diff --git a/installation/manual_install.mdx b/installation/manual_install.mdx index d4992ea2..d9b851c2 100644 --- a/installation/manual_install.mdx +++ b/installation/manual_install.mdx @@ -5,19 +5,18 @@ icon: "wrench" sidebarTitle: "Manual Installation" --- -import GitClone from "/snippets/git-clone.mdx"; -import Conda from "/snippets/conda.mdx"; -import PipInstall from "/snippets/pip-install.mdx"; -import InstallGpuDependencies from "/snippets/install-gpu-dependencies.mdx"; -import RunComfy from "/snippets/run-comfy.mdx"; -import AddExternalModels from "/snippets/install/add-external-models.mdx" - For the installation of ComfyUI, it is mainly divided into several steps: 1. Create a virtual environment(avoid polluting the system-level Python environment) 2. Clone the ComfyUI code repository 3. Install dependencies 4. Start ComfyUI + +Python 3.13 is very well supported. If you have trouble with some custom node dependencies on 3.13 you can try 3.12. + +Python 3.14 will work if you comment out the `kornia` dependency in the requirements.txt file (breaks the canny node) but it is not recommended. + + You can also refer to [ComfyUI CLI](/comfy-cli/getting-started) to install ComfyUI, it is a command line tool that can easily install ComfyUI and manage its dependencies. ## Create a virtual environment @@ -26,7 +25,14 @@ You can also refer to [ComfyUI CLI](/comfy-cli/getting-started) to install Comfy Independent virtual environments are necessary because ComfyUI's dependencies may conflict with other dependencies on the system, and it can also avoid polluting the system-level Python environment. - +[Install Miniconda](https://docs.anaconda.com/free/miniconda/index.html#latest-miniconda-installer-links). This will help you install the correct versions of Python and other libraries needed by ComfyUI. + +Create an environment with Conda. + +``` +conda create -n comfyenv +conda activate comfyenv +``` ## Clone the ComfyUI code repository @@ -51,13 +57,162 @@ git clone git@github.com:comfyanonymous/ComfyUI.git - + Install GPU Dependencies + + +Nvidia users should install stable pytorch using this command: + +```bash +pip install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cu130 +``` + +Alternatively, you can install the nightly version of PyTorch. + + +Install Nightly version (might be more risky) + +This is the command to install pytorch nightly instead which might have performance improvements: + +```bash +pip install --pre torch torchvision torchaudio --index-url https://download.pytorch.org/whl/nightly/cu130 +``` + + + +If you get the "Torch not compiled with CUDA enabled" error, uninstall torch with: + +```bash +pip uninstall torch +``` + +And install it again with the command above. + + + +AMD users can install rocm and pytorch with pip if you don't have it already installed, this is the command to install the stable version: + +```bash +pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/rocm6.4 +``` + +Alternatively, you can install the nightly version of PyTorch. + + +Install Nightly version (might be more risky) + +This is the command to install the nightly with ROCm 7.0 which might have some performance improvements: + +```bash +pip install --pre torch torchvision torchaudio --index-url https://download.pytorch.org/whl/nightly/rocm7.0 +``` + + + + +Experimental support for Windows and Linux. RDNA 3, 3.5 and 4 only. + +These have less hardware support than the builds above but they work on Windows. You also need to install the pytorch version specific to your hardware. + + +**RDNA 3 (RX 7000 series):** + +```bash +pip install --pre torch torchvision torchaudio --index-url https://rocm.nightlies.amd.com/v2/gfx110X-dgpu/ +``` + +**RDNA 3.5 (Strix halo/Ryzen AI Max+ 365):** + +```bash +pip install --pre torch torchvision torchaudio --index-url https://rocm.nightlies.amd.com/v2/gfx1151/ +``` + +**RDNA 4 (RX 9000 series):** + +```bash +pip install --pre torch torchvision torchaudio --index-url https://rocm.nightlies.amd.com/v2/gfx120X-all/ +``` + + +Intel Arc GPU users can install native PyTorch with torch.xpu support using pip. More information can be found [here](https://pytorch.org/docs/main/notes/get_start_xpu.html). + +**Option 1: Install PyTorch xpu** + +To install PyTorch xpu, use the following command: + +```bash +pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/xpu +``` + + +Install Nightly version (might be more risky) + +This is the command to install the Pytorch xpu nightly which might have some performance improvements: + +```bash +pip install --pre torch torchvision torchaudio --index-url https://download.pytorch.org/whl/nightly/xpu +``` + + +**Option 2: Intel Extension for PyTorch (IPEX)** + +Alternatively, Intel GPUs supported by Intel Extension for PyTorch (IPEX) can leverage IPEX for improved performance. + +Visit [Installation](https://intel.github.io/intel-extension-for-pytorch/index.html#installation?platform=gpu) for more information. + + +You can install ComfyUI in Apple Mac silicon (M1 or M2) with any recent macOS version. + +Install pytorch nightly. For instructions, read the [Accelerated PyTorch training on Mac](https://developer.apple.com/metal/pytorch/) Apple Developer guide (make sure to install the latest pytorch nightly). + +```bash +conda install pytorch-nightly::pytorch torchvision torchaudio -c pytorch-nightly +``` + + +Remember to add your models, VAE, LoRAs etc. to the corresponding Comfy folders (models/checkpoints, models/vae, etc.). + + + +For models compatible with Ascend Extension for PyTorch (torch_npu). To get started, ensure your environment meets the prerequisites outlined on the [installation](https://ascend.github.io/docs/sources/ascend/quick_install.html) page. + +**Step-by-step guide:** + +1. Begin by installing the recommended or newer kernel version for Linux as specified in the Installation page of torch-npu, if necessary. +2. Proceed with the installation of Ascend Basekit, which includes the driver, firmware, and CANN, following the instructions provided for your specific platform. +3. Next, install the necessary packages for torch-npu by adhering to the platform-specific instructions on the [Installation](https://ascend.github.io/docs/sources/pytorch/install.html#pytorch) page. +4. Finally, follow the ComfyUI manual installation guide for Linux. Once all components are installed, you can run ComfyUI as described earlier. + + +For models compatible with Cambricon Extension for PyTorch (torch_mlu). + +**Step-by-step guide:** + +1. Install the Cambricon CNToolkit by adhering to the platform-specific instructions on the [Installation](https://www.cambricon.com/docs/sdk_1.15.0/cntoolkit_3.7.2/cntoolkit_install_3.7.2/index.html) +2. Next, install the PyTorch(torch_mlu) following the instructions on the [Installation](https://www.cambricon.com/docs/sdk_1.15.0/cambricon_pytorch_1.17.0/user_guide_1.9/index.html) +3. Launch ComfyUI by running `python main.py` + + +For models compatible with Iluvatar Extension for PyTorch. + +**Step-by-step guide:** + +1. Install the Iluvatar Corex Toolkit by adhering to the platform-specific instructions on the [Installation](https://support.iluvatar.com/#/DocumentCentre?id=1&nameCenter=2&productId=520117912052801536) +2. Launch ComfyUI by running `python main.py` + - + ```bash +cd ComfyUI +pip install -r requirements.txt +``` - + Start the application + +``` +cd ComfyUI +python main.py +``` @@ -82,4 +237,182 @@ git clone git@github.com:comfyanonymous/ComfyUI.git - \ No newline at end of file +## Adding Extra Model Paths + +If you want to manage your model files outside of `ComfyUI/models`, you may have the following reasons: + +- You have multiple ComfyUI instances and want them to share model files to save disk space +- You have different types of GUI programs (such as WebUI) and want them to use the same model files +- Model files cannot be recognized or found + +We provide a way to add extra model search paths via the `extra_model_paths.yaml` configuration file + +### Open Config File + + + + For the ComfyUI version such as [portable](/installation/comfyui_portable_windows) and [manual](/installation/manual_install), you can find an example file named `extra_model_paths.yaml.example` in the root directory of ComfyUI: + ``` + ComfyUI/extra_model_paths.yaml.example + ``` + + Copy and rename it to `extra_model_paths.yaml` for use. Keep it in ComfyUI's root directory at `ComfyUI/extra_model_paths.yaml`. + You can also find the config example file [here](https://github.com/comfyanonymous/ComfyUI/blob/master/extra_model_paths.yaml.example) + + + + If you are using the [ComfyUI Desktop](/installation/desktop/windows) application, you can follow the image below to open the extra model config file: + + ![Open Config File](/images/desktop/extra_model_paths.jpg) + + Or open it directly at: + + + + ``` + C:\Users\YourUsername\AppData\Roaming\ComfyUI\extra_models_config.yaml + ``` + + + ``` + ~/Library/Application Support/ComfyUI/extra_models_config.yaml + ``` + + + + You should keep the file in the same directory, should not move these files to other places. + + + +If the file does not exist, you can create it yourself with any text editor. + +### Example Structure + +Suppose you want to add the following model paths to ComfyUI: + +``` +📁 YOUR_PATH/ + ├── 📁models/ + | ├── 📁 lora/ + | │ └── xxxxx.safetensors + | ├── 📁 checkpoints/ + | │ └── xxxxx.safetensors + | ├── 📁 vae/ + | │ └── xxxxx.safetensors + | └── 📁 controlnet/ + | └── xxxxx.safetensors +``` + +Then you can configure the `extra_model_paths.yaml` file like below to let ComfyUI recognize the model paths on your device: + +``` +my_custom_config: + base_path: YOUR_PATH + loras: models/loras/ + checkpoints: models/checkpoints/ + vae: models/vae/ + controlnet: models/controlnet/ +``` +or + +``` +my_custom_config: + base_path: YOUR_PATH/models/ + loras: loras + checkpoints: checkpoints + vae: vae + controlnet: controlnet +``` + + + For the desktop version, please add the configuration to the existing configuration path without overwriting the path configuration generated during installation. Please back up the corresponding file before modification, so that you can restore it when you make a mistake. + + +Or you can refer to the default [extra_model_paths.yaml.example](https://github.com/comfyanonymous/ComfyUI/blob/master/extra_model_paths.yaml.example) for more configuration options. After saving, you need to **restart ComfyUI** for the changes to take effect. + +Below is the original config example: + +```yaml +#Rename this to extra_model_paths.yaml and ComfyUI will load it + + +#config for a1111 ui +#all you have to do is change the base_path to where yours is installed +a111: + base_path: path/to/stable-diffusion-webui/ + + checkpoints: models/Stable-diffusion + configs: models/Stable-diffusion + vae: models/VAE + loras: | + models/Lora + models/LyCORIS + upscale_models: | + models/ESRGAN + models/RealESRGAN + models/SwinIR + embeddings: embeddings + hypernetworks: models/hypernetworks + controlnet: models/ControlNet + +#config for comfyui +#your base path should be either an existing comfy install or a central folder where you store all of your models, loras, etc. + +#comfyui: +# base_path: path/to/comfyui/ +# # You can use is_default to mark that these folders should be listed first, and used as the default dirs for eg downloads +# #is_default: true +# checkpoints: models/checkpoints/ +# clip: models/clip/ +# clip_vision: models/clip_vision/ +# configs: models/configs/ +# controlnet: models/controlnet/ +# diffusion_models: | +# models/diffusion_models +# models/unet +# embeddings: models/embeddings/ +# loras: models/loras/ +# upscale_models: models/upscale_models/ +# vae: models/vae/ + +#other_ui: +# base_path: path/to/ui +# checkpoints: models/checkpoints +# gligen: models/gligen +# custom_nodes: path/custom_nodes + +``` + +For example, if your WebUI is located at `D:\stable-diffusion-webui\`, you can modify the corresponding configuration to +```yaml +a111: + base_path: D:\stable-diffusion-webui\ + checkpoints: models/Stable-diffusion + configs: models/Stable-diffusion + vae: models/VAE + loras: | + models/Lora + models/LyCORIS + upscale_models: | + models/ESRGAN + models/RealESRGAN + models/SwinIR + embeddings: embeddings + hypernetworks: models/hypernetworks + controlnet: models/ControlNet +``` + +### Add Extra Custom Nodes Path + +Besides adding external models, you can also add custom nodes paths that are not in the default path of ComfyUI + + + Please note that this will not change the default installation path of custom nodes, but will add an extra path search when starting ComfyUI. You still need to complete the installation of custom node dependencies in the corresponding environment to ensure the integrity of the running environment. + + +Below is a simple configuration example (MacOS), please modify it according to your actual situation and add it to the corresponding configuration file, save it and restart ComfyUI for the changes to take effect: + +```yaml +my_custom_nodes: + custom_nodes: /Users/your_username/Documents/extra_custom_nodes +``` diff --git a/snippets/amd-install.mdx b/snippets/amd-install.mdx deleted file mode 100644 index 1d2dcbe1..00000000 --- a/snippets/amd-install.mdx +++ /dev/null @@ -1,12 +0,0 @@ -``` -pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/rocm6.0 -``` - -Alternatively, you can install the nightly version of PyTorch. - - -Install Nightly version (might be more risky) -``` -pip3 install --pre torch torchvision torchaudio --index-url https://download.pytorch.org/whl/nightly/rocm6.0 -``` - diff --git a/snippets/conda.mdx b/snippets/conda.mdx deleted file mode 100644 index bdb063be..00000000 --- a/snippets/conda.mdx +++ /dev/null @@ -1,8 +0,0 @@ -[Install Miniconda](https://docs.anaconda.com/free/miniconda/index.html#latest-miniconda-installer-links). This will help you install the correct versions of Python and other libraries needed by ComfyUI. - -Create an environment with Conda. - -``` -conda create -n comfyenv -conda activate comfyenv -``` diff --git a/snippets/git-clone.mdx b/snippets/git-clone.mdx deleted file mode 100644 index a1805546..00000000 --- a/snippets/git-clone.mdx +++ /dev/null @@ -1,5 +0,0 @@ -```bash -git clone git@github.com:comfyanonymous/ComfyUI.git -``` - -More [info](https://docs.github.com/en/repositories/creating-and-managing-repositories/cloning-a-repository) on git clone. diff --git a/snippets/install-gpu-dependencies.mdx b/snippets/install-gpu-dependencies.mdx deleted file mode 100644 index 2e63c43d..00000000 --- a/snippets/install-gpu-dependencies.mdx +++ /dev/null @@ -1,15 +0,0 @@ -import AmdInstall from "/snippets/amd-install.mdx"; -import NvidiaInstall from "/snippets/nvidia-install.mdx"; -import MacInstall from "/snippets/mac-silicon-install.mdx"; - -Install GPU Dependencies - - - - - - - - - - diff --git a/snippets/install/add-external-models.mdx b/snippets/install/add-external-models.mdx deleted file mode 100644 index 570e762d..00000000 --- a/snippets/install/add-external-models.mdx +++ /dev/null @@ -1,179 +0,0 @@ -## Adding Extra Model Paths - -If you want to manage your model files outside of `ComfyUI/models`, you may have the following reasons: - -- You have multiple ComfyUI instances and want them to share model files to save disk space -- You have different types of GUI programs (such as WebUI) and want them to use the same model files -- Model files cannot be recognized or found - -We provide a way to add extra model search paths via the `extra_model_paths.yaml` configuration file - -### Open Config File - - - - For the ComfyUI version such as [portable](/installation/comfyui_portable_windows) and [manual](/installation/manual_install), you can find an example file named `extra_model_paths.yaml.example` in the root directory of ComfyUI: - ``` - ComfyUI/extra_model_paths.yaml.example - ``` - - Copy and rename it to `extra_model_paths.yaml` for use. Keep it in ComfyUI's root directory at `ComfyUI/extra_model_paths.yaml`. - You can also find the config example file [here](https://github.com/comfyanonymous/ComfyUI/blob/master/extra_model_paths.yaml.example) - - - - If you are using the [ComfyUI Desktop](/installation/desktop/windows) application, you can follow the image below to open the extra model config file: - - ![Open Config File](/images/desktop/extra_model_paths.jpg) - - Or open it directly at: - - - - ``` - C:\Users\YourUsername\AppData\Roaming\ComfyUI\extra_models_config.yaml - ``` - - - ``` - ~/Library/Application Support/ComfyUI/extra_models_config.yaml - ``` - - - - You should keep the file in the same directory, should not move these files to other places. - - - -If the file does not exist, you can create it yourself with any text editor. - -### Example Structure - -Suppose you want to add the following model paths to ComfyUI: - -``` -📁 YOUR_PATH/ - ├── 📁models/ - | ├── 📁 lora/ - | │ └── xxxxx.safetensors - | ├── 📁 checkpoints/ - | │ └── xxxxx.safetensors - | ├── 📁 vae/ - | │ └── xxxxx.safetensors - | └── 📁 controlnet/ - | └── xxxxx.safetensors -``` - -Then you can configure the `extra_model_paths.yaml` file like below to let ComfyUI recognize the model paths on your device: - -``` -my_custom_config: - base_path: YOUR_PATH - loras: models/loras/ - checkpoints: models/checkpoints/ - vae: models/vae/ - controlnet: models/controlnet/ -``` -or - -``` -my_custom_config: - base_path: YOUR_PATH/models/ - loras: loras - checkpoints: checkpoints - vae: vae - controlnet: controlnet -``` - - - For the desktop version, please add the configuration to the existing configuration path without overwriting the path configuration generated during installation. Please back up the corresponding file before modification, so that you can restore it when you make a mistake. - - -Or you can refer to the default [extra_model_paths.yaml.example](https://github.com/comfyanonymous/ComfyUI/blob/master/extra_model_paths.yaml.example) for more configuration options. After saving, you need to **restart ComfyUI** for the changes to take effect. - -Below is the original config example: - -```yaml -#Rename this to extra_model_paths.yaml and ComfyUI will load it - - -#config for a1111 ui -#all you have to do is change the base_path to where yours is installed -a111: - base_path: path/to/stable-diffusion-webui/ - - checkpoints: models/Stable-diffusion - configs: models/Stable-diffusion - vae: models/VAE - loras: | - models/Lora - models/LyCORIS - upscale_models: | - models/ESRGAN - models/RealESRGAN - models/SwinIR - embeddings: embeddings - hypernetworks: models/hypernetworks - controlnet: models/ControlNet - -#config for comfyui -#your base path should be either an existing comfy install or a central folder where you store all of your models, loras, etc. - -#comfyui: -# base_path: path/to/comfyui/ -# # You can use is_default to mark that these folders should be listed first, and used as the default dirs for eg downloads -# #is_default: true -# checkpoints: models/checkpoints/ -# clip: models/clip/ -# clip_vision: models/clip_vision/ -# configs: models/configs/ -# controlnet: models/controlnet/ -# diffusion_models: | -# models/diffusion_models -# models/unet -# embeddings: models/embeddings/ -# loras: models/loras/ -# upscale_models: models/upscale_models/ -# vae: models/vae/ - -#other_ui: -# base_path: path/to/ui -# checkpoints: models/checkpoints -# gligen: models/gligen -# custom_nodes: path/custom_nodes - -``` - -For example, if your WebUI is located at `D:\stable-diffusion-webui\`, you can modify the corresponding configuration to -```yaml -a111: - base_path: D:\stable-diffusion-webui\ - checkpoints: models/Stable-diffusion - configs: models/Stable-diffusion - vae: models/VAE - loras: | - models/Lora - models/LyCORIS - upscale_models: | - models/ESRGAN - models/RealESRGAN - models/SwinIR - embeddings: embeddings - hypernetworks: models/hypernetworks - controlnet: models/ControlNet -``` - -### Add Extra Custom Nodes Path - -Besides adding external models, you can also add custom nodes paths that are not in the default path of ComfyUI - - - Please note that this will not change the default installation path of custom nodes, but will add an extra path search when starting ComfyUI. You still need to complete the installation of custom node dependencies in the corresponding environment to ensure the integrity of the running environment. - - -Below is a simple configuration example (MacOS), please modify it according to your actual situation and add it to the corresponding configuration file, save it and restart ComfyUI for the changes to take effect: - -```yaml -my_custom_nodes: - custom_nodes: /Users/your_username/Documents/extra_custom_nodes -``` \ No newline at end of file diff --git a/snippets/mac-silicon-install.mdx b/snippets/mac-silicon-install.mdx deleted file mode 100644 index 7b247626..00000000 --- a/snippets/mac-silicon-install.mdx +++ /dev/null @@ -1,3 +0,0 @@ -``` bash -conda install pytorch-nightly::pytorch torchvision torchaudio -c pytorch-nightly -``` \ No newline at end of file diff --git a/snippets/nvidia-install.mdx b/snippets/nvidia-install.mdx deleted file mode 100644 index 649ec826..00000000 --- a/snippets/nvidia-install.mdx +++ /dev/null @@ -1,12 +0,0 @@ -``` -conda install pytorch torchvision torchaudio pytorch-cuda=12.1 -c pytorch -c nvidia -``` - -Alternatively, you can install the nightly version of PyTorch. - - -Install Nightly version (might be more risky) -``` -conda install pytorch torchvision torchaudio pytorch-cuda=12.1 -c pytorch-nightly -c nvidia -``` - \ No newline at end of file diff --git a/snippets/pip-install.mdx b/snippets/pip-install.mdx deleted file mode 100644 index 81541078..00000000 --- a/snippets/pip-install.mdx +++ /dev/null @@ -1,4 +0,0 @@ -```bash -cd ComfyUI -pip install -r requirements.txt -``` diff --git a/snippets/run-comfy.mdx b/snippets/run-comfy.mdx deleted file mode 100644 index 1c3ef542..00000000 --- a/snippets/run-comfy.mdx +++ /dev/null @@ -1,6 +0,0 @@ -Start the application - -``` -cd ComfyUI -python main.py -``` diff --git a/snippets/zh/amd-install.mdx b/snippets/zh/amd-install.mdx deleted file mode 100644 index c8f5fa6e..00000000 --- a/snippets/zh/amd-install.mdx +++ /dev/null @@ -1,12 +0,0 @@ -``` -pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/rocm6.0 -``` - -或者，您可以安装 PyTorch 的夜间版本。 - - -安装夜间版本（可能风险更大） -``` -pip3 install --pre torch torchvision torchaudio --index-url https://download.pytorch.org/whl/nightly/rocm6.0 -``` - diff --git a/snippets/zh/conda.mdx b/snippets/zh/conda.mdx deleted file mode 100644 index 9147f72d..00000000 --- a/snippets/zh/conda.mdx +++ /dev/null @@ -1,8 +0,0 @@ -[Install Miniconda](https://docs.anaconda.com/free/miniconda/index.html#latest-miniconda-installer-links). 这将帮助您安装 ComfyUI 所需的正确版本的 Python 和其他库。 - -使用 Conda 创建一个环境。 - -``` -conda create -n comfyenv -conda activate comfyenv -``` diff --git a/snippets/zh/git-clone.mdx b/snippets/zh/git-clone.mdx deleted file mode 100644 index f13e55c1..00000000 --- a/snippets/zh/git-clone.mdx +++ /dev/null @@ -1,5 +0,0 @@ -```bash -git clone git@github.com:comfyanonymous/ComfyUI.git -``` - -更多关于[git clone](https://docs.github.com/en/repositories/creating-and-managing-repositories/cloning-a-repository) 的信息。 diff --git a/snippets/zh/iluvatar-install.mdx b/snippets/zh/iluvatar-install.mdx new file mode 100644 index 00000000..ace7b154 --- /dev/null +++ b/snippets/zh/iluvatar-install.mdx @@ -0,0 +1,6 @@ +适用于与 Iluvatar Extension for PyTorch 兼容的模型。 + +**分步指南：** + +1. 按照[安装页面](https://support.iluvatar.com/#/DocumentCentre?id=1&nameCenter=2&productId=520117912052801536)上的平台特定说明安装 Iluvatar Corex Toolkit +2. 