docs: metadata batch 2 from the AEO tracker (30 live-verified weak pages)

basic-concepts/custom-nodes.mdx

@@ -1,6 +1,6 @@
 ---
 title: "Custom Nodes"
-description: "Learn about installing, enabling dependencies, updating, disabling, and uninstalling custom nodes in ComfyUI"
+description: "Custom nodes in ComfyUI: how they differ from Comfy Core nodes, plus installing, updating, enabling dependencies, disabling, and uninstalling them."
 icon: "window-maximize"
 ---
 
@@ -315,7 +315,7 @@
 
 The first step is to install Git, which is a command-line application for software version control. Git will download the ComfyUI manager from [github.com](https://github.com). Download and install Git from [git-scm.com](https://git-scm.com/).
 
 After installing Git, navigate to the ComfyUI server program directory and enter the folder labeled **custom_nodes**. Open a command window or terminal. Make sure the command line shows the current directory path as **custom_nodes**. Run the following command to clone the ComfyUI-Manager repository:
 
 ```bash
 git clone https://github.com/Comfy-Org/ComfyUI-Manager.git

basic-concepts/nodes.mdx

@@ -1,6 +1,6 @@
 ---
 title: "Nodes"
-description: "Understand the concept of a node in ComfyUI."
+description: "Nodes are ComfyUI's fundamental building blocks: independent Comfy Core or custom modules you connect with links to assemble complex workflows."
 icon: "circle"
 ---
 
@@ -159,12 +159,12 @@
 
 ![Disable Node Selection Toolbox](/images/concepts/node/setting_selection_toolbox.jpg)
 
 ## Subgraphs
 
 You can collapse a selection of nodes into one reusable subgraph node to tidy complex graphs and reuse the same structure across workflows.
 
 <Card title="Subgraph" icon="share-nodes" href="/interface/features/subgraph">
   Learn how to create, edit, nest, and publish subgraph blueprints to the node library.
 </Card>
 
 ## Custom Nodes

built-in-nodes/CheckpointLoaderSimple.mdx

@@ -1,6 +1,6 @@
 ---
-title: "CheckpointLoaderSimple - ComfyUI Built-in Node Documentation"
-description: "Documentation for CheckpointLoaderSimple node."
+title: "CheckpointLoaderSimple Node"
+description: "CheckpointLoaderSimple loads a diffusion checkpoint and splits it into model, CLIP, and VAE, auto-detecting files in ComfyUI/models/checkpoints."
 sidebarTitle: "CheckpointLoaderSimple"
 icon: "circle"
 mode: wide
@@ -8,7 +8,7 @@
 
 ## Overview
 
 Loads a diffusion model checkpoint file and decomposes it into three core components: the main model used for denoising latents, the CLIP text encoder, and the VAE image encoder/decoder. This node automatically detects all model files in the `ComfyUI/models/checkpoints` folder and any additional paths configured in your `extra_model_paths.yaml` file.
 
 ## Inputs
 
@@ -22,7 +22,7 @@
 
 | Output Name | Description | Data Type |
 | --- | --- | --- |
 | `MODEL` | The model used for denoising latents. This is the core diffusion model used for image generation. | MODEL |
 | `CLIP` | The CLIP model used for encoding text prompts, converting text descriptions into information that AI can understand. | CLIP |
 | `VAE` | The VAE model used for encoding and decoding images to and from latent space. | VAE |
 

built-in-nodes/MultiGPU_WorkUnits.mdx

@@ -1,6 +1,6 @@
 ---
-title: "MultiGPU_WorkUnits - ComfyUI Built-in Node Documentation"
-description: "Documentation for MultiGPUWorkUnits node."
+title: "MultiGPU CFG Split Node"
+description: "MultiGPU CFG Split node reference: run diffusion processing across multiple identical GPUs in one system, with speedups up to 1.95x."
 sidebarTitle: "MultiGPU_WorkUnits"
 icon: "circle"
 mode: wide
@@ -8,15 +8,15 @@
 
 ## Overview:
 
 The MultiGPU CFG Split Node allows diffusion processing to occur using multiple GPUs installed in the same system. Performance results are workflow dependent, but speedups of up to 1.95x have been measured in common workflows.
 
 ## Key Details:
 
 Mixing different GPU types is not supported, the installed GPUs must be the same (ie 2x 5090, or 2x 5080, etc.)
 
 ComfyUI will automatically detect multiple installed GPUs at startup.
 
 ## Supported GPUs:
 
 Any homogeneous dual GPU setups with Ampere+ architecture (e.g 2 x 3090 or 2 x RTX6000 Pro)
 
@@ -27,7 +27,7 @@
 * FLUX.2 Klein \- Base Versions  
 * Z-Image  
 * Stable Diffusion 3.5 Large  
 * Hunyuan Video  
 * Qwen-Image-Edit-2511  
 * Hunyuan-3D-v2.1  
 * SDXL
@@ -37,7 +37,7 @@
 | Parameter | Description | Data Type | Required | Range |
 | --- | --- | --- | --- | --- |
 | `model` | The model to prepare for MultiGPU CFG splitting before sampling. | MODEL | Yes | N/A |
 | `max_gpus` | The maximum number of identical GPUs to use for splitting the workload. Set this to the number of matching GPUs installed in your system. | INT | Yes | Minimum: 1<br />Step: 1<br />Default: 2 |
 
 ## Outputs
 
@@ -48,20 +48,20 @@
 ## Node:
 
 ![image1.png](/images/built-in-nodes/MultiGPU_WorkUnits/image1.png)  
 The max\_gpus field should be set to the maximum number of identical GPUs installed in the system. 
 
 **Node placement:**  The MultiGPU CFG Split needs to be placed between the Model Load node and Sampling node. If other nodes are connected to the model output of the model loader node, the MultiGPU CFG should be the last node in the chain before the Sampling node.
 
 ![image2.png](/images/built-in-nodes/MultiGPU_WorkUnits/image2.png)
 
 **Workflow Requirements:** The node works by splitting the diffusion workflow at the CFG level, due to this, the CFG in the workflow must be greater than CFG=1. Distilled workflows which require a CFG \=1 will not show a performance benefit when using the MultiGPU CFG Split node to run on multiple GPUs. 
 
 ## Verifying Multi-GPU Utilization
 
 When running a workflow with MultiGPU CFG Split enabled, you can look at the Windows Task Manager and select the performance category  
 ![image3.png](/images/built-in-nodes/MultiGPU_WorkUnits/image3.webp)  
 ![image4.png](/images/built-in-nodes/MultiGPU_WorkUnits/image4.webp)  
 You should see activity on both installed GPUs while the sampler is running in the workflow. 
 
 ## Sample Multi-GPU Workflow: (Wan 2.2 FP8)
 

built-in-nodes/sampling/ksampler.mdx

@@ -1,34 +1,34 @@
 ---
-title: "Ksampler - ComfyUI Built-in Node Documentation"
-description: "The Ksampler node is a commonly used sampling node in ComfyUI."
+title: "KSampler Node"
+description: "KSampler node reference: multi-step denoising of latent images with conditioning, sampler, and scheduler, the core of text-to-image workflows."
 sidebarTitle: "Ksampler"
 icon: "circle"
 ---
 
 ![Ksampler](/images/built-in-nodes/sampling/ksampler.jpg)
 
 The KSampler node performs multi-step denoising sampling on latent images. It combines positive and negative conditions (prompts) and uses specified sampling algorithms and schedulers to generate high-quality latent images. It is commonly used in AI image generation workflows like text-to-image and image-to-image.
 
 ## Parameter Description
 
 ### Input Parameters
 | Parameter    | Type         | Required | Default | Description                                                                                                        |
 | ------------ | ------------ | -------- | ------- | ------------------------------------------------------------------------------------------------------------------ |
 | model        | MODEL        | Yes      | None    | Model used for denoising (e.g. Stable Diffusion model)                                                             |
 | seed         | INT          | Yes      | 0       | Random seed to ensure reproducible results                                                                         |
 | steps        | INT          | Yes      | 20      | Number of denoising steps - more steps mean finer details but slower generation                                    |
 | cfg          | FLOAT        | Yes      | 8.0     | Classifier-Free Guidance scale - higher values better match prompts but too high impacts quality                   |
 | sampler_name | Enum         | Yes      | None    | Name of sampling algorithm, affects generation speed, style and quality                                            |
 | scheduler    | Enum         | Yes      | None    | Scheduler that controls the noise removal process                                                                  |
 | positive     | CONDITIONING | Yes      | None    | Positive conditions describing desired image content                                                               |
 | negative     | CONDITIONING | Yes      | None    | Negative conditions describing content to exclude                                                                  |
 | latent_image | LATENT       | Yes      | None    | Latent image to denoise, usually noise or output from previous step                                                |
 | denoise      | FLOAT        | Yes      | 1.0     | Denoising strength - 1.0 for full denoising, lower values preserve original structure, suitable for image-to-image |
 
 ### Output Parameters
 | Output  | Type   | Description                                              |
 | ------- | ------ | -------------------------------------------------------- |
 | samples | LATENT | Denoised latent image that can be decoded to final image |
 
