强大的stable-diffusion-webui通过webui-user.bat/sh (Windows/Linux) 文件进行配置，今天的主角是COMMANDLINE_ARGS参数，以下就是COMMANDLINE_ARGS参数带详解，附送google翻译的描述。
| Argument Command | Value | Default | Description | 描述（google翻译） |
| CONFIGURATION | ||||
| -h, –help | None | FALSE | Show this help message and exit. | 显示此帮助消息并退出。 |
| –exit | Terminate after installation | 安装后终止 | ||
| –data-dir | DATA_DIR | ./ | base path where all user data is stored | 存储所有用户数据的基本路径 |
| –config | CONFIG | configs/stable-diffusion/v1-inference.yaml | Path to config which constructs model. | 构造模型的配置路径。 |
| –ckpt | CKPT | model.ckpt | Path to checkpoint of Stable Diffusion model; if specified, this checkpoint will be added to the list of checkpoints and loaded. | 稳定扩散模型检查点的路径；如果指定，该检查点将被添加到检查点列表中并加载。 |
| –ckpt-dir | CKPT_DIR | None | Path to directory with Stable Diffusion checkpoints. | 具有稳定扩散检查点的目录路径。 |
| –no-download-sd-model | None | FALSE | Don’t download SD1.5 model even if no model is found. | 即使没有找到模型，也不要下载SD1.5模型。 |
| –do-not-download-clip | None | FALSE | do not download CLIP model even if it’s not included in the checkpoint | 即使未包含在检查点中，也不要下载 CLIP 模型 |
| –vae-dir | VAE_PATH | None | Path to Variational Autoencoders model | 变分自动编码器模型的路径 |
| –vae-path | VAE_PATH | None | Checkpoint to use as VAE; setting this argument | 用作 VAE 的检查点；设置这个参数 |
| –gfpgan-dir | GFPGAN_DIR | GFPGAN/ | GFPGAN directory. | GFPGAN 目录。 |
| –gfpgan-model | GFPGAN_MODEL | GFPGAN model file name. | ||
| –codeformer-models-path | CODEFORMER_MODELS_PATH | models/Codeformer/ | Path to directory with codeformer model file(s). | 包含 Codeformer 模型文件的目录路径。 |
| –gfpgan-models-path | GFPGAN_MODELS_PATH | models/GFPGAN | Path to directory with GFPGAN model file(s). | 包含 GFPGAN 模型文件的目录路径。 |
| –esrgan-models-path | ESRGAN_MODELS_PATH | models/ESRGAN | Path to directory with ESRGAN model file(s). | 包含 ESRGAN 模型文件的目录路径。 |
| –bsrgan-models-path | BSRGAN_MODELS_PATH | models/BSRGAN | Path to directory with BSRGAN model file(s). | 包含 BSRGAN 模型文件的目录路径。 |
| –realesrgan-models-path | REALESRGAN_MODELS_PATH | models/RealESRGAN | Path to directory with RealESRGAN model file(s). | RealESRGAN 模型文件的目录路径。 |
| –scunet-models-path | SCUNET_MODELS_PATH | models/ScuNET | Path to directory with ScuNET model file(s). | ScuNET 模型文件的目录路径。 |
| –swinir-models-path | SWINIR_MODELS_PATH | models/SwinIR | Path to directory with SwinIR and SwinIR v2 model file(s). | 包含 SwinIR 和 SwinIR v2 模型文件的目录路径。 |
| –ldsr-models-path | LDSR_MODELS_PATH | models/LDSR | Path to directory with LDSR model file(s). | 包含 LDSR 模型文件的目录路径。 |
| –lora-dir | LORA_DIR | models/Lora | Path to directory with Lora networks. | Lora 网络目录的路径。 |
| –clip-models-path | CLIP_MODELS_PATH | None | Path to directory with CLIP model file(s). | 包含 CLIP 模型文件的目录路径。 |
| –embeddings-dir | EMBEDDINGS_DIR | embeddings/ | Embeddings directory for textual inversion (default: embeddings). | 用于文本反转的嵌入目录（默认值：嵌入）。 |
| –textual-inversion-templates-dir | TEXTUAL_INVERSION_TEMPLATES_DIR | textual_inversion_templates | Directory with textual inversion templates. | 带有文本反转模板的目录。 |
| –hypernetwork-dir | HYPERNETWORK_DIR | models/hypernetworks/ | hypernetwork directory. | 超网络目录。 |
