diff --git a/CMakeLists.txt b/CMakeLists.txt new file mode 100644 index 00000000000..2f659f0f1dd --- /dev/null +++ b/CMakeLists.txt @@ -0,0 +1 @@ +rocm_setup_version(VERSION 0.18.2) diff --git a/amd-docs/.readthedocs.yaml b/amd-docs/.readthedocs.yaml new file mode 100644 index 00000000000..7952df64526 --- /dev/null +++ b/amd-docs/.readthedocs.yaml @@ -0,0 +1,21 @@ +# Read the Docs configuration file +# See https://docs.readthedocs.io/en/stable/config-file/v2.html for details + +version: 2 + +sphinx: + configuration: amd-docs/conf.py + +# RTD by default builds html only +# Additional formats available for extra build time: htmlzip, pdf, epub +formats: [] + +python: + install: + - requirements: amd-docs/sphinx/requirements.txt + +# Defines build environment +build: + os: ubuntu-24.04 + tools: + python: "3.12" diff --git a/amd-docs/about/license.rst b/amd-docs/about/license.rst new file mode 100644 index 00000000000..4b289a4e677 --- /dev/null +++ b/amd-docs/about/license.rst @@ -0,0 +1,12 @@ +.. meta:: + :description: ComfyUI license + :keywords: ComfyUI, ROCm, developer, reference, agent + +.. _license: + +****************************************** +License +****************************************** + +.. include:: ../../LICENSE + :literal: \ No newline at end of file diff --git a/amd-docs/conf.py b/amd-docs/conf.py new file mode 100644 index 00000000000..71d462b9b84 --- /dev/null +++ b/amd-docs/conf.py @@ -0,0 +1,58 @@ +# Configuration file for the Sphinx documentation builder. +# +# This file only contains a selection of the most common options. For a full +# list see the documentation: +# https://www.sphinx-doc.org/en/master/usage/configuration.html + +import re + +''' +html_theme is usually unchanged (rocm_docs_theme). +flavor defines the site header display, select the flavor for the corresponding portals +flavor options: rocm, rocm-docs-home, rocm-blogs, rocm-ds, instinct, ai-developer-hub, local, generic +''' +html_theme = "rocm_docs_theme" +html_theme_options = {"flavor": "rocm-llmext", "repository_url": "https://github.com/AMD-Ecosystem/comfyui/"} + +''' +docs_header_version is used to manually configure the version in the header. If +there exists a non-null value mapped to docs_header_version, then the header in +the documentation page will contain the given version string. +''' +html_context = { + "docs_header_version": "26.04" +} + + +# This section turns on/off article info +setting_all_article_info = True +all_article_info_os = ["linux"] +all_article_info_author = "" + +# Dynamically extract component version +with open('../CMakeLists.txt', encoding='utf-8') as f: + pattern = r'.*\brocm_setup_version\(VERSION\s+([0-9A-Za-z._-]+)' # Update according to each component's CMakeLists.txt + match = re.search(pattern, + f.read()) + if not match: + raise ValueError("VERSION not found!") + version_number = match[1] + +# for PDF output on Read the Docs +project = "ComfyUI" +author = "Advanced Micro Devices, Inc." +copyright = "Copyright (c) 2026 Advanced Micro Devices, Inc. All rights reserved." +version = version_number +release = version_number + +external_toc_path = "./sphinx/_toc.yml" # Defines Table of Content structure definition path + +# Add more addtional package accordingly +extensions = [ + "rocm_docs", + "sphinx.ext.autodoc", # for Python docstrings +] + +html_title = f"{project} {version_number} documentation" + +external_projects_current_project = "ComfyUI" diff --git a/amd-docs/how-to/download-models.rst b/amd-docs/how-to/download-models.rst new file mode 100644 index 00000000000..21bf3809846 --- /dev/null +++ b/amd-docs/how-to/download-models.rst @@ -0,0 +1,50 @@ +.. meta:: + :description: Download models for ComfyUI + :keywords: ComfyUI, programming, agent, ROCm, example, sample, tutorial + +.. _comfyui-download-models: + +******************************************************************** +Download and use models in ComfyUI +******************************************************************** + +ComfyUI makes it easy to use models and build both simple and complex workflows with them. +However, you must first download the models you want to use. While you can download models directly from the UI, +the simplest and most stable method