通过运行 `python main.py` 启动 ComfyUI diff --git a/snippets/zh/install-gpu-dependencies.mdx b/snippets/zh/install-gpu-dependencies.mdx deleted file mode 100644 index 8e4277e4..00000000 --- a/snippets/zh/install-gpu-dependencies.mdx +++ /dev/null @@ -1,15 +0,0 @@ -import AmdInstall from "/snippets/zh/amd-install.mdx"; -import NvidiaInstall from "/snippets/zh/nvidia-install.mdx"; -import MacInstall from "/snippets/mac-silicon-install.mdx"; - -安装 GPU 依赖 - - - - - - - - - - diff --git a/snippets/zh/install/add-external-models.mdx b/snippets/zh/install/add-external-models.mdx deleted file mode 100644 index d9819b4e..00000000 --- a/snippets/zh/install/add-external-models.mdx +++ /dev/null @@ -1,158 +0,0 @@ -## 添加外部模型路径 - -如果你想要在 `ComfyUI/models` 之外管理你的模型文件，可能出于以下原因: - -- 你有多个 ComfyUI 实例，你想要让这些实例共享模型文件，从而减少磁盘占用 -- 你有多个不同的类型的 GUI 程序，如：WebUI, 你想要他们共用模型文件 -- 模型文件无法被识别或读取到 - -我们提供了通过 `extra_model_paths.yaml` 配置文件来添加额外模型搜索路径的方法。 - -### 不同 ComfyUI 版本配置文件位置 - - - - 对于[便携版](/zh-CN/installation/comfyui_portable_windows)和[手动安装](/zh-CN/installation/manual_install)的 ComfyUI版本，你可以在 ComfyUI 的根目录下找到 `extra_model_paths.yaml.example` 的示例文件 - ``` - ComfyUI/extra_model_paths.yaml.example - ``` - 复制并重命名为 `extra_model_paths.yaml` 来使用, 并保持在 ComfyUI 的根目录下, 路径应该是 `ComfyUI/extra_model_paths.yaml` - - 你也可以在 [这里](https://github.com/comfyanonymous/ComfyUI/blob/master/extra_model_paths.yaml.example) 找到配置示例文件 - - - - 如果你使用的是 ComfyUI 桌面应用程序，你可以参考下图打开额外模型的配置文件： - - ![Open Config File](/images/zh/desktop/extra_model_paths.jpg) - - 或者通过下面的位置打开： - - - - ``` - C:\Users\YourUsername\AppData\Roaming\ComfyUI\extra_models_config.yaml - ``` - - - ``` - ~/Library/Application Support/ComfyUI/extra_models_config.yaml - ``` - - - - 对应的配置文件不应该被改变 - - - -### 配置示例 - -比如，你需要额外让 ComfyUI 识别的模型文件位于下面的文件夹: - -``` -📁 YOUR_PATH/ - ├── 📁models/ - | ├── 📁 loras/ - | │ └── xxxxx.safetensors - | ├── 📁 checkpoints/ - | │ └── xxxxx.safetensors - | ├── 📁 vae/ - | │ └── xxxxx.safetensors - | └── 📁 controlnet/ - | └── xxxxx.safetensors -``` - -那么你可以进行如下的配置来让 ComfyUI 识别到你设备上的模型路径 - -``` -my_custom_config: - base_path: YOUR_PATH - loras: models/loras/ - checkpoints: models/checkpoints/ - vae: models/vae/ - controlnet: models/controlnet/ -``` - -或者使用 -``` -my_custom_config: - base_path: YOUR_PATH/models/ - loras: loras - checkpoints: checkpoints - vae: vae - controlnet: controlnet -``` - - - 对于桌面版，请在原有配置路径下新增配置，而不覆盖掉安装过程中自动生成的路径配置，请在修改前备份对应的文件，这样在你配置错误时可以及时恢复 - - -或者你也可以参考默认的 [extra_model_paths.yaml.example](https://github.com/comfyanonymous/ComfyUI/blob/master/extra_model_paths.yaml.example) 来配置，保存之后， 需要 **重启 ComfyUI** 才能生效。 - -下面是完整的原始的配置配置示例: - -```yaml -#Rename this to extra_model_paths.yaml and ComfyUI will load it - - -#config for a1111 ui -#all you have to do is change the base_path to where yours is installed -a111: - base_path: path/to/stable-diffusion-webui/ - - checkpoints: models/Stable-diffusion - configs: models/Stable-diffusion - vae: models/VAE - loras: | - models/Lora - models/LyCORIS - upscale_models: | - models/ESRGAN - models/RealESRGAN - models/SwinIR - embeddings: embeddings - hypernetworks: models/hypernetworks - controlnet: models/ControlNet - -#config for comfyui -#your base path should be either an existing comfy install or a central folder where you store all of your models, loras, etc. - -#comfyui: -# base_path: path/to/comfyui/ -# # You can use is_default to mark that these folders should be listed first, and used as the default dirs for eg downloads -# #is_default: true -# checkpoints: models/checkpoints/ -# clip: models/clip/ -# clip_vision: models/clip_vision/ -# configs: models/configs/ -# controlnet: models/controlnet/ -# diffusion_models: | -# models/diffusion_models -# models/unet -# embeddings: models/embeddings/ -# loras: models/loras/ -# upscale_models: models/upscale_models/ -# vae: models/vae/ - -#other_ui: -# base_path: path/to/ui -# checkpoints: models/checkpoints -# gligen: models/gligen -# custom_nodes: path/custom_nodes - -``` - -### 添加额外自定义节点路径 - -除了添加外部模型之外，你同样可以添加不在 ComfyUI 默认路径下的自定义节点路径 - - - 请注意，这并不会改变自定义节点的默认安装路径，只是在启动 ComfyUI 时会增加额外的路径搜索，你仍旧需要在对应的环境中完成自定义节点的依赖的安装，来保证其运行环境的完整性。 - - -下面是一个简单的配置示例（Mac 系统），请根据你的实际情况进行修改，并新增到对应的配置文件中，保存后需要 **重启 ComfyUI** 才能生效: - -```yaml -my_custom_nodes: - custom_nodes: /Users/your_username/Documents/extra_custom_nodes -``` \ No newline at end of file diff --git a/snippets/zh/mac-silicon-install.mdx b/snippets/zh/mac-silicon-install.mdx deleted file mode 100644 index 7b247626..00000000 --- a/snippets/zh/mac-silicon-install.mdx +++ /dev/null @@ -1,3 +0,0 @@ -``` bash -conda install pytorch-nightly::pytorch torchvision torchaudio -c pytorch-nightly -``` \ No newline at end of file diff --git a/snippets/zh/nvidia-install.mdx b/snippets/zh/nvidia-install.mdx deleted file mode 100644 index 13e33cb8..00000000 --- a/snippets/zh/nvidia-install.mdx +++ /dev/null @@ -1,12 +0,0 @@ -``` -conda install pytorch torchvision torchaudio pytorch-cuda=12.1 -c pytorch -c nvidia -``` - -或者，您可以安装 PyTorch 的夜间版本。 - - -安装夜间版本（可能风险更大） -``` -conda install pytorch torchvision torchaudio pytorch-cuda=12.1 -c pytorch-nightly -c nvidia -``` - \ No newline at end of file diff --git a/snippets/zh/pip-install.mdx b/snippets/zh/pip-install.mdx deleted file mode 100644 index 81541078..00000000 --- a/snippets/zh/pip-install.mdx +++ /dev/null @@ -1,4 +0,0 @@ -```bash -cd ComfyUI -pip install -r requirements.txt -``` diff --git a/snippets/zh/run-comfy.mdx b/snippets/zh/run-comfy.mdx deleted file mode 100644 index f4bb4e9e..00000000 --- a/snippets/zh/run-comfy.mdx +++ /dev/null @@ -1,6 +0,0 @@ -启动 ComfyUI - -``` -cd ComfyUI -python main.py -``` diff --git a/zh-CN/installation/manual_install.mdx b/zh-CN/installation/manual_install.mdx index dc007c88..a164456a 100644 --- a/zh-CN/installation/manual_install.mdx +++ b/zh-CN/installation/manual_install.mdx @@ -5,19 +5,18 @@ icon: "wrench" sidebarTitle: "手动安装" --- -import GitClone from "/snippets/zh/git-clone.mdx"; -import Conda from "/snippets/zh/conda.mdx"; -import PipInstall from "/snippets/zh/pip-install.mdx"; -import InstallGpuDependencies from "/snippets/zh/install-gpu-dependencies.mdx"; -import RunComfy from "/snippets/zh/run-comfy.mdx"; -import AddExternalModels from "/snippets/zh/install/add-external-models.mdx" - 对于 ComfyUI 的安装， 主要分为几个步骤 1. 创建一个虚拟环境(避免污染系统级 Python 环境) 2. 克隆 ComfyUI 代码仓库 3. 安装依赖 4. 启动 ComfyUI + +Python 3.13 支持非常好。如果你在 3.13 上遇到某些自定义节点依赖问题,可以尝试使用 3.12。 + +Python 3.14 可以工作，但需要在 requirements.txt 文件中注释掉 `kornia` 依赖（会导致 canny 节点失效），不建议使用。 + + 你也可以参考 [ComfyUI CLI](/zh-CN/comfy-cli/getting-started) 来安装 ComfyUI, 它是一个命令行工具，可以方便地安装 ComfyUI 并管理其依赖。 ## （可选）创建虚拟环境 @@ -25,7 +24,15 @@ import AddExternalModels from "/snippets/zh/install/add-external-models.mdx" 独立的虚拟环境是必要的，因为 ComfyUI 的依赖可能会与系统上的其他依赖冲突，也可以避免对系统级 Python 环境的污染。 - + +[Install Miniconda](https://docs.anaconda.com/free/miniconda/index.html#latest-miniconda-installer-links). 这将帮助您安装 ComfyUI 所需的正确版本的 Python 和其他库。 + +使用 Conda 创建一个环境。 + +``` +conda create -n comfyenv +conda activate comfyenv +``` ## 克隆代码仓库 @@ -51,13 +58,162 @@ git clone git@github.com:comfyanonymous/ComfyUI.git ## 安装GPU 及 ComfyUI 依赖 - + 安装 GPU 依赖 + + +Nvidia 用户应使用以下命令安装稳定版 pytorch： + +```bash +pip install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cu130 +``` + +或者，您可以安装 PyTorch 的夜间版本。 + + +安装夜间版本（可能风险更大） + +这是安装 pytorch 夜间版本的命令，可能会有一些性能改进： + +```bash +pip install --pre torch torchvision torchaudio --index-url https://download.pytorch.org/whl/nightly/cu130 +``` + + + +如果您遇到 "Torch not compiled with CUDA enabled" 错误，请使用以下命令卸载 torch： + +```bash +pip uninstall torch +``` + +然后使用上述命令重新安装。 + + + +AMD 用户可以使用 pip 安装 rocm 和 pytorch（如果尚未安装），这是安装稳定版本的命令： + +```bash +pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/rocm6.4 +``` + +或者，您可以安装 PyTorch 的夜间版本。 + + +安装夜间版本（可能风险更大） + +这是安装 ROCm 7.0 夜间版本的命令，可能会有一些性能改进： + +```bash +pip install --pre torch torchvision torchaudio --index-url https://download.pytorch.org/whl/nightly/rocm7.0 +``` + + + + +Windows 和 Linux 的实验性支持。仅支持 RDNA 3、3.5 和 4。 + +这些版本的硬件支持比上述版本少，但它们可以在 Windows 上运行。您还需要安装特定于您硬件的 PyTorch 版本。 + + +**RDNA 3 (RX 7000 系列):** + +```bash +pip install --pre torch torchvision torchaudio --index-url https://rocm.nightlies.amd.com/v2/gfx110X-dgpu/ +``` + +**RDNA 3.5 (Strix halo/Ryzen AI Max+ 365):** + +```bash +pip install --pre torch torchvision torchaudio --index-url https://rocm.nightlies.amd.com/v2/gfx1151/ +``` + +**RDNA 4 (RX 9000 系列):** + +```bash +pip install --pre torch torchvision torchaudio --index-url https://rocm.nightlies.amd.com/v2/gfx120X-all/ +``` + + +Intel Arc GPU 用户可以使用 pip 安装支持 torch.xpu 的原生 PyTorch。更多信息可以在[这里](https://pytorch.org/docs/main/notes/get_start_xpu.html)找到。 + +**选项 1: 安装 PyTorch xpu** + +要安装 PyTorch xpu，请使用以下命令： + +```bash +pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/xpu +``` + + +安装夜间版本（可能风险更大） + +这是安装 PyTorch xpu 夜间版本的命令，可能会有一些性能改进： + +```bash +pip install --pre torch torchvision torchaudio --index-url https://download.pytorch.org/whl/nightly/xpu +``` + + +**选项 2: Intel Extension for PyTorch (IPEX)** + +或者，Intel Extension for PyTorch (IPEX) 支持的 Intel GPU 可以利用 IPEX 来提高性能。 + +访问[安装页面](https://intel.github.io/intel-extension-for-pytorch/index.html#installation?platform=gpu)了解更多信息。 + + +您可以在任何最新的 macOS 版本上的 Apple Mac silicon（M1 或 M2）中安装 ComfyUI。 + +安装 pytorch nightly。有关说明，请阅读 [Accelerated PyTorch training on Mac](https://developer.apple.com/metal/pytorch/) Apple Developer 指南（确保安装最新的 pytorch nightly）。 + +```bash +conda install pytorch-nightly::pytorch torchvision torchaudio -c pytorch-nightly +``` + + +记得将您的模型、VAE、LoRA 等添加到相应的 Comfy 文件夹（models/checkpoints、models/vae 等）。 + + + +适用于与 Ascend Extension for PyTorch (torch_npu) 兼容的模型。要开始使用，请确保您的环境满足[安装页面](https://ascend.github.io/docs/sources/ascend/quick_install.html)上列出的先决条件。 + +**分步指南：** + +1. 首先，如有必要，按照 torch-npu 安装页面中指定的要求，为 Linux 安装推荐或更新的内核版本。 +2. 继续安装 Ascend Basekit，其中包括驱动程序、固件和 CANN，按照您特定平台的说明进行操作。 +3. 接下来，按照[安装页面](https://ascend.github.io/docs/sources/pytorch/install.html#pytorch)上的平台特定说明安装 torch-npu 所需的软件包。 +4. 最后，按照 Linux 的 ComfyUI 手动安装指南进行操作。安装所有组件后，您可以按照前面所述运行 ComfyUI。 + + +适用于与 Cambricon Extension for PyTorch (torch_mlu) 兼容的模型。 + +**分步指南：** + +1. 按照[安装页面](https://www.cambricon.com/docs/sdk_1.15.0/cntoolkit_3.7.2/cntoolkit_install_3.7.2/index.html)上的平台特定说明安装 Cambricon CNToolkit +2. 接下来，按照[安装页面](https://www.cambricon.com/docs/sdk_1.15.0/cambricon_pytorch_1.17.0/user_guide_1.9/index.html)上的说明安装 PyTorch(torch_mlu) +3. 通过运行 `python main.py` 启动 ComfyUI + + +适用于与 Iluvatar Extension for PyTorch 兼容的模型。 + +**分步指南：** + +1. 按照[安装页面](https://support.iluvatar.com/#/DocumentCentre?id=1&nameCenter=2&productId=520117912052801536)上的平台特定说明安装 Iluvatar Corex Toolkit +2. 通过运行 `python main.py` 启动 ComfyUI + - + ```bash +cd ComfyUI +pip install -r requirements.txt +``` - + 启动 ComfyUI + +``` +cd ComfyUI +python main.py +``` @@ -82,4 +238,161 @@ git clone git@github.com:comfyanonymous/ComfyUI.git - \ No newline at end of file +## 添加外部模型路径 + +如果你想要在 `ComfyUI/models` 之外管理你的模型文件，可能出于以下原因: + +- 你有多个 ComfyUI 实例，你想要让这些实例共享模型文件，从而减少磁盘占用 +- 你有多个不同的类型的 GUI 程序，如：WebUI, 你想要他们共用模型文件 +- 模型文件无法被识别或读取到 + +我们提供了通过 `extra_model_paths.yaml` 配置文件来添加额外模型搜索路径的方法。 + +### 不同 ComfyUI 版本配置文件位置 + + + + 对于[便携版](/zh-CN/installation/comfyui_portable_windows)和[手动安装](/zh-CN/installation/manual_install)的 ComfyUI版本，你可以在 ComfyUI 的根目录下找到 `extra_model_paths.yaml.example` 的示例文件 + ``` + ComfyUI/extra_model_paths.yaml.example + ``` + 复制并重命名为 `extra_model_paths.yaml` 来使用, 并保持在 ComfyUI 的根目录下, 路径应该是 `ComfyUI/extra_model_paths.yaml` + + 你也可以在 [这里](https://github.com/comfyanonymous/ComfyUI/blob/master/extra_model_paths.yaml.example) 找到配置示例文件 + + + + 如果你使用的是 ComfyUI 桌面应用程序，你可以参考下图打开额外模型的配置文件： + + ![Open Config File](/images/zh/desktop/extra_model_paths.jpg) + + 或者通过下面的位置打开： + + + + ``` + C:\Users\YourUsername\AppData\Roaming\ComfyUI\extra_models_config.yaml + ``` + + + ``` + ~/Library/Application Support/ComfyUI/extra_models_config.yaml + ``` + + + + 对应的配置文件不应该被改变 + + + +### 配置示例 + +比如，你需要额外让 ComfyUI 识别的模型文件位于下面的文件夹: + +``` +📁 YOUR_PATH/ + ├── 📁models/ + | ├── 📁 loras/ + | │ └── xxxxx.safetensors + | ├── 📁 checkpoints/ + | │ └── xxxxx.safetensors + | ├── 📁 vae/ + | │ └── xxxxx.safetensors + | └── 📁 controlnet/ + | └── xxxxx.safetensors +``` + +那么你可以进行如下的配置来让 ComfyUI 识别到你设备上的模型路径 + +``` +my_custom_config: + base_path: YOUR_PATH + loras: models/loras/ + checkpoints: models/checkpoints/ + vae: models/vae/ + controlnet: models/controlnet/ +``` + +或者使用 +``` +my_custom_config: + base_path: YOUR_PATH/models/ + loras: loras + checkpoints: checkpoints + vae: vae + controlnet: controlnet +``` + + + 对于桌面版，请在原有配置路径下新增配置，而不覆盖掉安装过程中自动生成的路径配置，请在修改前备份对应的文件，这样在你配置错误时可以及时恢复 + + +或者你也可以参考默认的 [extra_model_paths.yaml.example](https://github.com/comfyanonymous/ComfyUI/blob/master/extra_model_paths.yaml.example) 来配置，保存之后， 需要 **重启 ComfyUI** 才能生效。 + +下面是完整的原始的配置配置示例: + +```yaml +#Rename this to extra_model_paths.yaml and ComfyUI will load it + + +#config for a1111 ui +#all you have to do is change the base_path to where yours is installed +a111: + base_path: path/to/stable-diffusion-webui/ + + checkpoints: models/Stable-diffusion + configs: models/Stable-diffusion + vae: models/VAE + loras: | + models/Lora + models/LyCORIS + upscale_models: | + models/ESRGAN + models/RealESRGAN + models/SwinIR + embeddings: embeddings + hypernetworks: models/hypernetworks + controlnet: models/ControlNet + +#config for comfyui +#your base path should be either an existing comfy install or a central folder where you store all of your models, loras, etc. + +#comfyui: +# base_path: path/to/comfyui/ +# # You can use is_default to mark that these folders should be listed first, and used as the default dirs for eg downloads +# #is_default: true +# checkpoints: models/checkpoints/ +# clip: models/clip/ +# clip_vision: models/clip_vision/ +# configs: models/configs/ +# controlnet: models/controlnet/ +# diffusion_models: | +# models/diffusion_models +# models/unet +# embeddings: models/embeddings/ +# loras: models/loras/ +# upscale_models: models/upscale_models/ +# vae: models/vae/ + +#other_ui: +# base_path: path/to/ui +# checkpoints: models/checkpoints +# gligen: models/gligen +# custom_nodes: path/custom_nodes + +``` + +### 添加额外自定义节点路径 + +除了添加外部模型之外，你同样可以添加不在 ComfyUI 默认路径下的自定义节点路径 + + + 请注意，这并不会改变自定义节点的默认安装路径，只是在启动 ComfyUI 时会增加额外的路径搜索，你仍旧需要在对应的环境中完成自定义节点的依赖的安装，来保证其运行环境的完整性。 + + +下面是一个简单的配置示例（Mac 系统），请根据你的实际情况进行修改，并新增到对应的配置文件中，保存后需要 **重启 ComfyUI** 才能生效: + +```yaml +my_custom_nodes: + custom_nodes: /Users/your_username/Documents/extra_custom_nodes +```