| –localizations-dir | LOCALIZATIONS_DIR | localizations/ | Localizations directory. | 本地化目录。 |
| –styles-file | STYLES_FILE | styles.csv | Filename to use for styles. | 用于样式的文件名。 |
| –ui-config-file | UI_CONFIG_FILE | ui-config.json | Filename to use for UI configuration. | 用于 UI 配置的文件名。 |
| –no-progressbar-hiding | None | FALSE | Do not hide progress bar in gradio UI (we hide it because it slows down ML if you have hardware acceleration in browser). | 不要在 gradio UI 中隐藏进度条（我们隐藏它是因为如果浏览器中有硬件加速，它会减慢 ML 速度）。 |
| –max-batch-count | MAX_BATCH_COUNT | 16 | Maximum batch count value for the UI. | UI 的最大批次计数值。 |
| –ui-settings-file | UI_SETTINGS_FILE | config.json | Filename to use for UI settings. | 用于 UI 设置的文件名。 |
| –allow-code | None | FALSE | Allow custom script execution from web UI. | 允许从 Web UI 执行自定义脚本。 |
| –share | None | FALSE | Use share=True for gradio and make the UI accessible through their site. | 用于share=Truegradio 并使 UI 可通过其网站访问。 |
| –listen | None | FALSE | Launch gradio with 0.0.0.0 as server name, allowing to respond to network requests. | 使用 0.0.0.0 作为服务器名称启动 gradio，允许响应网络请求。 |
| –port | PORT | 7860 | Launch gradio with given server port, you need root/admin rights for ports < 1024; defaults to 7860 if available. | 使用给定的服务器端口启动 gradio，您需要端口 < 1024 的 root/admin 权限；如果可用，默认为 7860。 |
| –hide-ui-dir-config | None | FALSE | Hide directory configuration from web UI. | 从 Web UI 隐藏目录配置。 |
| –freeze-settings | None | FALSE | disable editing settings | 禁用编辑设置 |
| –enable-insecure-extension-access | None | FALSE | Enable extensions tab regardless of other options. | 无论其他选项如何，都启用扩展选项卡。 |
| –gradio-debug | None | FALSE | Launch gradio with –debug option. | 启动带有–debug选项的 gradio。 |
| –gradio-auth | GRADIO_AUTH | None | Set gradio authentication like username:password; or comma-delimit multiple like u1:p1,u2:p2,u3:p3. | 设置 gradio 身份验证，例如username:password；或用逗号分隔多个，例如u1:p1,u2:p2,u3:p3. |
| –gradio-auth-path | GRADIO_AUTH_PATH | None | Set gradio authentication file path ex. /path/to/auth/file same auth format as –gradio-auth. | 设置gradio认证文件路径ex。/path/to/auth/file与 相同的身份验证格式–gradio-auth。 |
| –disable-console-progressbars | None | FALSE | Do not output progress bars to console. | 不要将进度条输出到控制台。 |
| –enable-console-prompts | None | FALSE | Print prompts to console when generating with txt2img and img2img. | 使用 txt2img 和 img2img 生成时将提示打印到控制台。 |
| –api | None | FALSE | Launch web UI with API. | 使用 API 启动 Web UI。 |
| –api-auth | API_AUTH | None | Set authentication for API like username:password; or comma-delimit multiple like u1:p1,u2:p2,u3:p3. | 设置 API 的身份验证，例如username:password；或用逗号分隔多个，例如u1:p1,u2:p2,u3:p3. |
| –api-log | None | FALSE | Enable logging of all API requests. | 启用所有 API 请求的日志记录。 |
| –nowebui | None | FALSE | Only launch the API, without the UI. | 只启动 API，不启动 UI。 |
| –ui-debug-mode | None | FALSE | Don’t load model to quickly launch UI. | 不要加载模型来快速启动 UI。 |
| –device-id | DEVICE_ID | None | Select the default CUDA device to use (export CUDA_VISIBLE_DEVICES=0,1 etc might be needed before). | 选择要使用的默认 CUDA 设备（CUDA_VISIBLE_DEVICES=0,1之前可能需要导出等）。 |