is to download them from a model repository (such as +`Hugging Face `__ or `Civitai `__) +using command-line tools like ``curl``. + +When downloading models through the command line, ensure you save them to the directories expected by ComfyUI: + +* ``$COMFYUI_PATH/models/diffusion_models`` for diffusion models +* ``$COMFYUI_PATH/models/unet`` for UNet models +* ``$COMFYUI_PATH/models/vae`` for VAE models +* ``$COMFYUI_PATH/models/text_encoders`` for text encoders +* ``$COMFYUI_PATH/models/clip`` for CLIP models +* ``$COMFYUI_PATH/models/checkpoints`` for model checkpoints + +Saving models to these directories makes it possible to use them in the standard ComfyUI nodes. + +Download custom nodes +==================================================================== + +ComfyUI comes with a rich library of nodes and templates. Additionally, a vast community builds custom nodes that you can import and install in two ways: from the command line or using the ComfyUI Manager. + +Command line installation +-------------------------------------------------------------------- + +To install nodes from the command line, clone a custom node repository into the ``custom_nodes`` directory and optionally install the dependencies: + +.. code-block:: bash + + git clone $COMFYUI_PATH/custom_nodes/ + pip install -r $COMFYUI_PATH/custom_nodes//requirements.txt + +.. note:: + + For newly installed nodes to appear in the UI, ensure you restart the server. + +ComfyUI Manager installation +-------------------------------------------------------------------- + +Installing nodes with the ComfyUI Manager is done directly in the UI. Select the custom nodes to install from the navigator and restart the server. \ No newline at end of file diff --git a/amd-docs/how-to/hunyuan3d-workflow.rst b/amd-docs/how-to/hunyuan3d-workflow.rst new file mode 100644 index 00000000000..0cc816f482e --- /dev/null +++ b/amd-docs/how-to/hunyuan3d-workflow.rst @@ -0,0 +1,52 @@ +.. meta:: + :description: ComfyUI example: Hunyuan3D 2.1 workflow + :keywords: ComfyUI, programming, agent, ROCm, example, sample, tutorial + +.. _run-comfyui-hunyuan-3d: + +******************************************************************** +Run the Hunyuan3D 2.1 template in ComfyUI +******************************************************************** + +`Hunyuan3D `__ is an open-source 3D asset generation model released by Tencent, +capable of generating high-fidelity 3D models with high-resolution texture maps through text or images. + +Hunyuan3D 2.1 is Tencent's 3D asset generation system that turns single images into +production-ready 3D models with physically-based rendering (PBR) materials. This release +includes improved texture quality with finer surface details and enhanced three-dimensional depth perception. + +Setup +==================================================================== + +To run this workflow: + +1. Follow the :ref:`comfyui-on-rocm-installation` steps to set up the ComfyUI environment and launch the ComfyUI WebUI. + +2. Select **Template** from the navigation panel on the left and search for **Hunyuan 3D 2.1**. + + .. image:: ../images/hunyuan3d-workflow-01.png + :alt: Template selection + +3. Double-click on **Hunyuan3D 2.1** template. + +4. Drag and drop an input image into the **Step 2 - Upload image here** node. + + Example image: https://comfyanonymous.github.io/ComfyUI_examples/hunyuan_image/hunyuan_image_example.png + + .. image:: ../images/hunyuan3d-workflow-02.png + :alt: Upload image step + +5. Click **Run**. + +Modify resolution configuration +-------------------------------------------------------------------- + +To modify input resolution, edit the **resolution** option in the **Empty LaternHunyuan3Dv2** node. + +Additional resources +-------------------------------------------------------------------- + +- `ComfyUI Hunyuan3D-2 Examples `__ +- `Hunyuan 3D Models `__ + + diff --git a/amd-docs/how-to/wan-inference-workflow.rst b/amd-docs/how-to/wan-inference-workflow.rst new file mode 100644 index 00000000000..0227e1ebbd5 --- /dev/null +++ b/amd-docs/how-to/wan-inference-workflow.rst @@ -0,0 +1,56 @@ +.. meta:: + :description: ComfyUI example: Wan 2.2 inference workflow + :keywords: ComfyUI, programming, agent, ROCm, example, sample, tutorial + +.. _run-comfyui-wan-inference: + +*************************************************************************** +Run the Wan 2.2 inference template in ComfyUI +*************************************************************************** + +`Wan 2.2 `__ is an advanced AI +video generation model capable of producing high-resolution videos from text +descriptions or input images. With support for various aspect ratios and +customizable generation parameters, Wan 2.2 enables creative video synthesis +for a wide range of applications. + +Setup +==================================================================== + +To run this workflow: + +1. Follow the :ref:`comfyui-on-rocm-installation` steps to set up the ComfyUI environment and launch the ComfyUI WebUI. + +2. Select **Template** from the navigation panel on the left and search for the **Wan 2.2 14B Text to Video** template. + + .. figure:: ../images/wan22-templates-video.png + :align: center + :alt: ComfyUI Templates library with Video selected and the Wan 2.2 14B Text to Video card + + **Templates → Video:** under *Generation type*, choose **Video**, then open the **Wan 2.2 14B Text to Video** template (for example, double-click the card). + +3. Once the template is loaded, click **Run** to execute the workflow. + + +Trigger a run +-------------------------------------------------------------------- + +To trigger a run, enter prompts in the **CLIP Text Encode** nodes for positive and negative prompts, then click **Run**. + +.. figure:: ../images/wan22-workflow-canvas.png + :align: center + :alt: Wan 2.2 workflow graph with CLIP Text Encode nodes and the Run control + + **Loaded workflow:** set positive and negative text in the **CLIP Text Encode** nodes, then use the blue **Run** button (top right). + Model loaders and other nodes follow the template layout (for example, **Wan2.2 T2V fp8_scaled**). + +You can see workflow progress at the top of the UI in the green progress bar near the top of the browser. + + +Additional resources +-------------------------------------------------------------------- + +- `ComfyUI Wan 2.2 Documentation `__ +- `Wan 2.2 Model Files (HuggingFace) `__ + + diff --git a/amd-docs/images/chroma1-radiance-tti-card.png b/amd-docs/images/chroma1-radiance-tti-card.png new file mode 100644 index 00000000000..bf2cd8b2117 Binary files /dev/null and b/amd-docs/images/chroma1-radiance-tti-card.png differ diff --git a/amd-docs/images/chroma1-radiance-tti-missing-models.png b/amd-docs/images/chroma1-radiance-tti-missing-models.png new file mode 100644 index 00000000000..c37fbfbfefe Binary files /dev/null and b/amd-docs/images/chroma1-radiance-tti-missing-models.png differ diff --git a/amd-docs/images/comfyui-main.png b/amd-docs/images/comfyui-main.png new file mode 100644 index 00000000000..00a487e1a95 Binary files /dev/null and b/amd-docs/images/comfyui-main.png differ diff --git a/amd-docs/images/hunyuan3d-workflow-01.png b/amd-docs/images/hunyuan3d-workflow-01.png new file mode 100644 index 00000000000..75296083044 Binary files /dev/null and b/amd-docs/images/hunyuan3d-workflow-01.png differ diff --git a/amd-docs/images/hunyuan3d-workflow-02.png b/amd-docs/images/hunyuan3d-workflow-02.png new file mode 100644 index 00000000000..48d32b9ee47 Binary files /dev/null and b/amd-docs/images/hunyuan3d-workflow-02.png differ diff --git a/amd-docs/images/sd3_5-missing-models.png b/amd-docs/images/sd3_5-missing-models.png new file mode 100644 index 00000000000..7a280e645f8 Binary files /dev/null and b/amd-docs/images/sd3_5-missing-models.png differ diff --git a/amd-docs/images/sd3_5-simple-card.png b/amd-docs/images/sd3_5-simple-card.png new file mode 100644 index 00000000000..6e513a6c1e7 Binary files /dev/null and b/amd-docs/images/sd3_5-simple-card.png differ diff --git a/amd-docs/images/wan22-templates-video.png b/amd-docs/images/wan22-templates-video.png new file mode 100644 index 00000000000..69af9a33aaa Binary files /dev/null and b/amd-docs/images/wan22-templates-video.png differ diff --git a/amd-docs/images/wan22-workflow-canvas.png b/amd-docs/images/wan22-workflow-canvas.png new file mode 100644 index 00000000000..41a50875581 Binary files /dev/null and b/amd-docs/images/wan22-workflow-canvas.png differ diff --git a/amd-docs/index.rst b/amd-docs/index.rst new file mode 100644 index 00000000000..c06fe69fe69 --- /dev/null +++ b/amd-docs/index.rst @@ -0,0 +1,46 @@ +.. meta:: + :description: ComfyUI documentation + :keywords: ComfyUI, ROCm, documentation, agent, GPU + +.. _comfyui-documentation-index: + +******************************************************************** +ComfyUI on ROCm documentation +******************************************************************** + +While you can build workflows for generative AI tasks purely in code, the growing interest in GenAI +has led to increased demand for tools that don't require extensive programming knowledge. +ComfyUI provides you with a simple drag-and-drop interface for building GenAI workflows. +This guide will cover what ComfyUI is and how you can get it running on AMD Instinct GPUs. + +`ComfyUI `__ is an open-source, +node-based interface for building and running image generation workflows with +diffusion models such as Stable Diffusion. Its modular graph-based design lets +you construct, customize, and share complex pipelines without writing code. + +ComfyUI is part of the `AMD LLM Extension toolkit +`__. + +The ComfyUI public repository is located at `https://github.com/AMD-Ecosystem/ComfyUI/tree/release/0.18.2.amd0 `__. + +.. grid:: 2 + :gutter: 3 + + .. grid-item-card:: Install + + * :doc:`Install ComfyUI ` + + .. grid-item-card:: How to + + * :doc:`Download and use models in ComfyUI ` + * :doc:`Run the Hunyuan3D 2.1 template in ComfyUI ` + * :doc:`Run the Wan 2.2 inference template in ComfyUI ` + + .. grid-item-card:: Reference + + * `Overview and reference documentation (upstream) `__ + +To contribute to the documentation, refer to +`Contributing to ComfyUI `__. + +You can find licensing information on the :doc:`Licensing ` page. diff --git a/amd-docs/install/comfyui-install.rst b/amd-docs/install/comfyui-install.rst new file mode 100644 index 00000000000..d1f62279306 --- /dev/null +++ b/amd-docs/install/comfyui-install.rst @@ -0,0 +1,239 @@ +.. meta:: + :description: installing ComfyUI for ROCm + :keywords: installation instructions, Docker, AMD, ROCm, ComfyUI + +.. _comfyui-on-rocm-installation: + +******************************************************************** +ComfyUI on ROCm installation +******************************************************************** + +This topic covers setup and installation instructions to help you get started running ComfyUI. + +System requirements +==================================================================== + +To use ComfyUI `0.18.2 `__, you need the following prerequisites: + +- **ROCm version:** `7.2.0 `__, `7.1.0 `__ +- **Operating system:** Ubuntu 24.04, 22.04 +- **GPU platform:** AMD Instinct™ MI355X, MI325X, MI300X +- **PyTorch:** `2.10.0a0+git449b176 `__ +- **Python:** `3.12 `__ + +Install ComfyUI +================================================================================ + +To install ComfyUI on ROCm, you have the following options: + +* :ref:`using-docker-with-comfyui-pre-installed` **(recommended)** +* :ref:`build-comfyui-rocm-docker-image` + +After setting up the container with either option, follow the common step to launch the ComfyUI server. + +.. _using-docker-with-comfyui-pre-installed: + +Use a prebuilt Docker image with ComfyUI pre-installed +-------------------------------------------------------------------------------------- + +The prebuilt image contains a fully configured ComfyUI installation and all required dependencies pre-installed. + +1. Pull the Docker image. + + .. tab-set:: + + .. tab-item:: ROCm 7.2.0 + Ubuntu 24.04 + + .. code-block:: bash + + docker pull rocm/comfyui:comfyui-0.18.2.amd0_rocm7.2.0_ubuntu24.04 + + .. tab-item:: ROCm 7.1.0 + Ubuntu 22.04 + + .. code-block:: bash + + docker pull rocm/comfyui:comfyui-0.18.2.amd0_rocm7.1.0_ubuntu22.04 + +2. Start a Docker container using the image. + + .. tab-set:: + + .. tab-item:: ROCm 7.2.0 + Ubuntu 24.04 + + .. code-block:: bash + + docker run -it --privileged \ + --rm \ + --device=/dev/kfd \ + --device=/dev/dri \ + --group-add video \ + --cap-add=SYS_PTRACE \ + --security-opt seccomp=unconfined \ + --ipc=host \ + -p 8188:8188 \ + rocm/comfyui:comfyui-0.18.2.amd0_rocm7.2.0_ubuntu24.04 + + .. tab-item:: ROCm 7.1.0 + Ubuntu 22.04 + + .. code-block:: bash + + docker run -it --privileged \ + --rm \ + --device=/dev/kfd \ + --device=/dev/dri \ + --group-add video \ + --cap-add=SYS_PTRACE \ + --security-opt seccomp=unconfined \ + --ipc=host \ + -p 8188:8188 \ + rocm/comfyui:comfyui-0.18.2.amd0_rocm7.1.0_ubuntu22.04 + +.. _build-comfyui-rocm-docker-image: + +Build from source +-------------------------------------------------------------------------------------- + +ComfyUI on ROCm can be run directly by setting up a Docker container from scratch. +A Dockerfile is provided in the `https://github.com/AMD-Ecosystem/ComfyUI/blob/amd-integration/docker/Dockerfile.rocm `__ repository to help you get started. + +1. Clone the `https://github.com/AMD-Ecosystem/ComfyUI/tree/release/0.18.2.amd0 `__ repository. + + .. code-block:: bash + + git clone https://github.com/AMD-Ecosystem/ComfyUI.git -b amd-integration + cd ComfyUI + +2. Build the Docker image. + + .. code-block:: bash + + docker build --file docker/Dockerfile.rocm --tag comfyui-rocm . + + This will pull the ``rocm/pytorch-training:v25.2`` image and install ComfyUI, the ComfyUI Node Manager, + the `https://github.com/rgthree/rgthree-comfy `__ custom nodes, and the required dependencies. + +3. Launch a container based on the image. + + .. code-block:: bash + + docker run -it --privileged \ + --rm \ + --device=/dev/kfd \ + --device=/dev/dri \ + --group-add video \ + --cap-add=SYS_PTRACE \ + --security-opt seccomp=unconfined \ + --ipc=host \ + -p 8188:8188 \ + comfyui-rocm + + +Run ComfyUI +========================================================================================= + +To run ComfyUI, you can choose to launch the server remotely or from the command line. + +Launch the remote ComfyUI server +-------------------------------------------------------------------------------------- + +After starting a Docker container with either option above, you can launch the ComfyUI server: + +.. code-block:: bash + + python $COMFYUI_PATH/main.py --port 8188 --listen + +This starts the server on the default port ``8188``. The port can be changed by setting +the environment variable ``COMFYUI_PORT_HOST`` or by using the ``--port`` flag. + +Server options: + +- ``--listen``: Allow connections from any network interface (needed for remote or container access). +- ``--port ``: Change the default port (default: ``8188``). Can also be set via the ``COMFYUI_PORT_HOST`` environment variable. +- ``--gpu-only``: Force all operations to run on the GPU. + +Launch ComfyUI from the command line +-------------------------------------------------------------------------------------- + +1. Start the ComfyUI server from the command line. + + .. code-block:: bash + + python ComfyUI/main.py + + This starts the server and displays a prompt like: + + .. code-block:: text + + To see the GUI go to: http://127.0.0.1:8188 + +2. Navigate to ``http://127.0.0.1:8188`` in your web browser. You might need to + replace ``8188`` with the appropriate port number. + + .. image:: ../images/comfyui-main.png + :align: center + :alt: Example output with host name and port number + :width: 600px + +3. Search for one of the following templates and download any missing models. See :ref:`comfyui-download-models`. + + .. tab-set:: + + .. tab-item:: SD3.5 Simple + + Select **Template** → **Model Filter** → **SD3.5** → **SD3.5 Simple** + + .. image:: ../images/sd3_5-simple-card.png + :align: center + + Download required models, if missing. + + .. image:: ../images/sd3_5-missing-models.png + :align: center + + .. tab-item:: Chroma1 Radiance text to image + + Select **Template** → **Model Filter** → **Chroma** → **Chroma1 Radiance text to image** + + .. image:: ../images/chroma1-radiance-tti-card.png + :align: center + + Download required models, if missing. + + .. image:: ../images/chroma1-radiance-tti-missing-models.png + :align: center + +4. Click **Run**. + +The application will use your AMD GPU to convert the prompted text to an image. + + +Test the ComfyUI installation +========================================================================================= + +To