Stable Diffusion - 版本历史

Riguz：/* ComfyUI */

2024-05-08T10:38:34Z

ComfyUI

←上一版本		2024年5月8日 (三) 10:38的版本
第75行：		第75行：
	python3 main.py --port 5050 --listen		python3 main.py --port 5050 --listen
	</syntaxhighlight>		</syntaxhighlight>

			<syntaxhighlight lang="bash">
			cd custom_nodes
			git clone https://github.com/ltdrdata/ComfyUI-Manager.git
			</syntaxhighlight> <ref>https://www.comflowy.com/zh-CN/preparation-for-study/install-comfyui-manager</ref>

	Use *vae.safetensors<ref>https://www.tinydesk.ai/post/what-is-sdxl-vae</ref>.		Use *vae.safetensors<ref>https://www.tinydesk.ai/post/what-is-sdxl-vae</ref>.

Riguz：/* Webui */

2024-05-08T09:08:56Z

Webui

←上一版本		2024年5月8日 (三) 09:08的版本
第48行：		第48行：
	<syntaxhighlight lang="bash">		<syntaxhighlight lang="bash">
	sudo apt install wget git python3 python3-venv libgl1 libglib2.0-0		sudo apt install wget git python3 python3-venv libgl1 libglib2.0-0
			# https://github.com/AUTOMATIC1111/stable-diffusion-webui/issues/10117#issuecomment-1536437860
			sudo apt install --no-install-recommends google-perftools
	git clone https://github.com/AUTOMATIC1111/stable-diffusion-webui.git		git clone https://github.com/AUTOMATIC1111/stable-diffusion-webui.git
	cd stable-diffusion-webui		cd stable-diffusion-webui

Riguz：/* ComfyUI */

2024-05-08T03:19:22Z

ComfyUI

←上一版本		2024年5月8日 (三) 03:19的版本
第75行：		第75行：

	Use *vae.safetensors<ref>https://www.tinydesk.ai/post/what-is-sdxl-vae</ref>.		Use *vae.safetensors<ref>https://www.tinydesk.ai/post/what-is-sdxl-vae</ref>.

			<ref>https://www.tinydesk.ai/post/get-started-comfyui-quick-guide</ref>

	[[Category:Linux/Unix]]		[[Category:Linux/Unix]]
	[[Category:AI]]		[[Category:AI]]

Riguz：/* Webui */

2024-05-08T02:58:26Z

Webui

@@ 第59行： / 第59行： @@
 To use new models, download *.safetensors and put into /models/xx folder.
 [[Category:Linux/Unix]]
 [[Category:AI]]

Riguz：/* Stable Diffusion */

2024-05-07T05:45:02Z

Stable Diffusion

←上一版本		2024年5月7日 (二) 05:45的版本
第57行：		第57行：
	export COMMANDLINE_ARGS="--listen --port 5050 --subpath=/kas/py36lph9lctmsk11hp7gngmbt37n"		export COMMANDLINE_ARGS="--listen --port 5050 --subpath=/kas/py36lph9lctmsk11hp7gngmbt37n"
	</syntaxhighlight>		</syntaxhighlight>

			To use new models, download *.safetensors and put into /models/xx folder.

	[[Category:Linux/Unix]]		[[Category:Linux/Unix]]
	[[Category:AI]]		[[Category:AI]]

Riguz：创建页面，内容为“ = Dockerfile= FROM nvidia/cuda:12.4.1-cudnn-devel-ubuntu22.04 RUN sed -i 's|http://ports.ubuntu.com/|https://mirrors.tuna.tsinghua.edu.cn/ubuntu-ports/|g' /etc/apt/sources.list /etc/apt/sources.list && \ apt update && \ apt install -y build-essential cmake wget git python3 python3-pip sudo RUN pip3 install jupyterlab RUN apt-get install -y openssh-client openssh-server && \ mkdir -p /var/run/sshd && \ sed -…”

2024-05-07T03:49:17Z

创建页面，内容为“ = Dockerfile= <syntaxhighlight lang="dockerfile"> FROM nvidia/cuda:12.4.1-cudnn-devel-ubuntu22.04 RUN sed -i 's|http://ports.ubuntu.com/|https://mirrors.tuna.tsinghua.edu.cn/ubuntu-ports/|g' /etc/apt/sources.list /etc/apt/sources.list && \ apt update && \ apt install -y build-essential cmake wget git python3 python3-pip sudo RUN pip3 install jupyterlab RUN apt-get install -y openssh-client openssh-server && \ mkdir -p /var/run/sshd && \ sed -…”

新页面

= Dockerfile=

<syntaxhighlight lang="dockerfile">
FROM nvidia/cuda:12.4.1-cudnn-devel-ubuntu22.04

RUN sed -i 's|http://ports.ubuntu.com/|https://mirrors.tuna.tsinghua.edu.cn/ubuntu-ports/|g' /etc/apt/sources.list /etc/apt/sources.list && \
apt update && \
apt install -y build-essential cmake wget git python3 python3-pip sudo
RUN pip3 install jupyterlab
RUN apt-get install -y openssh-client openssh-server && \
mkdir -p /var/run/sshd && \
sed -ri 's/^PermitRootLogin\s+.*/PermitRootLogin yes/' /etc/ssh/sshd_config && \
cat /etc/ssh/ssh_config | grep -v StrictHostKeyChecking > /etc/ssh/ssh_config.new && \
echo " StrictHostKeyChecking no" >> /etc/ssh/ssh_config.new && \
mv /etc/ssh/ssh_config.new /etc/ssh/ssh_config

CMD ["sleep", "infinity"]
</syntaxhighlight>

Check GPU:
<syntaxhighlight lang="bash">
nvidia-smi
Tue May 7 11:47:20 2024
+---------------------------------------------------------------------------------------+
| NVIDIA-SMI 535.54.03 Driver Version: 535.54.03 CUDA Version: 12.2 |
|-----------------------------------------+----------------------+----------------------+
| GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. |
| | | MIG M. |
|=========================================+======================+======================|
| 0 NVIDIA GeForce RTX 2080 Ti On | 00000000:85:00.0 Off | N/A |
| 36% 28C P8 20W / 250W | 2847MiB / 11264MiB | 0% Default |
| | | N/A |
+-----------------------------------------+----------------------+----------------------+

+---------------------------------------------------------------------------------------+
| Processes: |
| GPU GI CI PID Type Process name GPU Memory |
| ID ID Usage |
|=======================================================================================|
+---------------------------------------------------------------------------------------+
</syntaxhighlight>

= Stable Diffusion =
== Webui==

<syntaxhighlight lang="bash">
sudo apt install wget git python3 python3-venv libgl1 libglib2.0-0
git clone https://github.com/AUTOMATIC1111/stable-diffusion-webui.git
cd stable-diffusion-webui
bash webui.sh
</syntaxhighlight>

To change configuration, edit webui-user.sh:
<syntaxhighlight lang="bash">
export COMMANDLINE_ARGS="--listen --port 5050 --subpath=/kas/py36lph9lctmsk11hp7gngmbt37n"
</syntaxhighlight>

[[Category:Linux/Unix]]
[[Category:AI]]

Stable Diffusion - 版本历史

Riguz：​/* ComfyUI */

Riguz：​/* Webui */

Riguz：​/* ComfyUI */

Riguz：​/* Webui */

Riguz：​/* Stable Diffusion */

Riguz：/* ComfyUI */

Riguz：/* Webui */

Riguz：/* ComfyUI */

Riguz：/* Webui */

Riguz：/* Stable Diffusion */