本次训练全程在colab上进行

1，连接云端硬盘

from google.colab import drive
drive.mount('/content/drive')

2，启动 StableDiffusion Web UI

%cd /content

%env TF_CPP_MIN_LOG_LEVEL=1

!apt -y update -qq
!wget http://launchpadlibrarian.net/367274644/libgoogle-perftools-dev_2.5-2.2ubuntu3_amd64.deb
!wget https://launchpad.net/ubuntu/+source/google-perftools/2.5-2.2ubuntu3/+build/14795286/+files/google-perftools_2.5-2.2ubuntu3_all.deb
!wget https://launchpad.net/ubuntu/+source/google-perftools/2.5-2.2ubuntu3/+build/14795286/+files/libtcmalloc-minimal4_2.5-2.2ubuntu3_amd64.deb
!wget https://launchpad.net/ubuntu/+source/google-perftools/2.5-2.2ubuntu3/+build/14795286/+files/libgoogle-perftools4_2.5-2.2ubuntu3_amd64.deb
!apt install -qq libunwind8-dev
!dpkg -i *.deb
%env LD_PRELOAD=libtcmalloc.so
!rm *.deb

!apt -y install -qq aria2
!pip install -q torch==1.13.1+cu116 torchvision==0.14.1+cu116 torchaudio==0.13.1 torchtext==0.14.1 torchdata==0.5.1 --extra-index-url https://download.pytorch.org/whl/cu116 -U
!pip install -q xformers==0.0.16 triton==2.0.0 -U

!git clone -b v1.9 https://github.com/camenduru/stable-diffusion-webui
!git clone https://huggingface.co/embed/negative /content/stable-diffusion-webui/embeddings/negative
!git clone https://huggingface.co/embed/lora /content/stable-diffusion-webui/models/Lora/positive
!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/embed/upscale/resolve/main/4x-UltraSharp.pth -d /content/stable-diffusion-webui/models/ESRGAN -o 4x-UltraSharp.pth
!wget https://raw.githubusercontent.com/camenduru/stable-diffusion-webui-scripts/main/run_n_times.py -O /content/stable-diffusion-webui/scripts/run_n_times.py
!git clone -b v1.9 https://github.com/camenduru/deforum-for-automatic1111-webui /content/stable-diffusion-webui/extensions/deforum-for-automatic1111-webui
!git clone -b v1.9 https://github.com/camenduru/stable-diffusion-webui-images-browser /content/stable-diffusion-webui/extensions/stable-diffusion-webui-images-browser
!git clone -b v1.9 https://github.com/camenduru/stable-diffusion-webui-huggingface /content/stable-diffusion-webui/extensions/stable-diffusion-webui-huggingface
!git clone -b v1.9 https://github.com/camenduru/sd-civitai-browser /content/stable-diffusion-webui/extensions/sd-civitai-browser
!git clone -b v1.9 https://github.com/camenduru/sd-webui-additional-networks /content/stable-diffusion-webui/extensions/sd-webui-additional-networks
!git clone -b v1.9 https://github.com/camenduru/sd-webui-tunnels /content/stable-diffusion-webui/extensions/sd-webui-tunnels
!git clone -b v1.9 https://github.com/camenduru/batchlinks-webui /content/stable-diffusion-webui/extensions/batchlinks-webui
!git clone -b v1.9 https://github.com/camenduru/stable-diffusion-webui-catppuccin /content/stable-diffusion-webui/extensions/stable-diffusion-webui-catppuccin
!git clone -b v1.9 https://github.com/camenduru/a1111-sd-webui-locon /content/stable-diffusion-webui/extensions/a1111-sd-webui-locon
!git clone -b v1.9 https://github.com/camenduru/stable-diffusion-webui-rembg /content/stable-diffusion-webui/extensions/stable-diffusion-webui-rembg
!git clone -b v1.9 https://github.com/camenduru/stable-diffusion-webui-two-shot /content/stable-diffusion-webui/extensions/stable-diffusion-webui-two-shot
!git clone -b v1.9 https://github.com/camenduru/sd_webui_stealth_pnginfo /content/stable-diffusion-webui/extensions/sd_webui_stealth_pnginfo
%cd /content/stable-diffusion-webui
!git reset --hard

!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/ckpt/stable-diffusion-2-1/resolve/main/v2-1_768-ema-pruned.ckpt -d /content/stable-diffusion-webui/models/Stable-diffusion -o v2-1_768-ema-pruned.ckpt
!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/ckpt/stable-diffusion-2-1/raw/main/v2-inference-v.yaml -d /content/stable-diffusion-webui/models/Stable-diffusion -o v2-1_768-ema-pruned.yaml

!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/joachimsallstrom/Double-Exposure-Embedding/resolve/main/dblx.pt -d /content/stable-diffusion-webui/embeddings -o dblx.pt
!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/Conflictx/AnimeScreencap/resolve/main/AnimeScreenCap.pt -d /content/stable-diffusion-webui/embeddings -o AnimeScreenCap.pt

!sed -i -e '''/    prepare_environment()/a    os.system(f"""sed -i -e ''"s/dict()))/dict())).cuda()/g"'' /content/stable-diffusion-webui/repositories/stable-diffusion-stability-ai/ldm/util.py""")''' /content/stable-diffusion-webui/launch.py
!sed -i -e 's/fastapi==0.90.1/fastapi==0.89.1/g' /content/stable-diffusion-webui/requirements_versions.txt

!mkdir /content/stable-diffusion-webui/extensions/deforum-for-automatic1111-webui/models

!sed -i -e 's/"sd_model_checkpoint",/"sd_model_checkpoint,sd_vae,CLIP_stop_at_last_layers",/g' /content/stable-diffusion-webui/modules/shared.py

!python launch.py --listen --xformers --enable-insecure-extension-access --theme dark --gradio-queue --multiple

3，上传原始照片

我们上传10张朱丽叶基德曼的照片

4，开始训练

Train Tab: 已经集成了Textual Inversion，可以用来训练现有神经网络，创造出新的概念，比如特定的人物、特定的风格等等。

4.1 Preprocess Image 图片预处理

4.2 Create Embedding 创建模型

创建embedding：给模型取个名字，这个非常重要，训练完成后，将会使用这个名字，作为触发的token。

Number of vectors per token:每个token的vector个数，如果图片较少，这里的值可以设置的大一些。

4.3 Train 训练模型

主要参数，见下图标识

Prompt模板内容

a photo of [name]

关于参数具体的取值：需要积累经验，根据不同的图片数量、质量，进行调优。

训练完成后，在/content/stable-diffusion-webui/textual_inversion目录以及/content/stable-diffusion-webui/embeddings目录生成了.pt文件，非常小，一般只有几十kb。可以复制保存，随时使用。

5，使用

a photo of modelofxyz

modelofxyz为之前你给模型取的名字

使用 Script Prompt S/R分析一下哪种CFG以及哪个阶段的模型效果最好

总的看来，较早阶段/较小CFG，人物饱和度较低，反之饱和度高。

下面开始使用Prompt，尝试不同的各种场景描述

a photo of modelofxyz-2000, walking at London street

CFG:4

a photo of modelofxyz-2000, wearing Chinese Tang clothing

CFG:5

a photo of modelofxyz-2000, wearing fashion long dress

a photo of modelofxyz-2000, (wearing EVA spacesuit:1.1)

其它