# ComfyUI: English Get Started ## Get Started - [Changelog](https://docs.comfy.org/changelog/index.md): ComfyUI changelog: the latest features, improvements, and bug fixes in each release, updated as new versions ship. ### Get Started - [ComfyUI Official Documentation](https://docs.comfy.org/index.md): Official documentation for ComfyUI, the open source node-based generative AI application. Learn to build workflows for image, video, audio, and 3D generation. - [Comfy Cloud - Official ComfyUI Cloud Platform Powered by RTX 6000 Pro](https://docs.comfy.org/get_started/cloud.md): Run ComfyUI workflows online with Comfy Cloud, the official cloud platform powered by NVIDIA RTX 6000 Pro GPUs. No local installation required. - [Getting Started with AI Image Generation](https://docs.comfy.org/get_started/first_generation.md): Generate your first AI image with ComfyUI. Learn to load example workflows, install models, and complete your first text-to-image generation. #### Local (Self-Hosted) - [System Requirements](https://docs.comfy.org/installation/system_requirements.md): Hardware and software requirements for installing and running ComfyUI. - [ComfyUI Portable for Windows](https://docs.comfy.org/installation/comfyui_portable_windows.md): Download and run ComfyUI Portable on Windows: a standalone package with embedded Python and CUDA builds for NVIDIA GPUs. Extract the archive, then run ComfyUI. - [Install ComfyUI Manually (Windows, macOS, Linux)](https://docs.comfy.org/installation/manual_install.md): Install ComfyUI manually on Windows, macOS, or Linux: create a virtual environment, clone the repository, install GPU dependencies, and start the app. - [How to Update ComfyUI](https://docs.comfy.org/installation/update_comfyui.md): Update ComfyUI on any install type: Portable update scripts, Desktop updates, and git pull for manual installs, plus fixes for common update issues. ##### Comfy Desktop - [Comfy Desktop Overview](https://docs.comfy.org/installation/desktop/overview.md): Comfy Desktop overview: a desktop app that installs, manages, and launches multiple instances of ComfyUI, the node-based engine for generative AI. - [Comfy Desktop FAQ](https://docs.comfy.org/installation/desktop/faq.md): Common questions and troubleshooting tips for Comfy Desktop ###### Installation - [Comfy Desktop for Windows](https://docs.comfy.org/installation/desktop/windows.md): Install Comfy Desktop on Windows: system requirements, setup steps, updates, and a clean uninstall for running ComfyUI locally on Windows 10 and later. - [Comfy Desktop for macOS](https://docs.comfy.org/installation/desktop/macos.md): Install Comfy Desktop on macOS: system requirements, setup steps, updates, and a clean uninstall for running ComfyUI locally on Apple silicon Macs. - [Comfy Desktop on Linux](https://docs.comfy.org/installation/desktop/linux.md): Comfy Desktop on Linux: install from the official .deb or AppImage, or clone the repo and run from source. Requires Ubuntu 22.04+, x64, and Node.js v22 LTS for a source build. ###### Usage Guide - [Using Comfy Desktop](https://docs.comfy.org/installation/desktop/usage/overview.md): Overview of Comfy Desktop — creating new installations, managing instances, and more - [Instance Management](https://docs.comfy.org/installation/desktop/usage/instance-management.md): Create, edit, rename, and delete ComfyUI instances in Comfy Desktop - [Snapshots](https://docs.comfy.org/installation/desktop/usage/snapshots.md): Back up, restore, and share ComfyUI instance configurations in Comfy Desktop - [Managing Installations](https://docs.comfy.org/installation/desktop/usage/manage.md): Launch, update, snapshot, and manage your ComfyUI installations - [Settings](https://docs.comfy.org/installation/desktop/usage/settings.md): Global settings, proxy/mirror configuration, and data locations - [Migrate from Legacy Desktop](https://docs.comfy.org/installation/desktop/usage/migrate.md): Learn how to migrate your Legacy Desktop installation to Comfy Desktop #### Install Custom Nodes - [How to Install Custom Nodes in ComfyUI](https://docs.comfy.org/installation/install_custom_node.md): Install custom nodes in ComfyUI with ComfyUI Manager, git clone, or a ZIP download, and install their Python dependencies safely. ##### ComfyUI-Manager - [Overview](https://docs.comfy.org/manager/overview.md): An extension to manage custom nodes, models, and more in ComfyUI - [ComfyUI-Manager Installation](https://docs.comfy.org/manager/install.md): Install ComfyUI-Manager on Desktop, Portable, or manual ComfyUI setups to search, install, and update custom nodes from inside the app. - [ComfyUI-Manager Configuration](https://docs.comfy.org/manager/configuration.md): ComfyUI-Manager configuration reference: config.ini paths and options, security levels, and the protected system path introduced in V3.38. - [ComfyUI-Manager Troubleshooting](https://docs.comfy.org/manager/troubleshooting.md): ComfyUI-Manager troubleshooting: fixes for custom git executable paths in config.ini, Manager self-update failures, and install errors. ###### Node Management - [Custom nodes (new UI)](https://docs.comfy.org/manager/pack-management.md): Install, update, and manage custom nodes with ComfyUI-Manager using the new interface - [Managing custom nodes with ComfyUI-Manager (legacy UI)](https://docs.comfy.org/manager/legacy-ui.md): Install, update, and manage custom nodes with ComfyUI-Manager using the legacy interface ### Agent Tools - [Agent Tools](https://docs.comfy.org/agent-tools/index.md): Leverage AI agents to use ComfyUI smarter and faster. Comfy MCP, Comfy CLI, and the Comfy In-App Agent. - [Comfy MCP: Connect AI Agents to ComfyUI](https://docs.comfy.org/agent-tools/mcp.md): Connect AI agents to ComfyUI over the Model Context Protocol. Generate images, video, audio, and 3D, and run real workflows on Comfy Cloud or your own machine. - [Comfy CLI](https://docs.comfy.org/agent-tools/cli.md): Drive Comfy from the terminal: local ComfyUI, partner generate calls, and full workflows on Comfy Cloud. Complements MCP for scripts, CI, and automation. - [Comfy In-App Agent](https://docs.comfy.org/agent-tools/in-app-agent.md): Join the private alpha waitlist for Comfy In-App Agent on Comfy Cloud. - [Skills](https://docs.comfy.org/agent-tools/skills.md): Agent skills and plugins for Comfy, published through the Comfy Skills repository. ### Basic Concepts - [ComfyUI Workflows: Nodes, Links, and Visual Programming](https://docs.comfy.org/basic-concepts/workflow.md): Learn what a workflow is in ComfyUI: a graph of connected nodes that creates images, video, audio, and 3D. Covers nodes, links, and saving workflows as JSON. - [Nodes](https://docs.comfy.org/basic-concepts/nodes.md): Nodes are ComfyUI's fundamental building blocks: independent Comfy Core or custom modules you connect with links to assemble complex workflows. - [Custom Nodes](https://docs.comfy.org/basic-concepts/custom-nodes.md): Custom nodes in ComfyUI: how they differ from Comfy Core nodes, plus installing, updating, enabling dependencies, disabling, and uninstalling them. - [Properties](https://docs.comfy.org/basic-concepts/properties.md): Master Comfy properties with our official development documentation. Understand core concepts to build custom nodes efficiently. Read the full