| –administrator | None | FALSE | Administrator privileges. | 管理员权限。 |
| –cors-allow-origins | CORS_ALLOW_ORIGINS | None | Allowed CORS origin(s) in the form of a comma-separated list (no spaces). | 允许的 CORS 来源采用逗号分隔列表的形式（无空格）。 |
| –cors-allow-origins-regex | CORS_ALLOW_ORIGINS_REGEX | None | Allowed CORS origin(s) in the form of a single regular expression. | 允许采用单个正则表达式形式的 CORS 来源。 |
| –tls-keyfile | TLS_KEYFILE | None | Partially enables TLS, requires –tls-certfile to fully function. | 部分启用 TLS，需要–tls-certfile完全发挥作用。 |
| –tls-certfile | TLS_CERTFILE | None | Partially enables TLS, requires –tls-keyfile to fully function. | 部分启用 TLS，需要–tls-keyfile完全发挥作用。 |
| –disable-tls-verify | None | FALSE | When passed, enables the use of self-signed certificates. | 通过后，即可使用自签名证书。 |
| –server-name | SERVER_NAME | None | Sets hostname of server. | 设置服务器的主机名。 |
| –no-gradio-queue | None | FALSE | Disables gradio queue; causes the webpage to use http requests instead of websockets; was the default in earlier versions. | 禁用渐变队列；导致网页使用http请求而不是websocket；是早期版本中的默认值。 |
| –gradio-allowed-path | None | None | Add path to Gradio’s allowed_paths; make it possible to serve files from it. | 添加Gradio的路径allowed_paths；使得可以从中提供文件。 |
| –no-hashing | None | FALSE | Disable SHA-256 hashing of checkpoints to help loading performance. | 禁用检查点的 SHA-256 哈希以帮助加载性能。 |
| –skip-version-check | None | FALSE | Do not check versions of torch and xformers. | 不要检查 torch 和 xformers 的版本。 |
| –skip-python-version-check | None | FALSE | Do not check versions of Python. | 不检查 Python 的版本。 |
| –skip-torch-cuda-test | None | FALSE | Do not check if CUDA is able to work properly. | 不检查CUDA是否能够正常工作。 |
| –skip-install | None | FALSE | Skip installation of packages. | 跳过软件包的安装。 |
| –loglevel | None | None | log level; one of: CRITICAL, ERROR, WARNING, INFO, DEBUG | 日志级别；以下之一：严重、错误、警告、信息、调试 |
| –log-startup | None | FALSE | launch.py argument: print a detailed log of what’s happening at startup | launch.py 参数：打印启动时发生的情况的详细日志 |
| –api-server-stop | None | FALSE | enable server stop/restart/kill via api | 通过 api 启用服务器停止/重新启动/终止 |
| –timeout-keep-alive | int | 30 | set timeout_keep_alive for uvicorn | 为 uvicorn 设置 timeout_keep_alive |
| PERFORMANCE | ||||
| –xformers | None | FALSE | Enable xformers for cross attention layers. | 为交叉注意力层启用 xformers。 |
| –force-enable-xformers | None | FALSE | Enable xformers for cross attention layers regardless of whether the checking code thinks you can run it; do not make bug reports if this fails to work. | 为交叉注意层启用 xformers，无论检查代码是否认为您可以运行它；如果这不起作用，请不要报告错误。 |
| –xformers-flash-attention | None | FALSE | Enable xformers with Flash Attention to improve reproducibility (supported for SD2.x or variant only). | 启用带有 Flash Attention 的 xformers 以提高再现性（仅支持 SD2.x 或变体）。 |
| –opt-sdp-attention | None | FALSE | Enable scaled dot product cross-attention layer optimization; requires PyTorch 2.* | 启用缩放点积交叉注意层优化；需要 PyTorch 2.* |
| –opt-sdp-no-mem-attention | FALSE | None | Enable scaled dot product cross-attention layer optimization without memory efficient attention, makes image generation deterministic; requires PyTorch 2.* | 启用缩放点积交叉注意力层优化，无需内存高效注意力，使图像生成具有确定性；需要 PyTorch 2.* |
