伊奈(angel_ina) | artist sytle 2 in 1 |版本eps lokr v1.0 (ID: 1154916)

注意：本模型未经许可严禁转移至其他平台，若发现会立刻联系平台相关方进行下架处理,

Attention: This model is strictly prohibited from being transferred to other platforms without permission. If discovered, relevant parties on the platform will be immediately contacted for removal.

免责声明：本模型严禁用于除同人生成外的其他用途（如商业用途），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: This model is strictly prohibited from being used for purposes other than fan generated (such as commercial use). Users must strictly comply with local laws and regulations and use AI technology legally and compliantly. I am not responsible for any adverse consequences caused by the user's violation of local laws and regulations.

For NoobXL epsv11 lokr v1.0

关于noobxl lokr v1.0版本

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

1：本模型是基于NoobXL epsv1.1 底膜训练的sdxl Lokr模型，使用sdxl_vae作为vae,

注：所有基于noob eps v1.1及以后版本的模型训练的lora\lokr理论上均可直接用于noob vpred065s版本后的noob vpred模型！！！

Note: All models trained based on noob eps v1.1 and later versions, including LoRA/LoKR, can theoretically be used directly for noob vpred models of version vpred065s and later!

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\1024x1536）与面部修复（adetailer）生成,

Tips: Pictures showed on the screen were only generated by t2i (832x1216\1024x1536) and adetailer node.

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,

负面tag（除开画福瑞之外建议均使用这套负面tag）：

negative prompt (Unless you plan to create Fury, please use this set of negative tags) :

worst quality,old,early,low quality,quality,lowres,signature,username,bad id,bad twitter id,english commentary,logo,bad hands,mutated hands,mammal,anthro,furry,ambiguous_form,feral,semi-anthro,

3:Rules of trigger word: 模型触发词使用规则

（1）：画风触发词（trigger word）：angel ina x

早期画风触发词（early）：angel ina 1

晚期画风触发词（latest）（mainly use）：angel ina 2

example： <1girl/1boy/1other/...>,

<character>, <series>, angel ina x,

<general tags>,

nlp（自然语言）.

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

注：在dan tag格式的prompt后添加描述图片大致内容的英语自然语言（小于100字）有助于提升图像整体质量,

Note: Adding a natural language description of the general content （less than 100words）of the image after a prompt in dan tag format can help improve the overall quality of the image.

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

描述:

训练词语: