BadhandV4

介绍（Chinese Version）

简介

此文本嵌入（text embedding）为 负面文本嵌入。它能够在对画风影响较小的前提下改善AI生成图片的手部细节。如果它让你的模型表现得比以前更糟，请勿使用它。您可与其他负面文本嵌入一同使用。虽然它是为 AnimeIllustDiffusion 模型设计的，但您也可以在其他模型上使用。

它似乎在较高的 CFG Scale 下（>=11）表现得更好。

如何使用

对于 AUTOMATIC1111 WebUI 用户

1. 下载模型文件 badhandv4.pt；

2. 将模型文件放置于您 Stable Diffusion WebUI 目录下的 "embeddings" 文件夹内；

3. 打开 WebUI，在负面提示词框内填入 “badhandv4” 以触发效果。

对于 ComfuUI 用户

1. 下载模型文件 badhandv4.pt；

2. 将模型文件放置于您 ComfyUI 目录下的 "models/embeddings" 文件夹内；

3. 打开 ComfyUI，在 负面提示词框内 填入 “embedding:badhandv4” 以触发效果。

Diffusers 管线

对于 Diffusers 库，您可以通过以下方式加载 Badhandv4：

import torch
from diffusers import StableDiffusionPipeline

pipe = StableDiffusionPipeline.from_pretrained(
    "admruul/anything-v3.0",
    torch_dtype=torch.float16,
).to("cuda")
pipe.load_textual_inversion("Eugeoter/badhandv4")
image = pipe('best quality, masterpiece, 1girl, open hand, upper body, smile', negative_prompt='<badhandv4>, worst quality, low quality, bad anatomy').images[0]
image.show()

Introduction (英文版本)

Introduction

This text embedding is a negative text embedding. It can improve the hand details of AI-generated images with less impact on the style of painting. If it makes your model behave worse than before, please do not use it. You can use it with other negative text embeddings.

Although it was designed for AnimeIllustDiffusion model, you can use it on other models as well.

It performs better with higher CFG scale (>=11).

Quick Start

For AUTOMATIC1111 WebUI User

1. Download model file badhandv4.pt;

2. Move the model file to the "embeddings" folder in your Stable Diffusion WebUI directory;

3. Lanuch WebUI. Enter "badhandv4" into the negative prompt box to trigger its effect.

For ComfyUI User

1. Download model file badhandv4.pt;

2. Move the model file to the "models/embeddings" folder in your ComfyUI directory;

3. Lanuch ComfyUI. Enter "embedding:badhandv4" into the negative prompt box to trigger its effect.

Diffusers Pipeline

For Diffusers library, you can load Badhandv4 through the following python code:

import torch
from diffusers import StableDiffusionPipeline

pipe = StableDiffusionPipeline.from_pretrained(
    "admruul/anything-v3.0",
    torch_dtype=torch.float16,
).to("cuda")
pipe.load_textual_inversion("Eugeoter/badhandv4")
image = pipe('best quality, masterpiece, 1girl, open hand, upper body, smile', negative_prompt='<badhandv4>, worst quality, low quality, bad anatomy').images[0]
image.show()