guide now. - [Links](https://docs.comfy.org/basic-concepts/links.md): Understand connection links in ComfyUI - [Models](https://docs.comfy.org/basic-concepts/models.md): How model files fit into ComfyUI workflows: where they go, how to load them, and common fixes. - [Dependencies](https://docs.comfy.org/basic-concepts/dependencies.md): Understand dependencies in ComfyUI ### Interface Guide - [Interface Overview](https://docs.comfy.org/interface/overview.md): ComfyUI interface tour covering the workspace parts used to build, organize, and debug workflows in the visual node editor. - [ComfyUI APP mode guide](https://docs.comfy.org/interface/app-mode.md): Learn how to build and use APP mode in ComfyUI to simplify workflow interaction by defining custom input/output interfaces. - [Nodes 2.0](https://docs.comfy.org/interface/nodes-2.md): Nodes 2.0 moves ComfyUI node rendering from LiteGraph Canvas to a Vue-based system for faster iteration: what changed and how to enable it. - [Mask Editor - Create and Edit Masks in ComfyUI](https://docs.comfy.org/interface/maskeditor.md): Learn how to use the Mask Editor in ComfyUI, including tools, layers, settings, and shortcuts - [Templates - ComfyUI Built-in Workflow Templates](https://docs.comfy.org/interface/features/template.md): Templates provide model workflows natively supported by ComfyUI and example workflows from custom nodes. You can find and use workflows for currently supported models here. - [Subgraph - Simplify your workflow](https://docs.comfy.org/interface/features/subgraph.md): An introduction to the Subgraph feature in ComfyUI, including how to create, navigate, and manage subgraphs. - [Partial Execution - Run Only Part of Your workflow in ComfyUI](https://docs.comfy.org/interface/features/partial-execution.md): How to use and the requirements for the Partial Execution feature in ComfyUI - [Node docs - View documentation for any node](https://docs.comfy.org/interface/features/node-docs.md): Learn how to access built-in documentation for nodes in ComfyUI, including both built-in and custom nodes. #### ComfyUI Settings - [ComfyUI Settings Overview](https://docs.comfy.org/interface/settings/overview.md): Detailed description of ComfyUI settings overview - [Account Management](https://docs.comfy.org/interface/user.md): In this document, we will introduce the account management features of ComfyUI, including account login, registration, and logout operations. - [Credits Management](https://docs.comfy.org/interface/credits.md): Credits for Partner Nodes in ComfyUI: how to buy credits, track usage history, and monitor your balance from Settings > Credits. - [Comfy Settings](https://docs.comfy.org/interface/settings/comfy.md): Detailed description of ComfyUI core setting options - [ComfyUI LiteGraph (Canvas) Settings](https://docs.comfy.org/interface/settings/lite-graph.md): Detailed description of ComfyUI graphics rendering engine LiteGraph setting options - [Customizing ComfyUI Appearance](https://docs.comfy.org/interface/appearance.md): Learn how to customize the appearance of ComfyUI using color palettes and advanced CSS options - [ComfyUI 3D Settings](https://docs.comfy.org/interface/settings/3d.md): Detailed description of ComfyUI 3D setting options - [ComfyUI Mask Editor Settings](https://docs.comfy.org/interface/settings/mask-editor.md): Detailed description of ComfyUI mask editor setting options - [Keyboard and Mouse Shortcuts](https://docs.comfy.org/interface/shortcuts.md): ComfyUI keyboard and mouse shortcuts: the full default list, plus how to view and customize keybindings in the in-app settings menu. - [Extension Settings](https://docs.comfy.org/interface/settings/extension.md): Detailed description of ComfyUI extension management and setting options - [About Page](https://docs.comfy.org/interface/settings/about.md): Detailed description of ComfyUI About settings page #### Cloud Exclusive - [Share workflows](https://docs.comfy.org/cloud/share-workflow.md): Learn how to share your Comfy Cloud workflows with others via shareable links - [Import models](https://docs.comfy.org/cloud/import-models.md): Learn how to import models from Civitai and Hugging Face to Comfy Cloud ### Tutorials #### Basic Examples - [ComfyUI Text to Image Workflow](https://docs.comfy.org/tutorials/basic/text-to-image.md): Build a text-to-image workflow in ComfyUI: load the default workflow, install an SD1.5 checkpoint, write prompts, and learn what each node does. - [ComfyUI Image to Image Workflow](https://docs.comfy.org/tutorials/basic/image-to-image.md): Build an image-to-image workflow in ComfyUI: load a reference image and generate new versions in a different style, from line art, or restore old images. - [ComfyUI Inpainting Workflow](https://docs.comfy.org/tutorials/basic/inpaint.md): ComfyUI inpainting tutorial: edit parts of an image, draw masks with the mask editor, and connect the VAE Encode (for Inpainting) node in a workflow. - [Outpainting Workflow Example](https://docs.comfy.org/tutorials/basic/outpaint.md): Outpainting workflow in ComfyUI: extend an image beyond its borders using the Pad Image for Outpainting node and inpainting-model techniques. - [ComfyUI Image Upscale Workflow](https://docs.comfy.org/tutorials/basic/upscale.md): Upscale images in ComfyUI: load an upscale model, build the workflow, and chain it after text-to-image for higher resolution outputs. - [ComfyUI LoRA Example](https://docs.comfy.org/tutorials/basic/lora.md): Use LoRA models in ComfyUI: install a LoRA, load it with the Load LoRA node, and run a workflow that applies its style on top of a checkpoint. - [ComfyUI Multiple LoRAs Example](https://docs.comfy.org/tutorials/basic/multiple-loras.md): This guide demonstrates how to apply multiple LoRA models simultaneously in ComfyUI #### ControlNet - [ComfyUI ControlNet Usage Example](https://docs.comfy.org/tutorials/controlnet/controlnet.md): ControlNet in ComfyUI: control image generation with condition images instead of trial-and-error prompting, plus a step-by-step workflow example. - [ComfyUI Pose ControlNet Usage Example](https://docs.comfy.org/tutorials/controlnet/pose-controlnet-2-pass.md): Learn Pose ControlNet in ComfyUI. Use OpenPose skeletons to control character posture and generate large images with a two-pass workflow. - [Depth ControlNet Workflow Example](https://docs.comfy.org/tutorials/controlnet/depth-controlnet.md): Depth ControlNet workflow in ComfyUI: how depth maps encode distance, and how to use one to control scene structure during image generation. - [ComfyUI Depth T2I Adapter Usage Example](https://docs.comfy.org/tutorials/controlnet/depth-t2i-adapter.md): This guide will introduce you to the basic concepts of Depth T2I Adapter and demonstrate how to generate corresponding images in ComfyUI - [ComfyUI Mixing ControlNet Examples](https://docs.comfy.org/tutorials/controlnet/mixing-controlnets.md): In this example, we will demonstrate how to mix multiple ControlNets and learn to use multiple ControlNet models to control image generation #### Image - [Cosmos Predict2 Text-to-Image ComfyUI Official Example](https://docs.comfy.org/tutorials/image/cosmos/cosmos-predict2-t2i.md): This guide demonstrates how to complete Cosmos-Predict2 text-to-image workflow in ComfyUI - [ComfyUI OmniGen2 Native