verify that ComfyUI was installed correctly, test ROCm PyTorch support. +Inside the running container, confirm that PyTorch detects the GPU: + +.. code-block:: bash + + python3 -c "import torch; print(torch.cuda.is_available()); print(torch.cuda.get_device_name(0))" + +The expected output is ``True`` followed by your AMD GPU device name, for example: + +.. code-block:: text + + True + AMD Instinct MI355X + +If you see the version string above, ComfyUI ``0.18.2`` has been installed successfully. You can now use ComfyUI in your projects. + + +Next Steps +-------------------------------------------------------------------------------------- + +Now that you have ComfyUI running on your AMD Instinct GPU, you can: + +* Explore additional workflow templates +* Create custom workflows from scratch +* Install community-created custom nodes +* Experiment with different models and parameters +* Build your own custom nodes for specialized tasks diff --git a/amd-docs/sphinx/_toc.yml.in b/amd-docs/sphinx/_toc.yml.in new file mode 100644 index 00000000000..2ed0ef5631b --- /dev/null +++ b/amd-docs/sphinx/_toc.yml.in @@ -0,0 +1,34 @@ +defaults: + numbered: False + maxdepth: 6 +root: index +subtrees: +- entries: + - file: what-is-comfyui.rst + title: What is ComfyUI? + +- caption: Install + entries: + - file: install/comfyui-install.rst + title: Install ComfyUI + +- caption: How to + entries: + - file: how-to/download-models.rst + title: Download and use models in ComfyUI + - file: how-to/hunyuan3d-workflow.rst + title: Run the Hunyuan3D 2.1 template in ComfyUI + - file: how-to/wan-inference-workflow.rst + title: Run the Wan 2.2 inference template in ComfyUI + +- caption: Reference + entries: + - url: https://docs.comfy.org/index.html + title: Overview and reference documentation (upstream) + +- caption: About + entries: + - url: https://rocm.blogs.amd.com/artificial-intelligence/comfyui/README.html + title: ROCm ComfyUI blog + - file: about/license.rst + title: License diff --git a/amd-docs/sphinx/requirements.in b/amd-docs/sphinx/requirements.in new file mode 100644 index 00000000000..834f75631ea --- /dev/null +++ b/amd-docs/sphinx/requirements.in @@ -0,0 +1 @@ +rocm-docs-core==1.37.0 diff --git a/amd-docs/sphinx/requirements.txt b/amd-docs/sphinx/requirements.txt new file mode 100644 index 00000000000..d8cf7dcf575 --- /dev/null +++ b/amd-docs/sphinx/requirements.txt @@ -0,0 +1,279 @@ +# +# This file is autogenerated by pip-compile with Python 3.12 +# by the following command: +# +# pip-compile requirements.in +# +accessible-pygments==0.0.5 + # via pydata-sphinx-theme +alabaster==1.0.0 + # via sphinx +asttokens==3.0.2 + # via stack-data +attrs==26.1.0 + # via + # jsonschema + # jupyter-cache + # referencing +babel==2.18.0 + # via + # pydata-sphinx-theme + # sphinx +beautifulsoup4==4.15.0 + # via pydata-sphinx-theme +breathe==4.36.0 + # via rocm-docs-core +certifi==2026.6.17 + # via requests +cffi==2.1.0 + # via + # cryptography + # pynacl +charset-normalizer==3.4.9 + # via requests +click==8.4.2 + # via + # jupyter-cache + # sphinx-external-toc +colorama==0.4.6 + # via + # click + # ipython + # sphinx +comm==0.2.3 + # via ipykernel +cryptography==49.0.0 + # via pyjwt +debugpy==1.8.21 + # via ipykernel +decorator==5.3.1 + # via ipython +docutils==0.22.4 + # via + # myst-parser + # pydata-sphinx-theme + # sphinx +executing==2.2.1 + # via stack-data +fastjsonschema==2.21.2 + # via + # nbformat + # rocm-docs-core +gitdb==4.0.12 + # via gitpython +gitpython==3.1.51 + # via rocm-docs-core +greenlet==3.5.3 + # via sqlalchemy +idna==3.18 + # via requests +imagesize==2.0.0 + # via sphinx +importlib-metadata==9.0.0 + # via + # jupyter-cache + # myst-nb +ipykernel==7.3.0 + # via myst-nb +ipython==9.15.0 + # via + # ipykernel + # myst-nb +ipython-pygments-lexers==1.1.1 + # via ipython +jedi==0.20.0 + # via ipython +jinja2==3.1.6 + # via + # myst-parser + # sphinx +jsonschema==4.26.0 + # via nbformat +jsonschema-specifications==2025.9.1 + # via jsonschema +jupyter-cache==1.0.1 + # via myst-nb +jupyter-client==8.9.1 + # via + # ipykernel + # nbclient +jupyter-core==5.9.1 + # via + # ipykernel + # jupyter-client + # nbclient + # nbformat +markdown-it-py==4.2.0 + # via + # mdit-py-plugins + # myst-parser +markupsafe==3.0.3 + # via jinja2 +matplotlib-inline==0.2.2 + # via + # ipykernel + # ipython +mdit-py-plugins==0.6.1 + # via myst-parser +mdurl==0.1.2 + # via markdown-it-py +myst-nb==1.4.0 + # via rocm-docs-core +myst-parser==5.1.0 + # via myst-nb +nbclient==0.11.0 + # via + # jupyter-cache + # myst-nb +nbformat==5.10.4 + # via + # jupyter-cache + # myst-nb + # nbclient +nest-asyncio2==1.7.2 + # via ipykernel +packaging==26.2 + # via + # ipykernel + # sphinx +parso==0.8.7 + # via jedi +platformdirs==4.10.0 + # via jupyter-core +prompt-toolkit==3.0.52 + # via ipython +psutil==7.2.2 + # via + # ipykernel + # ipython +pure-eval==0.2.3 + # via stack-data +pycparser==3.0 + # via cffi +pydata-sphinx-theme==0.16.1 + # via + # rocm-docs-core + # sphinx-book-theme +pygithub==2.9.1 + # via rocm-docs-core +pygments==2.20.0 + # via + # accessible-pygments + # ipython + # ipython-pygments-lexers + # pydata-sphinx-theme + # sphinx +pyjwt[crypto]==2.13.0 + # via pygithub +pynacl==1.6.2 + # via pygithub +python-dateutil==2.9.0.post0 + # via jupyter-client +pyyaml==6.0.3 + # via + # jupyter-cache + # myst-nb + # myst-parser + # rocm-docs-core + # sphinx-external-toc +pyzmq==27.1.0 + # via + # ipykernel + # jupyter-client +referencing==0.37.0 + # via + # jsonschema + # jsonschema-specifications +requests==2.34.2 + # via + # pygithub + # sphinx +rocm-docs-core==1.37.0 + # via -r requirements.in +roman-numerals==4.1.0 + # via sphinx +rpds-py==2026.6.3 + # via + # jsonschema + # referencing +six==1.17.0 + # via python-dateutil +smmap==5.0.3 + # via gitdb +snowballstemmer==3.1.1 + # via sphinx +soupsieve==2.8.4 + # via beautifulsoup4 +sphinx==9.1.0 + # via + # breathe + # myst-nb + # myst-parser + # pydata-sphinx-theme + # rocm-docs-core + # sphinx-book-theme + # sphinx-copybutton + # sphinx-design + # sphinx-external-toc + # sphinx-multitoc-numbering + # sphinx-notfound-page +sphinx-book-theme==1.2.0 + # via rocm-docs-core +sphinx-copybutton==0.5.2 + # via rocm-docs-core +sphinx-design==0.7.0 + # via rocm-docs-core +sphinx-external-toc==1.1.0 + # via rocm-docs-core +sphinx-multitoc-numbering==0.1.3 + # via sphinx-external-toc +sphinx-notfound-page==1.1.0 + # via rocm-docs-core +sphinxcontrib-applehelp==2.0.0 + # via sphinx +sphinxcontrib-devhelp==2.0.0 + # via sphinx +sphinxcontrib-htmlhelp==2.1.0 + # via sphinx +sphinxcontrib-jsmath==1.0.1 + # via sphinx +sphinxcontrib-qthelp==2.0.0 + # via sphinx +sphinxcontrib-serializinghtml==2.0.0 + # via sphinx +sqlalchemy==2.0.51 + # via jupyter-cache +stack-data==0.6.3 + # via ipython +tabulate==0.10.0 + # via jupyter-cache +tornado==6.5.7 + # via + # ipykernel + # jupyter-client +traitlets==5.15.1 + # via + # ipykernel + # ipython + # jupyter-client + # jupyter-core + # matplotlib-inline + # nbclient + # nbformat +typing-extensions==4.16.0 + # via + # beautifulsoup4 + # jupyter-client + # myst-nb + # pydata-sphinx-theme + # pygithub + # referencing + # sqlalchemy +urllib3==2.7.0 + # via + # pygithub + # requests +wcwidth==0.8.2 + # via prompt-toolkit +zipp==4.1.0 + # via importlib-metadata diff --git a/amd-docs/what-is-comfyui.rst b/amd-docs/what-is-comfyui.rst new file mode 100644 index 00000000000..ed178fd0ef0 --- /dev/null +++ b/amd-docs/what-is-comfyui.rst @@ -0,0 +1,93 @@ +.. meta:: + :description: What is ComfyUI? + :keywords: ComfyUI, documentation, agent, GPU, AMD, ROCm, overview, introduction + +.. _what-is-comfyui: + +******************************************************************** +What is ComfyUI? +******************************************************************** + +`ComfyUI `__ is a graphical node-based interface that +lets you create images, videos, and audio with minimal coding. You can even create +diffusion workflows by dragging and dropping nodes in a visual interface. + +To use a stable diffusion model in ComfyUI, you need to: + +1. Install ComfyUI +2. Download your desired model +3. Build your workflow using the model in the UI + +Understanding Nodes +==================================================================== + +The key building blocks of ComfyUI are nodes. Various node types are available, and +each type determines the operation performed in your workflow. Operations