 ## Usage Examples
 

development/comfyui-server/startup-flags.mdx

@@ -1,7 +1,7 @@
 ---
 title: "Startup Flags"
 sidebarTitle: "Startup Flags"
-description: "Complete reference for ComfyUI main.py command-line arguments"
+description: "ComfyUI startup flags reference: every main.py command-line argument from comfy/cli_args.py, plus how to add flags to Windows Portable .bat launchers."
 icon: "terminal"
 ---
 
@@ -82,7 +82,7 @@
 | `--oneapi-device-selector` `STRING` | — | oneAPI device selector string for Intel devices. |
 
 <Note>
   On Windows, when multiple NVIDIA GPUs are detected, ComfyUI uses GPU 0 only by default. To restore all GPUs, pass `--cuda-device all --disable-pinned-memory`. Multiple visible GPUs with pinned memory enabled can cause CUDA host-transfer failures.
 </Note>
 
 ## Precision & Inference
@@ -106,12 +106,12 @@
 | `--fp64-unet` | Run the diffusion model in fp64. |
 | `--bf16-unet` | Run the diffusion model in bf16. |
 | `--fp16-unet` | Run the diffusion model in fp16. |
 | `--fp8_e4m3fn-unet` | Store UNet weights in fp8 (e4m3fn). |
 | `--fp8_e5m2-unet` | Store UNet weights in fp8 (e5m2). |
 | `--fp8_e8m0fnu-unet` | Store UNet weights in fp8 (e8m0fnu). |
 
 Each FP8 flag suffix names an 8-bit float layout from the industry FP8 spec (ONNX / OCP):
 - **e4m3fn**: 4 exponent bits, 3 mantissa bits. Good balance of precision and range for model weights on NVIDIA Ada Lovelace and newer GPUs.
 - **e5m2**: 5 exponent bits, 2 mantissa bits. Wider dynamic range but lower precision than e4m3fn. Useful when weight magnitudes vary widely.
 - **e8m0fnu**: 8 exponent bits, 0 mantissa bits. Maximum dynamic range with no fractional precision. Typically used as a block scaling factor (powers of two only).
 
@@ -168,7 +168,7 @@
 ## Attention
 
 <Note>
   Cross-attention method flags are mutually exclusive. Split and quad attention are ignored when xformers is used.
 </Note>
 
 | Flag | Description |
@@ -178,9 +178,9 @@
 | `--use-pytorch-cross-attention` | Use PyTorch 2.0 cross attention. |
 | `--use-sage-attention` | Use Sage attention. |
 | `--use-flash-attention` | Use FlashAttention. |
 | `--disable-xformers` | Disable xformers. |
 | `--force-upcast-attention` | Force attention upcasting. Report if this fixes black images. Mutually exclusive with `--dont-upcast-attention`. |
 | `--dont-upcast-attention` | Disable all attention upcasting. For debugging only. |
 
 ## VRAM & Memory
 
@@ -196,16 +196,16 @@
 | `--novram` | — | Minimal VRAM usage when `--lowvram` is not enough. |
 | `--cpu` | — | Use CPU for everything (slow). |
 | `--reserve-vram` `GB` | OS-dependent | VRAM in GB to reserve for the OS and other software. |
 | `--async-offload` `[NUM_STREAMS]` | enabled on Nvidia | Async weight offloading. Optional stream count (default: 2). |
 | `--disable-async-offload` | — | Disable async weight offloading. |
 | `--disable-dynamic-vram` | — | Disable dynamic VRAM; use estimate-based model loading. |
 | `--enable-dynamic-vram` | auto on Nvidia | Enable dynamic VRAM on systems where it is not enabled by default. |
 | `--fast-disk` | disabled | Prefer disk-backed dynamic loading over unpinned RAM. Useful with fast NVMe. |
 | `--force-non-blocking` | disabled | Force non-blocking tensor operations. May help on non-Nvidia systems; can break some workflows. |
 | `--disable-smart-memory` | disabled | Aggressively offload to RAM instead of keeping models in VRAM. |
 | `--disable-pinned-memory` | disabled | Disable pinned memory use. |
 | `--mmap-torch-files` | disabled | Use mmap when loading ckpt/pt files. |
 | `--disable-mmap` | disabled | Do not use mmap when loading safetensors. |
 
 ## Performance & Debugging
 
@@ -254,12 +254,12 @@
 
 | Flag | Default | Description |
 |------|---------|-------------|
 | `--front-end-version` | `comfyanonymous/ComfyUI@latest` | Frontend version in `[owner]/[repo]@[version]` format. Requires internet to download from GitHub releases. Version can be `latest` or a semver (e.g. `1.0.0`). |
 | `--front-end-root` `PATH` | — | Local filesystem path to the frontend directory. Overrides `--front-end-version`. |
 | `--comfy-api-base` | `https://api.comfy.org` | Base URL for the ComfyUI API. |
 | `--database-url` | `sqlite:///<ComfyUI>/user/comfyui.db` | Database URL. Use `sqlite:///:memory:` for in-memory. |
 | `--enable-assets` | disabled | Enable the assets system (API routes, database sync, background scanning). |
 | `--feature-flag` `KEY[=VALUE]` | — | Set a server feature flag. Bare `KEY` sets true. Can be repeated. Booleans and numbers are auto-converted. |
 | `--list-feature-flags` | — | Print known CLI-settable feature flags as JSON and exit. |
 