Workflow Examples](https://docs.comfy.org/tutorials/image/omnigen/omnigen2.md): ComfyUI OmniGen2 Native Workflow Examples - Unified text-to-image, image editing, and multi-image composition model. ##### Flux - [ComfyUI Flux.2 Dev Example](https://docs.comfy.org/tutorials/flux/flux-2-dev.md): This guide provides a brief introduction to the Flux.2 model and guides you through using the Flux.2 Dev model for text-to-image generation in ComfyUI. - [ComfyUI Flux.2 Klein 4B Guide](https://docs.comfy.org/tutorials/flux/flux-2-klein.md): A quick introduction to FLUX.2 [klein] 4B and how to run text-to-image and image editing workflows in ComfyUI. - [Flux.1 Krea Dev ComfyUI Workflow Tutorial](https://docs.comfy.org/tutorials/flux/flux1-krea-dev.md): Generate images with the open-source Flux.1 Krea Dev model in ComfyUI, built by Black Forest Labs and Krea for natural details and distinctive aesthetics. - [ComfyUI Flux Kontext Dev Native Workflow Example](https://docs.comfy.org/tutorials/flux/flux-1-kontext-dev.md): FLUX.1 Kontext Dev workflow for ComfyUI: edit images with text and image input using Black Forest Labs' open-source 12B multimodal editing model. - [ComfyUI Flux.1 Text-to-Image Workflow Example](https://docs.comfy.org/tutorials/flux/flux-1-text-to-image.md): Generate text-to-image with the open-source Flux.1 model in ComfyUI, including full and FP8 checkpoint versions, with step-by-step workflow setup. - [ByteDance USO ComfyUI Native Workflow example](https://docs.comfy.org/tutorials/flux/flux-1-uso.md): Unified Style and Subject-Driven Generation with ByteDance's USO model - [ComfyUI Flux.1 fill dev Example](https://docs.comfy.org/tutorials/flux/flux-1-fill-dev.md): This guide demonstrates how to use Flux.1 fill dev to create Inpainting and Outpainting workflows. - [ComfyUI Flux.1 ControlNet Examples](https://docs.comfy.org/tutorials/flux/flux-1-controlnet.md): FLUX.1 Canny and Depth workflow examples for ComfyUI: add ControlNet-style structural control to FLUX.1 with Black Forest Labs' FLUX.1 Tools. ##### Qwen - [Qwen-Image ComfyUI Native Workflow Example](https://docs.comfy.org/tutorials/image/qwen/qwen-image.md): Qwen-Image is a 20B parameter MMDiT (Multimodal Diffusion Transformer) model open-sourced under the Apache 2.0 license. - [Qwen-Image-2512 ComfyUI Native Workflow Example](https://docs.comfy.org/tutorials/image/qwen/qwen-image-2512.md): Qwen-Image-2512 is the December update of Qwen-Image's text-to-image foundational model, featuring enhanced human realism, finer natural detail, and improved text rendering. - [Qwen-Image-Edit ComfyUI Native Workflow Example](https://docs.comfy.org/tutorials/image/qwen/qwen-image-edit.md): Qwen-Image-Edit is the image editing version of Qwen-Image, further trained based on the 20B model, supporting precise text editing and dual semantic/appearance editing capabilities. - [Qwen-Image-Edit-2511 ComfyUI Native Workflow Example](https://docs.comfy.org/tutorials/image/qwen/qwen-image-edit-2511.md): Edit images with Qwen-Image-Edit-2511 in ComfyUI, with improved character consistency, multi-person editing, LoRA support, and stronger geometric reasoning. - [Qwen-Image-Layered ComfyUI Workflow Example](https://docs.comfy.org/tutorials/image/qwen/qwen-image-layered.md): Qwen-Image-Layered is a model capable of decomposing an image into multiple RGBA layers, enabling inherent editability through layer decomposition. ##### Z-Image - [Z-Image ComfyUI Workflow Example](https://docs.comfy.org/tutorials/image/z-image/z-image.md): Z-Image is a 6B efficient image generation foundation model from Alibaba Tongyi Lab. Its single-stream DiT design targets fine-tuning and custom development. - [Z-Image-Turbo ComfyUI Workflow Example](https://docs.comfy.org/tutorials/image/z-image/z-image-turbo.md): Z-Image-Turbo is a distilled 6B parameter efficient image generation model with sub-second inference latency. ##### Boogu - [Boogu-Image-0.1 ComfyUI Workflow Example](https://docs.comfy.org/tutorials/image/boogu/boogu-image-0.1.md): Boogu-Image-0.1 is an Apache-2.0 10B parameter unified image generation and editing model family, with variants for text-to-image and instruction-driven editing. ##### HiDream - [ComfyUI Native HiDream-I1 Text-to-Image Workflow Example](https://docs.comfy.org/tutorials/image/hidream/hidream-i1.md): This guide will walk you through completing a ComfyUI native HiDream-I1 text-to-image workflow example - [ComfyUI Native HiDream-E1, E1.1 Workflow Example](https://docs.comfy.org/tutorials/image/hidream/hidream-e1.md): This guide will help you understand and complete the ComfyUI native HiDream-I1 text-to-image workflow example - [ComfyUI Native HiDream-O1-Image Workflow Example](https://docs.comfy.org/tutorials/image/hidream/hidream-o1.md): This guide walks you through the ComfyUI native HiDream-O1-Image text-to-image and image editing workflows ##### Ovis - [Ovis-Image ComfyUI Workflow Example](https://docs.comfy.org/tutorials/image/ovis/ovis-image.md): Ovis-Image is a 7B text-to-image model for high-quality text rendering in ComfyUI, delivering crisp bilingual text on posters, banners, and UI mockups. ##### NewBie-image - [ComfyUI NewBie-image-Exp0.1 Workflow Example](https://docs.comfy.org/tutorials/image/newbie-image/newbie-image-exp-0-1.md): NewBie-image-Exp0.1 is a 3.5B anime-style text-to-image model built on Next-DiT, optimized for detailed anime art with XML structured prompts in ComfyUI. ##### ERNIE-Image - [ERNIE-Image ComfyUI workflow example](https://docs.comfy.org/tutorials/image/ernie-image/ernie-image.md): ERNIE-Image is Baidu's open 8B Diffusion Transformer text-to-image model with precise text rendering, strong instruction following, and a built-in Prompt Enhancer. ##### Anima - [Anima Base v1 ComfyUI workflow example](https://docs.comfy.org/tutorials/image/anima/anima.md): Anima is a 2B-parameter text-to-image model by CircleStone Labs / Comfy Org, optimized for anime and non-photorealistic illustration generation. ##### Lens - [Lens ComfyUI workflow example](https://docs.comfy.org/tutorials/image/lens/lens.md): Lens is a 3.8B parameter text-to-image model by Microsoft, using dual-stream MMDiT with GPT-OSS-20B text features and FLUX.2 VAE for efficient, high-resolution generation. ##### PixelDiT - [PixelDiT ComfyUI Workflow Example](https://docs.comfy.org/tutorials/image/pixeldit/pixeldit.md): PixelDiT is NVIDIA's pixel-space diffusion transformer for 1024px text-to-image generation. It operates directly in pixel space: no VAE encode/decode required. ##### Krea 2 - [Krea-2 ComfyUI Workflow Example](https://docs.comfy.org/tutorials/image/krea/krea-2.md): Krea 2 is a text-to-image model designed for high aesthetic quality and stylistic diversity. It comes in two variants: RAW (base) and Turbo (distilled). ##### Ideogram - [ComfyUI Ideogram 4.0 Open-Source Model Tutorial](https://docs.comfy.org/tutorials/image/ideogram/ideogram-v4.md): Ideogram 4.0 in ComfyUI: run Ideogram's open-source text-to-image model locally, with accurate text rendering and JSON or natural-language style prompts. ##### Mage-Flow - [Mage-Flow: ComfyUI Workflow Example](https://docs.comfy.org/tutorials/image/mage-flow/mage-flow.md): Mage-Flow is Microsoft's compact 4B model for text-to-image generation and instruction-based image editing in