include: + +* Loading model checkpoints +* Encoding prompts +* Generating images/videos +* Saving images/videos + +You connect nodes through links that determine what information passes from one node to the next in your workflow. +By connecting nodes and modifying their parameters, you can build both simple and complex workflows for tasks such as: + +* Image/video generation +* Video editing +* Super resolution + +You can create workflows from scratch or use the wide variety of available templates. +Beyond the core nodes and functionality, a vibrant community builds custom workflows +and nodes that you can import and use. You can also create your own custom nodes. + +Why ComfyUI? +==================================================================== + +ComfyUI is well suited for both beginners and advanced users who want to harness the power of generative +AI without extensive programming knowledge. Here's why ComfyUI stands out: + +* **Visual workflow design**: Build complex AI pipelines through an intuitive drag-and-drop interface instead of writing code +* **Flexibility and control**: Fine-tune every aspect of your generation process with granular control over model parameters +* **Modular architecture**: Reuse and remix workflow components, making it easy to experiment and iterate +* **Community-driven ecosystem**: Access thousands of custom nodes, workflows, and models shared by the community +* **Hardware optimization**: Leverage AMD ROCm acceleration for enhanced performance on AMD GPUs +* **Reproducibility**: Save and share complete workflows as JSON files, ensuring consistent results +* **Multi-modal capabilities**: Work with images, videos, and audio in a unified interface +* **Resource efficiency**: Optimize memory usage and processing through intelligent node execution + +Features and use cases +==================================================================== + +ComfyUI provides the following key features: + +* **Node-based workflow editor**: Intuitive visual interface for building generative AI pipelines +* **Extensive model support**: Compatible with Stable Diffusion, SDXL, Flux, and other popular models +* **Advanced sampling methods**: Multiple samplers and schedulers for fine-tuned generation control +* **LoRA and embedding support**: Easily integrate LoRAs, embeddings, and other model enhancements +* **Batch processing**: Generate multiple outputs efficiently with queue management +* **Custom node ecosystem**: Extend functionality with community-created or custom-built nodes +* **Workflow templates**: Start quickly with pre-built workflows for common tasks +* **Real-time preview**: Monitor generation progress with live previews +* **API access**: Integrate ComfyUI into automated pipelines via REST API + +ComfyUI on ROCm also includes performance-enhancing features: + +* **GPU acceleration**: Optimized performance on AMD Radeon and Instinct GPUs +* **Memory optimization**: Efficient VRAM usage for handling large models +* **Mixed precision support**: Faster inference with FP16 and other precision modes +* **Multi-GPU support**: Scale workflows across multiple AMD GPUs + +ComfyUI is commonly used in the following scenarios: + +* **AI art generation**: Create stunning images from text prompts with full creative control +* **Video synthesis**: Generate and edit videos using temporal diffusion models +* **Image-to-image transformation**: Apply style transfer, upscaling, and artistic effects +* **Character design**: Develop consistent characters using LoRAs and controlnets +* **Product visualization**: Generate product mockups and marketing materials +* **Content creation workflows**: Build automated pipelines for social media and digital content +* **Research and experimentation**: Test new models, techniques, and parameter combinations +* **Animation and VFX**: Create frames for animation or visual effects sequences +* **Super resolution and upscaling**: Enhance image and video quality with AI-powered upscaling +* **Inpainting and outpainting**: Edit specific regions or extend images beyond their borders + +For deeper exploration of ComfyUI use cases, refer to resources such as the `ComfyUI YouTube Series `__. \ No newline at end of file