| –opt-split-attention | None | FALSE | Force-enables Doggettx’s cross-attention layer optimization. By default, it’s on for CUDA-enabled systems. | 强制启用 Doggettx 的交叉注意力层优化。默认情况下，它在启用 CUDA 的系统上处于打开状态。 |
| –opt-split-attention-invokeai | None | FALSE | Force-enables InvokeAI’s cross-attention layer optimization. By default, it’s on when CUDA is unavailable. | 强制启用 InvokeAI 的交叉注意力层优化。默认情况下，当 CUDA 不可用时它会打开。 |
| –opt-split-attention-v1 | None | FALSE | Enable older version of split attention optimization that does not consume all VRAM available. | 启用旧版本的分割注意力优化，不会消耗所有可用的 VRAM。 |
| –opt-sub-quad-attention | None | FALSE | Enable memory efficient sub-quadratic cross-attention layer optimization. | 实现内存高效的次二次交叉注意力层优化。 |
| –sub-quad-q-chunk-size | SUB_QUAD_Q_CHUNK_SIZE | 1024 | Query chunk size for the sub-quadratic cross-attention layer optimization to use. | 用于次二次交叉注意力层优化的查询块大小。 |
| –sub-quad-kv-chunk-size | SUB_QUAD_KV_CHUNK_SIZE | None | KV chunk size for the sub-quadratic cross-attention layer optimization to use. | 用于次二次交叉注意力层优化的 KV 块大小。 |
| –sub-quad-chunk-threshold | SUB_QUAD_CHUNK_THRESHOLD | None | The percentage of VRAM threshold for the sub-quadratic cross-attention layer optimization to use chunking. | 使用分块进行次二次交叉注意力层优化的 VRAM 阈值的百分比。 |
| –opt-channelslast | None | FALSE | Enable alternative layout for 4d tensors, may result in faster inference only on Nvidia cards with Tensor cores (16xx and higher). | 启用 4d 张量的替代布局，可能会导致仅在具有 Tensor 核心（16xx 及更高）的 Nvidia 卡上更快的推理。 |
| –disable-opt-split-attention | None | FALSE | Force-disables cross-attention layer optimization. | 强制禁用交叉注意力层优化。 |
| –disable-nan-check | None | FALSE | Do not check if produced images/latent spaces have nans; useful for running without a checkpoint in CI. | 不检查生成的图像/潜在空间是否有 nan；对于在 CI 中没有检查点的情况下运行很有用。 |
| –use-cpu | {all, sd, interrogate, gfpgan, bsrgan, esrgan, scunet, codeformer} | None | Use CPU as torch device for specified modules. | 使用CPU作为指定模块的火炬设备。 |
| –no-half | None | FALSE | Do not switch the model to 16-bit floats. | 不要将模型切换为 16 位浮点数。 |
| –precision | {full,autocast} | autocast | Evaluate at this precision. | 以此精度进行评估。 |
| –no-half-vae | None | FALSE | Do not switch the VAE model to 16-bit floats. | 不要将 VAE 模型切换为 16 位浮点数。 |
| –upcast-sampling | None | FALSE | Upcast sampling. No effect with –no-half. Usually produces similar results to –no-half with better performance while using less memory. | 向上采样。对 没有影响–no-half。通常会–no-half在使用更少内存的情况下产生与更好性能类似的结果。 |
| –medvram | None | FALSE | Enable Stable Diffusion model optimizations for sacrificing a some performance for low VRAM usage. | 启用稳定扩散模型优化，以牺牲一些性能来降低 VRAM 使用率。 |
| –medvram-sdxl | None | FALSE | enable –medvram optimization just for SDXL models | –medvram仅针对 SDXL 模型启用优化 |
| –lowvram | None | FALSE | Enable Stable Diffusion model optimizations for sacrificing a lot of speed for very low VRAM usage. | 启用稳定扩散模型优化，以牺牲大量速度以获得非常低的 VRAM 使用率。 |
| –lowram | None | FALSE | Load Stable Diffusion checkpoint weights to VRAM instead of RAM. | 将稳定扩散检查点权重加载到 VRAM 而不是 RAM。 |