 ```bash

installation/desktop/linux.mdx

@@ -1,6 +1,6 @@
 ---
-title: "Linux — Comfy Desktop"
-description: "Build and run Comfy Desktop from source on Linux"
+title: "Comfy Desktop on Linux"
+description: "Comfy Desktop on Linux: no official installer exists. Clone the repo and run from source instead. Requires Ubuntu 22.04+, x64, and Node.js v22 LTS."
 icon: "linux"
 sidebarTitle: "Linux"
 ---
@@ -12,7 +12,7 @@
 - **OS:** Linux (Ubuntu 22.04 or later recommended)
 - **Architecture:** x64
 - **Node.js:** v22 LTS or later
 - **pnpm:** v10 or later (enable with Corepack)
 - **GPU:** A dedicated GPU (NVIDIA / AMD) is recommended, but not required
 - **Disk Space:** At least 4.85 GB recommended per ComfyUI installation
 
@@ -29,7 +29,7 @@
 corepack enable
 ```
 
 If you do not use nvm, install Node.js 22 from [nodejs.org](https://nodejs.org/) instead.
 
 ### Clone and install
 
@@ -71,7 +71,7 @@
 pnpm run build:linux
 ```
 
 Artifacts land in `dist/`. If an AppImage fails because Chromium cannot create a sandbox, retry with `--no-sandbox`. That flag disables Electron sandboxing for every process.
 