ComfyUI, with native resolutions up to 2K. #### 3D - [TripoSplat Image to Gaussian Splat ComfyUI Workflow Example](https://docs.comfy.org/tutorials/3d/triposplat.md): Generate high-quality 3D Gaussian splat representations from a single 2D image using TripoSplat, with controllable density and budget for rendering. - [ComfyUI Hunyuan3D-2 Examples](https://docs.comfy.org/tutorials/3d/hunyuan3D-2.md): Hunyuan3D 2.0 in ComfyUI: generate textured 3D models from text or images with Tencent's open-source two-stage model, geometry first, then textures. - [Pixal3D Image to 3D Model ComfyUI Workflow Example](https://docs.comfy.org/tutorials/3d/pixal3d.md): Generate high-fidelity 3D models with full PBR textures from a single image using Pixal3D, a pixel-aligned image-to-3D model from Tencent ARC. - [TRELLIS.2 Image to 3D Model ComfyUI Workflow Example](https://docs.comfy.org/tutorials/3d/trellis2.md): Generate high-fidelity 3D models with full PBR textures from a single image using TRELLIS.2, Microsoft's open-source 4B-parameter image-to-3D model. #### LLM - [Gemma 4 ComfyUI workflow example](https://docs.comfy.org/tutorials/llm/gemma4/gemma4.md): Run Google's lightweight open Gemma 4 LLM in ComfyUI for text generation, image understanding, video analysis, and audio transcription with up to 256K context. - [Qwen 3.0 ComfyUI workflow example](https://docs.comfy.org/tutorials/llm/qwen/qwen3.md): Qwen 3.0 is Alibaba Cloud's powerful open-source LLM with strong reasoning capabilities, available in 4B size for text generation and structured reasoning tasks. - [Qwen3.5 ComfyUI workflow example](https://docs.comfy.org/tutorials/llm/qwen/qwen3_5.md): Qwen3.5 is Alibaba Cloud's open-source multimodal LLM with image understanding and text generation capabilities, available in 4B size for image captioning and reverse prompt engineering. #### Video - [ComfyUI Bernini-R Examples](https://docs.comfy.org/tutorials/video/bytedance/bernini-r.md): Learn how to use Bernini-R in ComfyUI for image and video editing with in-context conditioning: relighting, restyling, subject insertion, and more. ##### MiniMax H3 - [ComfyUI MiniMax H3 Video Generation Guide](https://docs.comfy.org/tutorials/video/minimax/minimax-h3.md): How to use open-weights MiniMax H3 in ComfyUI: text-to-video, image-to-video, and reference-to-video workflows with native stereo audio, prompt writing tips, and Sage Attention speedups. - [ComfyUI MiniMax H3 Text-to-Video, Image-to-Video, and Reference-to-Video Workflows](https://docs.comfy.org/tutorials/video/minimax/minimax-h3-native.md): Run MiniMax H3 text-to-video (T2V), image-to-video (I2V), and reference-to-video (R2V) workflows in ComfyUI, plus advanced native-node techniques for guide anchoring and latent noise masks. - [ComfyUI MiniMax H3 Multiframe Reference Workflow](https://docs.comfy.org/tutorials/video/minimax/minimax-h3-multiframe.md): Generate MiniMax H3 video continuations and multi-shot scenes in ComfyUI by anchoring reference frames at specific points along the output timeline with Add Guide nodes. - [ComfyUI MiniMax H3 Fun ControlNet Union: Pose, Depth, and Canny Control Video](https://docs.comfy.org/tutorials/video/minimax/minimax-h3-fun-controlnet.md): Control MiniMax H3 video motion in ComfyUI with Canny, Depth, HED, MLSD, or Pose control videos, or run mask-based video inpainting with the Fun ControlNet Union patch. - [ComfyUI MiniMax H3 Prompt Guide: Official Guides, Tips, and Prompt Embeddings](https://docs.comfy.org/tutorials/video/minimax/minimax-h3-prompt-guide.md): Write better MiniMax H3 prompts in ComfyUI: MiniMax's official prompt writing guides, general prompting tips, and community prompt embeddings for style effects. ##### LTX - [LTX-0.9.5 ComfyUI Workflow Examples](https://docs.comfy.org/tutorials/video/ltxv.md): Learn how to use LTX-Video 0.9.5 in ComfyUI for efficient video generation - [LTX-2.0 ComfyUI Workflow Examples](https://docs.comfy.org/tutorials/video/ltx/ltx-2.md): Learn how to use LTX-2 in ComfyUI for synchronized audio-video generation - [LTX-2.3: ComfyUI Workflow Examples](https://docs.comfy.org/tutorials/video/ltx/ltx-2-3.md): Learn how to use LTX-2.3 in ComfyUI with native workflows for text-to-video, image-to-video, FLF2V, audio-driven video, IC-LoRA control, and ID-LoRA personalization. - [LTX-2.5: ComfyUI Workflow Examples](https://docs.comfy.org/tutorials/video/ltx/ltx-2-5.md): Use LTX-2.5 in ComfyUI with native text-to-video, image-to-video, and first-last-frame workflows, including synchronized audio and native multishot scenes. ##### Wan Video - [Wan Animate 2: Motion Transfer](https://docs.comfy.org/tutorials/video/wan/wan-animate-2.md): Animate a still character using a driving video with Wan Animate 2, transferring motion directly from video frames without pose extraction or skeleton preprocessing - [Wan2.2 Video Generation ComfyUI Official Native Workflow Example](https://docs.comfy.org/tutorials/video/wan/wan2_2.md): Run Wan2.2 video workflows in ComfyUI: the 5B hybrid TI2V model plus 14B text-to-video, image-to-video, and first-last-frame examples, with downloads. - [Wan2.2 Animate ComfyUI native workflow](https://docs.comfy.org/tutorials/video/wan/wan2-2-animate.md): Unified character animation and replacement framework with precise motion and expression replication. - [Wan Dancer: Music to Dance Video Generation](https://docs.comfy.org/tutorials/video/wan/wan-dancer.md): Create synchronized dance videos from music with Wan Dancer in ComfyUI. Use a reference image and audio to generate coherent, expressive dance motion. - [Wan2.2-S2V Audio-Driven Video Generation ComfyUI Native Workflow Example](https://docs.comfy.org/tutorials/video/wan/wan2-2-s2v.md): This is a native workflow example for Wan2.2-S2V audio-driven video generation in ComfyUI. - [ComfyUI Wan2.2 Fun Inp Start-End Frame Video Generation Example](https://docs.comfy.org/tutorials/video/wan/wan2-2-fun-inp.md): This article introduces how to use ComfyUI to complete the Wan2.2 Fun Inp start-end frame video generation example - [ComfyUI Wan2.2 Fun Control Video Generation Example](https://docs.comfy.org/tutorials/video/wan/wan2-2-fun-control.md): This article introduces how to use ComfyUI to complete the Wan2.2 Fun Control video generation using control videos - [ComfyUI Wan2.2 Fun Camera Control: Video Generation Workflow Example](https://docs.comfy.org/tutorials/video/wan/wan2-2-fun-camera.md): This article demonstrates how to use camera control for video generation with Wan2.2 Fun Camera Control in ComfyUI. ###### Wan2.1 - [ComfyUI Wan2.1 Video Examples](https://docs.comfy.org/tutorials/video/wan/wan-video.md): Run Wan2.1 video workflows in ComfyUI: text-to-video with the 1.3B model and image-to-video with the 14B model, including model installation. - [Causal Forcing I2V ComfyUI Workflow Example](https://docs.comfy.org/tutorials/video/wan/wan-causal-forcing.md): Generate videos from images using Causal Forcing or Causal Forcing++ with Wan2.1. Achieves smooth, temporally consistent video in as few as 1 inference step. - [ComfyUI Wan2.1 VACE Video Examples](https://docs.comfy.org/tutorials/video/wan/vace.md): This article introduces how to complete Wan VACE video generation examples in ComfyUI - [ComfyUI Wan-Move Workflow Example](https://docs.comfy.org/tutorials/video/wan/wan-move.md): Wan-Move