Stable Diffusion Web UIをインストールする！（Ubuntu Desktop 22.04／GPUなし）
Ubuntu Desktop 22.04で、NVIDIAのGPUなしの環境で、Stable Diffusion Web UIをインストールします。
記事の目次
PyTorchをインストールする！
以下の記事を参考にPyTorchをインストールします。
Gitをインストールする！
Gitがインストールされていない場合は、Gitを標準のリポジトリからインストールします。
$ sudo apt install git
Git HubからStable Diffusion Web UIをダウンロードする！
Git HubからStable Diffusion Web UIをインストールします。
$ git clone https://github.com/AUTOMATIC1111/stable-diffusion-webui Cloning into 'stable-diffusion-webui'... remote: Enumerating objects: 26602, done. remote: Counting objects: 100% (31/31), done. remote: Compressing objects: 100% (18/18), done. remote: Total 26602 (delta 16), reused 24 (delta 13), pack-reused 26571 Receiving objects: 100% (26602/26602), 31.93 MiB | 20.98 MiB/s, done. Resolving deltas: 100% (18641/18641), done.
Stable Diffusion Web UIのディレクトリに移動する！
Stable Diffution Web UIをダウンロードしたディレクトリに移動します。
$ cd stable-diffusion-webui
Stable Diffusion Web UIを起動する！
Stable Diffusion Web UIを起動します。少し時間がかかります。アクセスするためのURLが表示されればインストール完了です。プロンプトは終了しないので注意しましょう。
$ python3 launch.py --use-cpu all --no-half --no-half-vae --skip-torch-cuda-test Python 3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0] Version: v1.5.2 Commit hash: c9c8485bc1e8720aba70f029d25cba1c4abf2b5c Installing gfpgan Installing clip Installing open_clip Cloning Stable Diffusion into /home/usradmin/stable-diffusion-webui/repositories/stable-diffusion-stability-ai... Cloning into '/home/usradmin/stable-diffusion-webui/repositories/stable-diffusion-stability-ai'... remote: Enumerating objects: 574, done. remote: Counting objects: 100% (304/304), done. remote: Compressing objects: 100% (86/86), done. remote: Total 574 (delta 244), reused 218 (delta 218), pack-reused 270 Receiving objects: 100% (574/574), 73.43 MiB | 21.74 MiB/s, done. Resolving deltas: 100% (276/276), done. Cloning Stable Diffusion XL into /home/usradmin/stable-diffusion-webui/repositories/generative-models... Cloning into '/home/usradmin/stable-diffusion-webui/repositories/generative-models'... remote: Enumerating objects: 740, done. remote: Counting objects: 100% (563/563), done. remote: Compressing objects: 100% (286/286), done. remote: Total 740 (delta 337), reused 424 (delta 263), pack-reused 177 Receiving objects: 100% (740/740), 22.32 MiB | 22.85 MiB/s, done. Resolving deltas: 100% (375/375), done. Cloning K-diffusion into /home/usradmin/stable-diffusion-webui/repositories/k-diffusion... Cloning into '/home/usradmin/stable-diffusion-webui/repositories/k-diffusion'... remote: Enumerating objects: 957, done. remote: Counting objects: 100% (233/233), done. remote: Compressing objects: 100% (131/131), done. remote: Total 957 (delta 150), reused 177 (delta 102), pack-reused 724 Receiving objects: 100% (957/957), 208.76 KiB | 1.68 MiB/s, done. Resolving deltas: 100% (628/628), done. Cloning CodeFormer into /home/usradmin/stable-diffusion-webui/repositories/CodeFormer... Cloning into '/home/usradmin/stable-diffusion-webui/repositories/CodeFormer'... remote: Enumerating objects: 594, done. remote: Counting objects: 100% (245/245), done. remote: Compressing objects: 100% (97/97), done. remote: Total 594 (delta 175), reused 170 (delta 148), pack-reused 349 Receiving objects: 100% (594/594), 17.31 MiB | 20.85 MiB/s, done. Resolving deltas: 100% (286/286), done. Cloning BLIP into /home/usradmin/stable-diffusion-webui/repositories/BLIP... Cloning into '/home/usradmin/stable-diffusion-webui/repositories/BLIP'... remote: Enumerating objects: 277, done. remote: Counting objects: 100% (165/165), done. remote: Compressing objects: 100% (30/30), done. remote: Total 277 (delta 137), reused 136 (delta 135), pack-reused 112 Receiving objects: 100% (277/277), 7.03 MiB | 17.96 MiB/s, done. Resolving deltas: 100% (153/153), done. Installing requirements for CodeFormer Installing requirements Launching Web UI with arguments: --use-cpu all --no-half --no-half-vae --skip-torch-cuda-test /usr/lib/python3/dist-packages/pkg_resources/__init__.py:116: PkgResourcesDeprecationWarning: 1.1build1 is an invalid version and will not be supported in a future release warnings.warn( /usr/lib/python3/dist-packages/pkg_resources/__init__.py:116: PkgResourcesDeprecationWarning: 0.1.43ubuntu1 is an invalid version and will not be supported in a future release warnings.warn( no module 'xformers'. Processing without... no module 'xformers'. Processing without... No module 'xformers'. Proceeding without it. Warning: caught exception 'Found no NVIDIA driver on your system. Please check that you have an NVIDIA GPU and installed a driver from http://www.nvidia.com/Download/index.aspx', memory monitor disabled Downloading: "https://huggingface.co/runwayml/stable-diffusion-v1-5/resolve/main/v1-5-pruned-emaonly.safetensors" to /home/usradmin/stable-diffusion-webui/models/Stable-diffusion/v1-5-pruned-emaonly.safetensors 100%|██████████████████████████████████████████████████████████████████████████████| 3.97G/3.97G [01:19<00:00, 53.5MB/s] [W NNPACK.cpp:64] Could not initialize NNPACK! Reason: Unsupported hardware. Calculating sha256 for /home/usradmin/stable-diffusion-webui/models/Stable-diffusion/v1-5-pruned-emaonly.safetensors: Running on local URL: http://127.0.0.1:7860 To create a public link, set `share=True` in `launch()`. Startup time: 215.1s (launcher: 124.1s, import torch: 5.2s, import gradio: 1.4s, setup paths: 0.7s, other imports: 0.8s, setup codeformer: 0.2s, list SD models: 80.6s, load scripts: 0.9s, create ui: 0.8s, gradio launch: 0.2s). 6ce0161689b3853acaa03779ec93eafe75a02f4ced659bee03f50797806fa2fa Loading weights [6ce0161689] from /home/usradmin/stable-diffusion-webui/models/Stable-diffusion/v1-5-pruned-emaonly.safetensors Creating model from config: /home/usradmin/stable-diffusion-webui/configs/v1-inference.yaml LatentDiffusion: Running in eps-prediction mode DiffusionWrapper has 859.52 M params. Downloading (…)olve/main/vocab.json: 100%|███████████████████████████████████████████| 961k/961k [00:00<00:00, 1.36MB/s] Downloading (…)olve/main/merges.txt: 100%|███████████████████████████████████████████| 525k/525k [00:00<00:00, 1.06MB/s] Downloading (…)cial_tokens_map.json: 100%|█████████████████████████████████████████████| 389/389 [00:00<00:00, 1.68MB/s] Downloading (…)okenizer_config.json: 100%|█████████████████████████████████████████████| 905/905 [00:00<00:00, 4.42MB/s] Downloading (…)lve/main/config.json: 100%|█████████████████████████████████████████| 4.52k/4.52k [00:00<00:00, 16.7MB/s] Applying attention optimization: InvokeAI... done. Model loaded in 51.8s (calculate hash: 16.9s, load weights from disk: 0.5s, create model: 5.9s, apply weights to model: 25.7s, hijack: 0.2s, load textual inversion embeddings: 0.3s, calculate empty prompt: 2.1s).
Stable Diffution Web UIにアクセスする！
表示された以下のURLにアクセスするとStable DiffusionのWeb UI画面にアクセスできます。
http://127.0.0.1:7860
おわりに
Stable Diffusion Web UIは、GitHubからダウンロードすることができます。
参考情報
関連記事