 ## Removing leftover data
 

installation/desktop/overview.mdx

@@ -1,6 +1,6 @@
 ---
 title: "Comfy Desktop Overview"
-description: "Learn about Comfy Desktop — a modern desktop app for managing multiple ComfyUI installations"
+description: "Comfy Desktop overview: a desktop app that installs, manages, and launches multiple instances of ComfyUI, the node-based engine for generative AI."
 icon: "desktop"
 sidebarTitle: "Overview"
 ---

interface/credits.mdx

@@ -1,6 +1,6 @@
 ---
 title: "Credits Management"
-description: "In this article, we will introduce ComfyUI's credit management features, including how to obtain, use, and view credits."
+description: "Credits for Partner Nodes in ComfyUI: how to buy credits, track usage history, and monitor your balance from Settings > Credits."
 sidebarTitle: "Credits"
 icon: "coins"
 ---
@@ -56,7 +56,7 @@
 3. Choose your payment method
   - Credit Card
   - WeChat (only supported when paying in Comfy Credits)
   - Alipay (only supported when paying in Comfy Credits)
 4. Click the `Pay` button or the `Generate QR Code` button to complete the payment process
 </Step>
 
@@ -90,7 +90,7 @@
   </Accordion>
 
   <Accordion title="Why don't I see WeChat or Alipay payment options?">
   Please ensure you are paying in Comfy Credits, as WeChat and Alipay are only supported when paying in Comfy Credits
   </Accordion>
 
   <Accordion title="Do credits expire?">

interface/nodes-2.mdx

@@ -1,6 +1,6 @@
 ---
 title: "Nodes 2.0"
-description: "Learn about Nodes 2.0, the new Vue-based node rendering system in ComfyUI that enables faster development and richer interactions."
+description: "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."
 sidebarTitle: "Nodes 2.0"
 icon: "sparkles"
 ---

interface/overview.mdx

@@ -1,6 +1,6 @@
 ---
-title: "ComfyUI Interface Overview"
-description: "In this article, we will briefly introduce the basic user interface of ComfyUI, familiarizing you with the various parts of the ComfyUI interface."
+title: "Interface Overview"
+description: "ComfyUI interface tour covering the workspace parts used to build, organize, and debug workflows in the visual node editor."
 sidebarTitle: "Interface Overview"
 icon: "window"
 ---
@@ -51,7 +51,7 @@
 8. **Quick Access Button**: Opens the right-side panel.
 
 **Bottom Right Canvas Controls:**
 9. **Canvas Navigation Tools**: Can switch between move or pan modes, open the minimap, and toggle node connection display.
 