is a motion-controllable video generation model via latent trajectory guidance, enabling fine-grained point-level motion control for image-to-video generation. - [Wan-Alpha Tutorial](https://docs.comfy.org/tutorials/video/wan/wan-alpha.md): Learn how to generate videos with alpha channel transparency using Wan-Alpha in ComfyUI - [Wan ATI Native Workflow](https://docs.comfy.org/tutorials/video/wan/wan-ati.md): Wan ATI trajectory control in ComfyUI: draw trajectories to direct object, region, and camera motion in generated video, built on Wan2.1. - [ComfyUI Wan2.1 Fun Control Video Examples](https://docs.comfy.org/tutorials/video/wan/fun-control.md): This guide demonstrates how to use Wan2.1 Fun Control in ComfyUI to generate videos with control videos - [ComfyUI Wan2.1 Fun Camera Official Examples](https://docs.comfy.org/tutorials/video/wan/fun-camera.md): This guide demonstrates how to use Wan2.1 Fun Camera in ComfyUI for video generation - [ComfyUI Wan2.1 Fun InP Video Examples](https://docs.comfy.org/tutorials/video/wan/fun-inp.md): This guide demonstrates how to use Wan2.1 Fun InP in ComfyUI to generate videos with first and last frame control - [ComfyUI Wan2.1 FLF2V Native Example](https://docs.comfy.org/tutorials/video/wan/wan-flf.md): This guide explains how to complete Wan2.1 FLF2V video generation examples in ComfyUI ##### ByteDance - [ComfyUI Bernini-R Examples](https://docs.comfy.org/tutorials/video/bytedance/bernini-r.md): Learn how to use Bernini-R in ComfyUI for image and video editing with in-context conditioning: relighting, restyling, subject insertion, and more. ##### Hunyuan - [ComfyUI Hunyuan Video Examples](https://docs.comfy.org/tutorials/video/hunyuan/hunyuan-video.md): This guide shows how to use Hunyuan Text-to-Video and Image-to-Video workflows in ComfyUI - [HunyuanVideo 1.5](https://docs.comfy.org/tutorials/video/hunyuan/hunyuan-video-1-5.md): Learn how to use HunyuanVideo 1.5, a lightweight 8.3B parameter model for high-quality video generation on consumer GPUs ##### Cosmos - [Cosmos Predict2 Video2World ComfyUI Official Example](https://docs.comfy.org/tutorials/video/cosmos/cosmos-predict2-video2world.md): This guide demonstrates how to complete Cosmos-Predict2 Video2World workflows in ComfyUI ##### Kandinsky - [Kandinsky 5.0](https://docs.comfy.org/tutorials/video/kandinsky/kandinsky-5.md): This guide shows how to use Kandinsky 5.0 video generation workflows in ComfyUI ##### ZAI - [ComfyUI SCAIL-2 Character Replacement Workflow Tutorial](https://docs.comfy.org/tutorials/video/zai/scail2.md): Drive a reference character image with a driving video for character animation or in-video character replacement using SCAIL-2. #### Audio ##### YuE2 - [ComfyUI YuE2 Music Generation Guide](https://docs.comfy.org/tutorials/audio/yue2/yue2.md): Generate complete songs with vocals in ComfyUI using the open-source YuE2 model: text to music with ABC planning, and melody-preserving covers with SheetSage2. ##### MiniMax Music 3 - [MiniMax Music 3 in ComfyUI: AI Music Generation](https://docs.comfy.org/tutorials/audio/minimax/minimax-music-3.md): Learn how to use MiniMax Music 3 in ComfyUI to generate complete songs up to 5 minutes long from a structured music caption and lyrics. ##### Stable Audio - [Stable Audio 1.0 ComfyUI workflow example](https://docs.comfy.org/tutorials/audio/stable-audio/stable-audio-1.md): Guide to using Stability AI's open-source Stable Audio 1.0 model in ComfyUI for text-to-audio generation. - [Stable Audio 3 ComfyUI workflow example](https://docs.comfy.org/tutorials/audio/stable-audio/stable-audio-3.md): Guide to using Stability AI's open-source Stable Audio 3 model in ComfyUI for text-to-audio generation with Qwen prompt expansion and category-aware reprompting. ##### ACE-Step - [ComfyUI ACE-Step Native Example](https://docs.comfy.org/tutorials/audio/ace-step/ace-step-v1.md): ACE-Step music generation in ComfyUI: text-to-music and music editing workflows with the Apache-2.0 open-source model from StepFun and ACE Studio. - [ComfyUI ACE-Step 1.5 Music Generation Guide](https://docs.comfy.org/tutorials/audio/ace-step/ace-step-v1-5.md): Learn how to use ACE-Step 1.5 for AI music generation in ComfyUI. Complete guide with workflows, model downloads, and setup instructions for ComfyUI. #### Utility - [ComfyUI preprocessor workflows](https://docs.comfy.org/tutorials/utility/preprocessors.md): Learn how to use depth estimation, lineart conversion, pose detection, and normals extraction preprocessors in ComfyUI ##### Upscale & Restore - [Image upscaling in ComfyUI](https://docs.comfy.org/tutorials/utility/image-upscale.md): Learn how to upscale images in ComfyUI using local models and partner nodes for different use cases - [Video upscaling in ComfyUI](https://docs.comfy.org/tutorials/utility/video-upscale.md): Learn how to upscale videos in ComfyUI using local models and partner nodes for different use cases - [SeedVR2: Image and video upscaling in ComfyUI](https://docs.comfy.org/tutorials/utility/seedvr2.md): Learn how to upscale images and videos using SeedVR2, a one-step diffusion-based restoration model from ByteDance Seed ##### Segmentation & Background - [SAM 3.1: Segment Anything in ComfyUI](https://docs.comfy.org/tutorials/utility/video-segment-sam3.md): Learn how to use Meta's SAM 3.1 model in ComfyUI to segment objects in images and videos using text prompts - [BiRefNet: Remove Image Background in ComfyUI](https://docs.comfy.org/tutorials/utility/remove-background-birefnet.md): Learn how to remove image backgrounds using the BiRefNet model, natively supported in ComfyUI ##### Pose & Detection - [SDPose: Pose Detection in ComfyUI](https://docs.comfy.org/tutorials/utility/pose-detection-sdpose.md): Learn how to extract pose keypoints and maps from images and videos using SDPose, natively supported in ComfyUI - [SAM 3D Body: Extract 3D Human Mesh From Video in ComfyUI](https://docs.comfy.org/tutorials/utility/sam3d-body.md): Extract a full-body 3D human mesh from a video using SAM 3D Body, with pose and shape estimation, face expressions, and a rendered mesh overlay video. ###### Face Detection - [MediaPipe: Face Detection in ComfyUI](https://docs.comfy.org/tutorials/utility/face-detection/mediapipe.md): Learn how to use MediaPipe Face Detection in ComfyUI to detect faces and extract facial landmarks, bounding boxes, and region masks from images ##### Depth & 3D - [ComfyUI Depth Anything 3 Examples](https://docs.comfy.org/tutorials/utility/depth-anything-3.md): Learn how to use Depth Anything 3 in ComfyUI for monocular and multi-view depth estimation from images and videos, powered by ByteDance Seed's vision transformer. - [ComfyUI Marigold V2 Depth, Normal, and Albedo Estimation Guide](https://docs.comfy.org/tutorials/utility/marigold-v2.md): Estimate depth, surface normals, and albedo from a single image in ComfyUI with Marigold V2: Qwen-Image Edit based diffusion transformers with dedicated LoRAs. - [ComfyUI MoGe Examples](https://docs.comfy.org/tutorials/utility/moge.md): This guide demonstrates how to use MoGe in ComfyUI for monocular geometry estimation: metric point maps, depth maps, normal maps, and mesh generation. ##### Video - [ComfyUI frame interpolation