| –disable-model-loading-ram-optimization | None | FALSE | disable an optimization that reduces RAM use when loading a model | 禁用加载模型时减少 RAM 使用的优化 |
| FEATURES | ||||
| –autolaunch | None | FALSE | Open the web UI URL in the system’s default browser upon launch. | 启动时在系统默认浏览器中打开 Web UI URL。 |
| –theme | None | Unset | Open the web UI with the specified theme (light or dark). If not specified, uses the default browser theme. | light打开具有指定主题（或）的 Web UI dark。如果未指定，则使用默认浏览器主题。 |
| –use-textbox-seed | None | FALSE | Use textbox for seeds in UI (no up/down, but possible to input long seeds). | 在 UI 中使用种子文本框（无向上/向下，但可以输入长种子）。 |
| –disable-safe-unpickle | None | FALSE | Disable checking PyTorch models for malicious code. | 禁用检查 PyTorch 模型是否存在恶意代码。 |
| –ngrok | NGROK | None | ngrok authtoken, alternative to gradio –share. | ngrok authtoken，gradio 的替代品–share。 |
| –ngrok-region | NGROK_REGION | us | The region in which ngrok should start. | ngrok 应该启动的区域。 |
| –update-check | None | None | On startup, notifies whether or not your web UI version (commit) is up-to-date with the current master branch. | 启动时，通知您的 Web UI 版本（提交）是否与当前主分支保持同步。 |
| –update-all-extensions | None | None | On startup, it pulls the latest updates for all extensions you have installed. | 启动时，它会提取您已安装的所有扩展的最新更新。 |
| –reinstall-xformers | None | FALSE | Force-reinstall xformers. Useful for upgrading – but remove it after upgrading or you’ll reinstall xformers perpetually. | 强制重新安装 xformers。对于升级很有用 – 但升级后将其删除，否则您将永久重新安装 xformers。 |
| –reinstall-torch | None | FALSE | Force-reinstall torch. Useful for upgrading – but remove it after upgrading or you’ll reinstall torch perpetually. | 强制重新安装割炬。对于升级很有用 – 但升级后将其删除，否则您将永久重新安装 torch。 |
| –tests | TESTS | FALSE | Run test to validate web UI functionality, see wiki topic for more details. | 运行测试以验证 Web UI 功能，请参阅 wiki 主题了解更多详细信息。 |
| –no-tests | None | FALSE | Do not run tests even if –tests option is specified. | –tests即使指定了选项，也不运行测试。 |
| –dump-sysinfo | None | FALSE | launch.py argument: dump limited sysinfo file (without information about extensions, options) to disk and quit | launch.py 参数：将有限的 sysinfo 文件（没有有关扩展、选项的信息）转储到磁盘并退出 |
| –disable-all-extensions | None | FALSE | disable all non-built-in extensions from running | 禁用所有非内置扩展运行 |
| –disable-extra-extensions | None | FALSE | disable all extensions from running | 禁用所有扩展程序运行 |
| DEFUNCT OPTIONS | ||||
| –show-negative-prompt | None | FALSE | No longer has an effect. | 不再有效果。 |
| –deepdanbooru | None | FALSE | No longer has an effect. | 不再有效果。 |
| –unload-gfpgan | None | FALSE | No longer has an effect. | 不再有效果。 |
| –gradio-img2img-tool | GRADIO_IMG2IMG_TOOL | None | No longer has an effect. | 不再有效果。 |
| –gradio-inpaint-tool | GRADIO_INPAINT_TOOL | None | No longer has an effect. | 不再有效果。 |
| –gradio-queue | None | FALSE | No longer has an effect. | 不再有效果。 |
| –add-stop-route | None | FALSE | No longer has an effect. | 不再有效果。 |
| –always-batch-cond-uncond | None | FALSE | No longer has an effect, move into UI under Setting > Optimizations | 不再有效果，移至UI下Setting > Optimizations |
参考：https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Command-Line-Arguments-and-Settings