 ### Sidebar Panel Buttons
 

interface/shortcuts.mdx

@@ -1,6 +1,6 @@
 ---
-title: "ComfyUI Keyboard Shortcuts and Custom Settings"
-description: "Keyboard and mouse shortcuts for ComfyUI and related settings"
+title: "Keyboard and Mouse Shortcuts"
+description: "ComfyUI keyboard and mouse shortcuts: the full default list, plus how to view and customize keybindings in the in-app settings menu."
 sidebarTitle: "Keybinding"
 icon: "keyboard"
 ---
@@ -27,24 +27,24 @@
 <Tab title="Windows/Linux">
 | Shortcut                           | Command                                                                                                        |
 |------------------------------------|--------------------------------------------------------------------------------------------------------------------|
 | Ctrl + Enter                       | Queue prompt                                                                                                      |
 | Ctrl + Shift + Enter               | Queue prompt (Front)                                                                                          |
 | Ctrl + Alt + Enter                 | Interrupt                                                                                                          |
 | Ctrl + Z / Ctrl + Y                | Undo/Redo                                                                                                          |
 | Ctrl + S                           | Save workflow                                                                                                      |
 | Ctrl + O                           | Load workflow                                                                                                      |
 | Ctrl + A                           | Select all nodes                                                                                                   |
 | Alt + C                            | Collapse/uncollapse selected nodes                                                                                 |
 | Ctrl + M                           | Mute/unmute selected nodes                                                                                         |
 | Ctrl + B                           | Bypass/unbypass selected nodes                                                                                     |
 | Delete<br/>Backspace               | Delete selected nodes                                                                                              |
 | Backspace                          | Clear workflow                                                                                                     |
 | Space                              | Move canvas when holding and moving cursor                                                                         |
 | Ctrl + Click<br/>Shift + Click     | Add clicked node to selection                                                                                      |
 | Ctrl + C/Ctrl + V                  | Copy and paste selected nodes (without maintaining connections to outputs of unselected nodes)                     |
 | Ctrl + C/Ctrl + Shift + V          | Copy and paste selected nodes (maintaining connections from outputs of unselected nodes to inputs of pasted nodes) |
 | Shift + Drag                       | Move multiple selected nodes at the same time                                                                      |
 | Ctrl + G                           | Add frame to selected nodes                                                                                        |
 | Ctrl + ,                           | Show settings dialog                                                                                               |
 | Alt + =                            | Zoom in (canvas)                                                                                                   |
 | Alt + -                            | Zoom out (canvas)                                                                                                  |
@@ -63,25 +63,25 @@
 <Tab title="MacOS">
 | Shortcut                              | Command                                                                                                           |
 |--------------------------------------|--------------------------------------------------------------------------------------------------------------------|
 | Cmd ⌘ + Enter                        | Queue prompt                                                                                                       |
 | Cmd ⌘ + Shift + Enter                | Queue prompt (Front)                                                                                               |
 | Cmd ⌘ + Alt + Enter                  | Interrupt                                                                                                          |
 | Cmd ⌘ + Z/Cmd ⌘ + Y                  | Undo/Redo                                                                                                          |
 | Cmd ⌘ + S                            | Save workflow                                                                                                      |
 | Cmd ⌘ + O                            | Load workflow                                                                                                      |
 | Cmd ⌘ + A                            | Select all nodes                                                                                                   |
 | Opt ⌥ + C                            | Collapse/uncollapse selected nodes                                                                                 |
 | Cmd ⌘ + M                            | Mute/unmute selected nodes                                                                                         |
 | Cmd ⌘ + B                            | Bypass/unbypass selected nodes                                                                                     |
 | Delete<br/>Backspace                 | Delete selected nodes                                                                                              |
 | Backspace                            | Clear workflow                                                                                                     |
 | Space                                | Move canvas when holding and moving cursor                                                                         |
 | Cmd ⌘ + Click<br/>Shift + Click      | Add clicked node to selection                                                                                      |
 | Cmd ⌘ + C / Cmd ⌘ + V                | Copy and paste selected nodes (without maintaining connections to outputs of unselected nodes)                     |
 | Cmd ⌘ + C / Cmd ⌘ + Shift + V        | Copy and paste selected nodes (maintaining connections from outputs of unselected nodes to inputs of pasted nodes) |
 | Shift + Drag                         | Move multiple selected nodes at the same time                                                                      |
 | Cmd ⌘ + G                            | Add frame to selected nodes                                                                                        |
 | Cmd ⌘ + ,                            | Show settings dialog                                                                                               |
 | Opt ⌥ + =                            | Zoom in (canvas)                                                                                                   |
 | Opt ⌥ + -                            | Zoom out (canvas)                                                                                                  |
 | .                                    | Fit view to selected nodes                                                                                         |

manager/configuration.mdx

@@ -1,7 +1,7 @@
 ---
-title: Configuration
+title: "ComfyUI-Manager Configuration"
 sidebarTitle: Config
-description: Configure ComfyUI-Manager settings
+description: "ComfyUI-Manager configuration reference: config.ini paths and options, security levels, and the protected system path introduced in V3.38."
 ---
 
 ## Configuration paths
@@ -116,7 +116,7 @@
 
 List pip spec requirements in `pip_auto_fix.list` (similar to `requirements.txt`). It will automatically restore specified versions when starting ComfyUI or when versions get mismatched during custom node installations. `--index-url` can be used.
 
 ### Use aria2 as downloader
 
 For faster downloads, you can configure ComfyUI-Manager to use aria2. See the [aria2 setup guide](https://github.com/Comfy-Org/ComfyUI-Manager/blob/main/docs/en/use_aria2.md).
 

manager/troubleshooting.mdx

@@ -1,7 +1,7 @@
 ---
-title: Troubleshooting
+title: "ComfyUI-Manager Troubleshooting"
 sidebarTitle: Troubleshooting
-description: Resolve common ComfyUI-Manager issues
+description: "ComfyUI-Manager troubleshooting: fixes for custom git executable paths in config.ini, Manager self-update failures, and install errors."
 ---
 