workflow](https://docs.comfy.org/tutorials/utility/frame-interpolation.md): Learn how to use frame interpolation to smooth motion and increase frame rate in ComfyUI video workflows - [VOID: Video Inpainting in ComfyUI](https://docs.comfy.org/tutorials/utility/void-video-inpainting.md): Learn how to remove objects from videos using the VOID video inpainting model by Netflix, natively supported in ComfyUI ### Comfy Cloud Nodes - [Comfy Cloud nodes](https://docs.comfy.org/cloud-nodes/overview.md): Run curated workflows on Comfy Cloud's GPUs from a local ComfyUI install, no subscription required ### Partner Nodes - [Partner Nodes](https://docs.comfy.org/tutorials/partner-nodes/overview.md): Partner Nodes call closed-source models such as OpenAI, Kling, and Luma through API requests inside ComfyUI: what they are, credits, and how to use them. - [Partner Node Pricing](https://docs.comfy.org/tutorials/partner-nodes/pricing.md): Partner Node pricing in credits for every provider, including Anthropic, OpenAI, Kling, and Luma, broken down by model, token type, and generation type. - [Concurrency Limits](https://docs.comfy.org/tutorials/partner-nodes/concurrency-limits.md): Understand how concurrency limits control simultaneous Partner Node requests on your account. - [FAQs about Partner Nodes](https://docs.comfy.org/tutorials/partner-nodes/faq.md): Some FAQs you may encounter when using Partner Nodes. - [Data Retention](https://docs.comfy.org/tutorials/partner-nodes/data-retention.md): How Comfy stores and deletes Partner Node inputs and outputs, and how long media files are retained. #### Partner Models ##### Image - [Image Models](https://docs.comfy.org/tutorials/partner-nodes/image/overview.md): Choose the right image model for your use case: text-to-image, editing, upscaling, background removal, and more ###### Black Forest Labs - [Flux 1.1 Pro Ultra Image Partner Nodes ComfyUI Official Workflow Examples](https://docs.comfy.org/tutorials/partner-nodes/black-forest-labs/flux-1-1-pro-ultra-image.md): This guide covers how to use the Flux 1.1 Pro Ultra Image Partner node in ComfyUI - [ComfyUI Flux.1 Kontext Pro Image Partner Nodes Official Example](https://docs.comfy.org/tutorials/partner-nodes/black-forest-labs/flux-1-kontext.md): This guide will show you how to use the Flux.1 Kontext Pro Image Partner node in ComfyUI to perform image editing ###### Beeble - [Beeble SwitchX Partner Nodes ComfyUI Official Examples](https://docs.comfy.org/tutorials/partner-nodes/beeble/beeble-switchx.md): This guide explains how to use Beeble SwitchX Partner Nodes in ComfyUI for AI-powered image and video relighting and environment editing ###### Bria - [Bria Background Removal in ComfyUI](https://docs.comfy.org/tutorials/partner-nodes/bria/background-removal.md): Learn how to use Bria Partner Nodes in ComfyUI for image and video background removal, green screen, and background replacement. - [Bria FIBO Edit Partner Nodes ComfyUI Official Example](https://docs.comfy.org/tutorials/partner-nodes/bria/fibo.md): Learn how to use the Bria FIBO Edit Partner node for precision image editing in ComfyUI - [Bria Eraser, Expand Image, and GenFill in ComfyUI](https://docs.comfy.org/tutorials/partner-nodes/bria/image-editing.md): Remove objects, expand images, and generate content inside masked regions with the Bria Eraser, Expand Image, and Generative Fill partner nodes in ComfyUI. ###### ByteDance - [ByteDance Seedream 5.0 Pro - Professional AI Image Generation](https://docs.comfy.org/tutorials/partner-nodes/bytedance/seedream-5-pro.md): Generate high-quality images with enhanced instruction following, precise editing, and professional-grade output using Seedream 5.0 Pro in ComfyUI - [ByteDance Seedream 5.0 Lite - Smart AI Image Creation](https://docs.comfy.org/tutorials/partner-nodes/bytedance/seedream-5-lite.md): Generate images with web-connected retrieval and enhanced instruction following using Seedream 5.0 lite in ComfyUI ###### Google - [Nano Banana Pro: Studio-Quality AI Image Generation](https://docs.comfy.org/tutorials/partner-nodes/google/nano-banana-pro.md): Generate and edit production-ready 4K images with Nano Banana Pro (Gemini 3 Pro Image) in ComfyUI, with advanced text rendering and character consistency. - [Nano Banana 2 - Fast AI Image Generation](https://docs.comfy.org/tutorials/partner-nodes/google/nano-banana-2.md): Generate high-quality images with Pro-level quality at Flash speed using Nano Banana 2 in ComfyUI - [Nano Banana 2 Lite: Fast AI Image Generation](https://docs.comfy.org/tutorials/partner-nodes/google/nano-banana-2-lite.md): Generate images at Google's fastest speed and lowest cost using Nano Banana 2 Lite, the Gemini 3.1 Flash-Lite Image model in ComfyUI ###### Grok - [Grok in ComfyUI: AI Image and Video Generation](https://docs.comfy.org/tutorials/partner-nodes/grok/grok-overview.md): Use xAI's Grok models in ComfyUI: Grok Imagine Image for text-to-image and image editing, and Grok Imagine Video for video generation, editing, and extension - [Grok Imagine Image in ComfyUI: AI Image Generation and Editing](https://docs.comfy.org/tutorials/partner-nodes/grok/grok-image.md): Generate and edit images with the Grok Imagine Image model in ComfyUI: text-to-image and natural-language image editing - [Grok Imagine Image 2.0 in ComfyUI: AI Image Generation and Editing](https://docs.comfy.org/tutorials/partner-nodes/grok/grok-image-2-0.md): Generate and edit images with Grok Imagine Image 2.0 in ComfyUI: Aurora engine, crisp short-text rendering, 1K/2K output, and up to 3 reference images - [Grok Imagine Image Quality in ComfyUI: AI Image Generation](https://docs.comfy.org/tutorials/partner-nodes/grok/grok-image-quality.md): Generate enhanced images with Grok Imagine Image Quality in ComfyUI: improved detail, better text rendering, and stronger creative control ###### Ideogram - [ComfyUI Ideogram 4.0 Partner Node Tutorial](https://docs.comfy.org/tutorials/partner-nodes/ideogram/ideogram-v4.md): Learn how to use the Ideogram 4.0 API Partner node in ComfyUI - [Ideogram P-Image - fast text-to-image](https://docs.comfy.org/tutorials/partner-nodes/ideogram/ideogram-p-image.md): Generate images from text descriptions using Ideogram's fast P-Image model in ComfyUI, with quality comparable to leading models at lower cost and latency ###### Krea - [ComfyUI Krea 2 Partner Nodes Official Example](https://docs.comfy.org/tutorials/partner-nodes/krea2/krea2-t2i.md): This guide explains how to use the Krea 2 Text to Image Partner node in ComfyUI ###### Luma - [Luma Uni-1 Guide](https://docs.comfy.org/tutorials/partner-nodes/luma/luma-uni-1.md): Use Luma Uni-1 partner nodes in ComfyUI for Create and Modify image workflows. - [Luma Text to Image Partner Nodes ComfyUI Official Example](https://docs.comfy.org/tutorials/partner-nodes/luma/luma-text-to-image.md): This guide explains how to use the Luma Text to Image Partner node in ComfyUI - [Luma Image to Image Partner Nodes ComfyUI Official Example](https://docs.comfy.org/tutorials/partner-nodes/luma/luma-image-to-image.md): This guide covers how to use the Luma Image to Image Partner node in ComfyUI ###### Meta - [Meta Muse Image in ComfyUI: Text to Image and Image Edit](https://docs.comfy.org/tutorials/partner-nodes/meta/muse-image.md): Generate and edit images with Meta's Muse Image 1.0 Partner Nodes in ComfyUI. Agentic image generation with built-in web search, image search, and code execution, plus instruction-based editing across up to 10 reference images. ###### OpenAI - [OpenAI GPT Image 2.5 Node: Flare and Sunburst Workflows](https://docs.comfy.org/tutorials/partner-nodes/openai/gpt-image-2-5.md): Generate and edit images in ComfyUI with the OpenAI GPT Image 2.5 Flare and Sunburst partner nodes: fast T2I previews, high-fidelity edits, and workflow templates. - [OpenAI GPT-Image-2 Node](https://docs.comfy.org/tutorials/partner-nodes/openai/gpt-image-2.md): Learn how to use the OpenAI GPT-Image-2 Partner node to generate images in ComfyUI - [OpenAI GPT-Image-1 Node](https://docs.comfy.org/tutorials/partner-nodes/openai/gpt-image-1.md): Learn how to use the OpenAI GPT-Image-1 Partner node to generate images in ComfyUI ###### Qwen - [Qwen Image 3.0 Pro - Advanced AI Image Generation](https://docs.comfy.org/tutorials/partner-nodes/qwen/qwen-image-3-0-pro.md): Generate information-dense images with ultra-long prompts, precise small-text rendering, and multi-image editing using Qwen Image 3.0 Pro in ComfyUI ###### Recraft - [Recraft V4 & V4.1 Image & Vector Generation in ComfyUI](https://docs.comfy.org/tutorials/partner-nodes/recraft/recraft-v4.md): Generate professional images and production-ready vectors with Recraft V4 and V4.1 in ComfyUI - [Recraft Text to Image Partner Nodes ComfyUI Official Example](https://docs.comfy.org/tutorials/partner-nodes/recraft/recraft-text-to-image.md): Learn how to use the Recraft Text to Image Partner node in ComfyUI ###### Reve - [Reve Image Create, Edit, and Remix in ComfyUI](https://docs.comfy.org/tutorials/partner-nodes/reve/reve-image.md): Learn how to use Reve Partner nodes in ComfyUI for high-quality image generation, editing, and remixing at up to 4K resolution ###### Runway - [Runway Partner Nodes Image Generation ComfyUI Official Example](https://docs.comfy.org/tutorials/partner-nodes/runway/image-generation.md): This article will introduce how to use Runway nodes in ComfyUI for text-to-image and reference-to-image generation ###### Topaz - [Topaz Image Enhance Wonder 3.5 - AI image enhancement](https://docs.comfy.org/tutorials/partner-nodes/topaz/image-enhance-wonder-3-5.md): Upscale and enhance images with Topaz Image Enhance Wonder 3.5 in ComfyUI: generative detail restoration, noise reduction, and text sharpening - [Topaz Image Enhance Bloom 2 - AI creative image upscaling](https://docs.comfy.org/tutorials/partner-nodes/topaz/image-enhance-bloom-2.md): Upscale and enhance images with Topaz Image Enhance Bloom 2 in ComfyUI: creative upscaling that adds new detail, texture, and visual elements ##### Video - [Video Models](https://docs.comfy.org/tutorials/partner-nodes/video/overview.md): Choose the right video model for your use case: text-to-video, image-to-video, video enhancement, and more ###### Black Forest Labs - [FLUX 3 Video - AI video generation with native audio](https://docs.comfy.org/tutorials/partner-nodes/black-forest-labs/flux-3-video.md): Generate videos with synchronized audio using FLUX 3 in ComfyUI, from text or images, with up to 20 seconds of footage in a single pass - [FLUX Video Upscale: AI video upscaling to 4K in ComfyUI](https://docs.comfy.org/tutorials/partner-nodes/black-forest-labs/flux-video-upscale.md): Upscale videos to 1080p, 2K, or 4K with the FLUX Video Upscale partner node in ComfyUI. Precise mode preserves faces and products; creative mode adds new detail to generated footage. ###### ByteDance - [Seedance 2.5 - AI video generation with audio](https://docs.comfy.org/tutorials/partner-nodes/bytedance/seedance-2-5.md): Generate 30-second videos with synchronized audio, multimodal reference control, and precise editing using Seedance 2.5 in ComfyUI - [Seedance 2.0 - AI video generation](https://docs.comfy.org/tutorials/partner-nodes/bytedance/seedance-2-0.md): Generate high-quality video from text, images, video, and audio with synced audio, consistent characters, and cinematic camera control using Seedance 2.0 in ComfyUI - [Seedance 2.0 Real Human - Verified real person video generation](https://docs.comfy.org/tutorials/partner-nodes/bytedance/seedance-2-0-real-human.md): Generate videos featuring real people in Seedance 2.0 with identity consistency, native audio-video sync, and a one-time ByteDance liveness verification in ComfyUI - [ByteDance vCube Video Enhance in ComfyUI](https://docs.comfy.org/tutorials/partner-nodes/bytedance/vcube.md): Upscale and restore video with ByteDance vCube in ComfyUI: super-resolution up to 8K, artifact and noise removal, color and sharpness enhancement, and frame interpolation ###### Google - [Gemini Omni Flash: Conversational Video Generation](https://docs.comfy.org/tutorials/partner-nodes/google/gemini-omni-flash.md): Generate and edit videos through natural language using Gemini Omni Flash 1.1, Google's multimodal video model, available in ComfyUI through Partner Nodes ###### Grok - [Grok Imagine Video in ComfyUI: AI Video Generation, Editing, and Extension](https://docs.comfy.org/tutorials/partner-nodes/grok/grok-video.md): Generate, edit, and extend videos with Grok Imagine in ComfyUI: text/image to video, video editing, video extension, and reference-to-video workflows - [Grok Imagine Video 1.5 Image to Video ComfyUI Official Example](https://docs.comfy.org/tutorials/partner-nodes/grok/grok-imagine-video-1-5.md): This guide explains how to use the Grok Imagine Video 1.5 Partner Node in ComfyUI to generate high-quality videos with native audio from images ###### HappyHorse - [HappyHorse 1.1 Video Generation in ComfyUI](https://docs.comfy.org/tutorials/partner-nodes/happyhorse/happyhorse1-1.md): Use HappyHorse 1.1 via ComfyUI Partner Nodes for image-to-video, text-to-video, and reference-to-video with native synchronized audio and multi-shot scenes. - [HappyHorse 1.0 Video Generation in ComfyUI](https://docs.comfy.org/tutorials/partner-nodes/happyhorse/happyhorse1-0.md): Learn how to use HappyHorse 1.0 via Partner Nodes in ComfyUI for image-to-video, text-to-video, reference-to-video, and video editing with cinematic aesthetics and multi-shot consistency ###### Kling - [Kling 3.0 Video and Image Generation in ComfyUI](https://docs.comfy.org/tutorials/partner-nodes/kling/kling-3-0.md): Learn how to use Kling 3.0 models in ComfyUI for multi-shot video generation, subject consistency, multilingual audio, and native text rendering - [Kling 2.6 Motion Control Partner Nodes ComfyUI Official Example](https://docs.comfy.org/tutorials/partner-nodes/kling/kling-motion-control.md): Learn how to use the Kling 2.6 Motion Control Partner node in ComfyUI for precise motion transfer from reference videos to character images ###### Lightricks - [LTX-2.5 API Video Generation in ComfyUI](https://docs.comfy.org/tutorials/partner-nodes/lightricks/ltx-2-5.md): Learn how to use the LTX-2.5 API nodes in ComfyUI with cloud workflows for text-to-video, image-to-video, and first-last-frame-to-video, with Fast and Pro model tiers. ###### Luma - [Luma Text to Video Partner Nodes ComfyUI Official Guide](https://docs.comfy.org/tutorials/partner-nodes/luma/luma-text-to-video.md): Learn how to use the Luma Text to Video Partner node in ComfyUI - [Luma Image to Video Partner