative prompt (long) :

lowres,bad anatomy,blurry,(worst quality:1.8),low quality,hands bad,(normal quality:1.3),bad hands,mutated hands and fingers,extra legs,extra arms,duplicate,cropped,jpeg,artifacts,blurry,multiple view,reference sheet,long body,multiple breasts,mutated,bad anatomy,disfigured,bad proportions,bad feet,ugly,text font ui,missing limb,monochrome,bad anatomy,blurry,(worst quality:1.8),low quality,hands bad,face bad,(normal quality:1.3),bad hands,mutated hands and fingers,extra legs,extra arms,duplicate,cropped,jpeg,artifacts,blurry,multiple view,long body,multiple breasts,mutated,disfigured,bad proportions,duplicate,bad feet,ugly,missing limb,

负面提示词必须包含: lowres (由于使用了大量低分辨率图片进行训练)。worst quality 和 low quality 可根据个人需求选择是否添加。也可以使用例图里的负面提示词(long)，这串提示词是内部成员测试时使用的的，它非常的“屎山”，我们也无法确认其效果如何，但”it just work.”。

Negative prompts must include: lowres (due to the use of a large number of low-resolution images for training). "worst quality" and "low quality" can be added based on personal preference. You can also use the negative prompts (long) shown in the example images. This string of prompts was used by internal members during testing. It is quite "shitty", and we cannot confirm its effectiveness, but "it just works."

3:Rules of trigger word: 模型触发词使用规则

（1）：画风触发词格式与分类：kuse (0201) xxx

<1>早期（early）（2017.7-2021.6）：kuse (0201) 1

<2>中期（mid）（2021.6-2022.7？）：kuse (0201) 2

<3>晚期（latest）（2022.7？-2024.10）：kuse (0201) 3

example： <1girl/1boy/1other/...>,

<character>, <series>, kuse (0201) xxx,

<general tags>,

masterpiece,best quality,absurdres,highres,sensitive,newest,

4:generation data(example)(Comfy UI): 生成参数（Comfyui）

lora weight: 1

Using Efficiency nodes (restore Web UI usage)（使用效率节点还原Web UI参数，Web UI可无视）

Using PAG Node(default) 使用PAG节点（默认参数）

steps: 30\28

CFG: 5.5

sampler: dpmpp_2m (Web UI: dpm2p_m karras?)

scheduler: karras

The following is the effect of not using Lokr, only inputting the corresponding artist prompt word into the noob model for t2i, and using Lokr with kuse_ (0201) 3 as the trigger word for text generation. (Both use the same prompt and seed)

noob xl v0.5直出t2i（artist tag kuse_(0201) only）

使用lokr后t2i效果图 (lokr used, trigger word kuse_(0201) 3)