Node](https://docs.comfy.org/tutorials/partner-nodes/luma/luma-image-to-video.md): Luma Image to Video Partner node workflow: convert a static image into video in ComfyUI, including required credits and node parameters. ###### MiniMax - [MiniMax H3 API Video Generation in ComfyUI](https://docs.comfy.org/tutorials/partner-nodes/minimax/minimax-h3.md): Learn how to use the MiniMax H3 API nodes in ComfyUI with cloud workflows for text-to-video, first/last-frame video, and reference-to-video, all with native stereo audio ###### Moonvalley - [Moonvalley Partner Nodes Official ComfyUI Example](https://docs.comfy.org/tutorials/partner-nodes/moonvalley/moonvalley-video-generation.md): This article introduces how to use Moonvalley Partner nodes for text-to-video, image-to-video, and video-to-video capabilities in ComfyUI. ###### Runway - [Runway Partner Nodes Video Generation ComfyUI Official Example](https://docs.comfy.org/tutorials/partner-nodes/runway/video-generation.md): This article will introduce how to use Runway nodes in ComfyUI for video generation workflows ###### Topaz - [Topaz Starlight Precise 2.5 - AI video upscaling](https://docs.comfy.org/tutorials/partner-nodes/topaz/video-enhance-starlight-precise-2-5.md): Upscale videos with Topaz Starlight Precise 2.5 in ComfyUI: sharper 4K output with reduced artifacts for live-action footage - [Topaz Astra Video Creative Upscale - AI video upscaling](https://docs.comfy.org/tutorials/partner-nodes/topaz/video-enhance-astra.md): Upscale and enhance videos with Topaz Astra in ComfyUI: Starlight (Astra) Fast upscaling with optional apo-8 frame interpolation - [Astra 2 - Creative diffusion video upscaling](https://docs.comfy.org/tutorials/partner-nodes/topaz/astra-2.md): What Astra 2 does for your videos in ComfyUI, plus creative upscaling with control over detail and style. ###### Wan - [Wan 3.0 Video Generation in ComfyUI](https://docs.comfy.org/tutorials/partner-nodes/wan/wan3-0.md): Learn how to use Wan 3.0 via Partner Nodes in ComfyUI for text-to-video, image-to-video, and reference-to-video generation with synchronized audio - [Wan2.7 Video Generation in ComfyUI](https://docs.comfy.org/tutorials/partner-nodes/wan/wan2-7.md): Learn how to use Wan2.7 via Partner Nodes in ComfyUI for image-to-video, text-to-video, reference-to-video, video continuation, and video editing ##### 3D - [3D Models](https://docs.comfy.org/tutorials/partner-nodes/3d/overview.md): Generate textured 3D assets from text prompts or images with state-of-the-art 3D models through Partner Nodes in ComfyUI ###### Hunyuan 3D - [Hunyuan 3D Partner Nodes Model Generation ComfyUI Official Example](https://docs.comfy.org/tutorials/partner-nodes/hunyuan3d/hunyuan3d-3-0.md): This article will introduce how to use Hunyuan 3D node's API in ComfyUI for 3D model generation ###### Meshy - [Meshy 7 in ComfyUI: Text to 3D and Image to 3D Workflows](https://docs.comfy.org/tutorials/partner-nodes/meshy/meshy-7.md): Generate production-ready 3D models with Meshy 7 in ComfyUI: text-to-3D and image-to-3D workflows with ultra mode, PBR textures, rigging, and animation - [Meshy 6 Partner Nodes Model Generation ComfyUI Official Example](https://docs.comfy.org/tutorials/partner-nodes/meshy/meshy-6.md): This article will introduce how to use Meshy 6 node's API in ComfyUI for 3D model generation ###### Rodin - [Rodin Partner Nodes Model Generation ComfyUI Official Example](https://docs.comfy.org/tutorials/partner-nodes/rodin/model-generation.md): This article will introduce how to use Rodin node's API in ComfyUI for model generation ###### Tripo - [Tripo P1 3D Model Generation ComfyUI Official Example](https://docs.comfy.org/tutorials/partner-nodes/tripo/tripo-p1.md): This guide explains how to use Tripo P1 Partner Nodes in ComfyUI to generate game-ready 3D models from text, images, or multiview references - [Tripo 3.1: High-Detail 3D Asset Generation ComfyUI Official Guide](https://docs.comfy.org/tutorials/partner-nodes/tripo/tripo-3-1.md): Learn how to generate high-detail 3D assets with Tripo 3.1 in ComfyUI via Partner Nodes, featuring high-density geometry and PBR-ready materials for production use. - [Tripo Partner Nodes Model Generation ComfyUI Official Example](https://docs.comfy.org/tutorials/partner-nodes/tripo/model-generation.md): This article will introduce how to use Tripo node's API in ComfyUI for model generation ##### Audio - [Audio Models](https://docs.comfy.org/tutorials/partner-nodes/audio/overview.md): Generate speech, music, and sound effects with state-of-the-art audio models through Partner Nodes in ComfyUI ###### Fish Audio - [Fish Audio: Text to Speech, Voice Cloning, and Speech to Text in ComfyUI](https://docs.comfy.org/tutorials/partner-nodes/fishaudio/fish-audio.md): Run Fish Audio TTS, voice cloning, and speech to text workflows in ComfyUI: template walkthroughs, node setup, and Cloud links - [Fish Audio Prompt Guide: writing prompts for Fish Audio TTS in ComfyUI](https://docs.comfy.org/tutorials/partner-nodes/fishaudio/prompt-guide.md): Complete prompt writing guide for Fish Audio partner nodes in ComfyUI: emotion tags, tone markers, audio effects, pauses, phoneme control, multi-speaker dialogue, and parameter tuning ###### ByteDance - [ByteDance Seed Audio 1.0 - Universal Audio Generation](https://docs.comfy.org/tutorials/partner-nodes/bytedance/seed-audio-1-0.md): Generate speech, music, sound effects, and multi-speaker dialogue from a single prompt with voice cloning, preset voices, and character-driven audio using Seed Audio 1.0 in ComfyUI ###### Sonilo - [Sonilo Partner Nodes Official ComfyUI Example](https://docs.comfy.org/tutorials/partner-nodes/sonilo/video-to-music.md): This article introduces how to use Sonilo Partner nodes for video-to-music and text-to-audio generation in ComfyUI. ##### LLMs - [LLMs](https://docs.comfy.org/tutorials/partner-nodes/language/overview.md): Use large language models (LLMs) for chat, prompt writing, and vision inside ComfyUI workflows through Partner Nodes ###### Anthropic - [Anthropic Claude Partner Nodes ComfyUI Official Example](https://docs.comfy.org/tutorials/partner-nodes/anthropic/claude.md): This article will introduce how to use Anthropic Claude Partner nodes in ComfyUI to complete conversational functions ###### Google - [Google Gemini Partner Nodes ComfyUI Official Example](https://docs.comfy.org/tutorials/partner-nodes/google/gemini.md): This article will introduce how to use Google Gemini Partner nodes in ComfyUI to complete conversational functions ###### OpenAI - [OpenAI Chat Partner Nodes ComfyUI Official Example](https://docs.comfy.org/tutorials/partner-nodes/openai/chat.md): This article will introduce how to use OpenAI Chat Partner nodes in ComfyUI to complete conversational functions - [GPT-6 Astra in ComfyUI](https://docs.comfy.org/tutorials/partner-nodes/openai/gpt-6-astra.md): Use OpenAI GPT-6 Astra through the OpenAI Chat node for complex reasoning, image analysis, prompt generation, and LLM-driven workflows in ComfyUI ###### OpenRouter - [OpenRouter LLM Partner Nodes ComfyUI Official Example](https://docs.comfy.org/tutorials/partner-nodes/openrouter/llm.md): Use the OpenRouter LLM partner node in ComfyUI for chat, reasoning, vision, and web-grounded answers across multiple frontier models.