 ## Common issues

specs/workflow_json.mdx

@@ -1,6 +1,6 @@
 ---
 title: "Workflow JSON"
-description: "JSON schema for a ComfyUI workflow."
+description: "Workflow JSON schema for the ComfyUI workflow file format (v1.0 plus legacy v0.4), covering nodes, links, groups, and version fields."
 ---
 
 The workflow JSON is defined using [JSON Schema](https://json-schema.org/). Changes to this schema will be discussed in the [rfcs repo](https://github.com/comfy-org/rfcs).
@@ -30,11 +30,11 @@
                     "links_ontop": {
                       "type": "boolean"
                     },
                     "align_to_grid": {
                       "type": "boolean"
                     }
                   },
                   "additionalProperties": true
                 }
               ]
             },
@@ -59,7 +59,7 @@
               "type": "number"
             }
           },
           "additionalProperties": true
         },
         "groups": {
           "type": "array",
@@ -91,7 +91,7 @@
               "color": {
                 "type": "string"
               },
               "font_size": {
                 "type": "number"
               },
               "locked": {
@@ -102,7 +102,7 @@
               "title",
               "bounding"
             ],
             "additionalProperties": true
           }
         },
         "nodes": {
@@ -139,7 +139,7 @@
                       "0",
                       "1"
                     ],
                     "additionalProperties": true
                   },
                   {
                     "type": "array",
@@ -172,7 +172,7 @@
                       "0",
                       "1"
                     ],
                     "additionalProperties": true
                   },
                   {
                     "type": "array",
@@ -198,17 +198,17 @@
                   "pinned": {
                     "type": "boolean"
                   },
                   "allow_interaction": {
                     "type": "boolean"
                   },
                   "horizontal": {
                     "type": "boolean"
                   },
                   "skip_repeated_outputs": {
                     "type": "boolean"
                   }
                 },
                 "additionalProperties": true
               },
               "order": {
                 "type": "number"
@@ -246,7 +246,7 @@
                         "null"
                       ]
                     },
                     "slot_index": {
                       "anyOf": [
                         {
                           "type": "integer"
@@ -261,7 +261,7 @@
                     "name",
                     "type"
                   ],
                   "additionalProperties": true
                 }
               },
               "outputs": {
@@ -301,7 +301,7 @@
                         }
                       ]
                     },
                     "slot_index": {
                       "anyOf": [
                         {
                           "type": "integer"
@@ -316,7 +316,7 @@
                     "name",
                     "type"
                   ],
                   "additionalProperties": true
                 }
               },
               "properties": {
@@ -326,23 +326,23 @@
                     "type": "string"
                   }
                 },
                 "additionalProperties": true
               },
               "widgets_values": {
                 "anyOf": [
                   {
                     "type": "array"
                   },
                   {
                     "type": "object",
                     "additionalProperties": {}
                   }
                 ]
               },
               "color": {
                 "type": "string"
               },
               "bgcolor": {
                 "type": "string"
               }
             },
@@ -356,7 +356,7 @@
               "mode",
               "properties"
             ],
             "additionalProperties": true
           }
         },
         "links": {
@@ -367,7 +367,7 @@
               "id": {
                 "type": "number"
               },
               "origin_id": {
                 "anyOf": [
                   {
                     "type": "integer"
@@ -377,7 +377,7 @@
                   }
                 ]
               },
               "origin_slot": {
                 "anyOf": [
                   {
                     "type": "integer"
@@ -387,7 +387,7 @@
                   }
                 ]
               },
               "target_id": {
                 "anyOf": [
                   {
                     "type": "integer"
@@ -397,7 +397,7 @@
                   }
                 ]
               },
               "target_slot": {
                 "anyOf": [
                   {
                     "type": "integer"
@@ -423,19 +423,19 @@
                   }
                 ]
               },
               "parentId": {
                 "type": "number"
               }
             },
             "required": [
               "id",
               "origin_id",
               "origin_slot",
               "target_id",
               "target_slot",
               "type"
             ],
             "additionalProperties": true
           }
         },
         "reroutes": {
@@ -446,7 +446,7 @@
               "id": {
                 "type": "number"
               },
               "parentId": {
                 "type": "number"
               },
               "pos": {
@@ -465,7 +465,7 @@
                       "0",
                       "1"
                     ],
                     "additionalProperties": true
                   },
                   {
                     "type": "array",
@@ -482,7 +482,7 @@
                   }
                 ]
               },
               "linkIds": {
                 "anyOf": [
                   {
                     "type": "array",
@@ -500,7 +500,7 @@
               "id",
               "pos"
             ],
             "additionalProperties": true
           }
         },
         "extra": {
@@ -535,7 +535,7 @@
                                 "0",
                                 "1"
                               ],
                               "additionalProperties": true
                             },
                             {
                               "type": "array",
@@ -557,7 +557,7 @@
                         "scale",
                         "offset"
                       ],
                       "additionalProperties": true
                     },
                     "info": {
                       "type": "object",
@@ -593,9 +593,9 @@
                         "modified",
                         "software"
                       ],
                       "additionalProperties": true
                     },
                     "linkExtensions": {
                       "type": "array",
                       "items": {
                         "type": "object",
@@ -603,15 +603,15 @@
                           "id": {
                             "type": "number"
                           },
                           "parentId": {
                             "type": "number"
                           }
                         },
                         "required": [
                           "id",
                           "parentId"
                         ],
                         "additionalProperties": true
                       }
                     },
                     "reroutes": {
@@ -622,7 +622,7 @@
                           "id": {
                             "type": "number"
                           },
                           "parentId": {
                             "type": "number"
                           },
                           "pos": {
@@ -641,7 +641,7 @@
                                   "0",
                                   "1"
                                 ],
                                 "additionalProperties": true
                               },
                               {
                                 "type": "array",
@@ -658,7 +658,7 @@
                               }
                             ]
                           },
                           "linkIds": {
                             "anyOf": [
                               {
                                 "type": "array",
@@ -676,11 +676,11 @@
                           "id",
                           "pos"
                         ],
                         "additionalProperties": true
                       }
                     }
                   },
                   "additionalProperties": true
                 }
               ]
             },
@@ -704,7 +704,7 @@
               "hash": {
                 "type": "string"
               },
               "hash_type": {
                 "type": "string"
               },
               "directory": {
@@ -716,7 +716,7 @@
               "url",
               "directory"
             ],
             "additionalProperties": false
           }
         }
       },

troubleshooting/custom-node-issues.mdx

@@ -1,6 +1,6 @@
 ---
-title: "How to Troubleshoot and Solve ComfyUI Issues"
-description: "Troubleshoot and fix problems caused by custom nodes and extensions"
+title: "Troubleshooting Custom Node Issues"
+description: "Fix ComfyUI custom node issues: disable all custom nodes with --disable-all-custom-nodes, then binary-search to isolate, fix, or remove the broken node."
 icon: "puzzle-piece"
 sidebarTitle: "Custom Node Issues"
 ---
@@ -140,7 +140,7 @@
    - Custom nodes using strict dependency versions (e.g., `torch==2.4.1`) while other plugins use different versions (e.g., `torch>=2.4.2`), causing conflicts after installation
    - Network issues preventing successful dependency installation
 
    When problems involve Python environment interdependencies and versions, troubleshooting becomes more complex and requires knowledge of Python environment management, including how to install and uninstall dependencies
    </Tab>
 </Tabs>
 

troubleshooting/overview.mdx

@@ -1,7 +1,7 @@
 ---
 title: "How to Troubleshoot and Solve ComfyUI Issues"
-description: "Common ComfyUI issues, solutions, and how to report bugs effectively"
+description: "ComfyUI troubleshooting guide: rule out custom nodes first, fix common core issues, and file a bug report with the right details."
 icon: "lightbulb"
 sidebarTitle: "Overview"
 ---
 
@@ -91,7 +91,7 @@
 
 <Tabs>
 <Tab title="Windows">
 - **Unsupported device**: Comfy Desktop Windows only supports NVIDIA GPUs with CUDA. Use [ComfyUI Portable](/installation/comfyui_portable_windows) or [manual installation](/installation/manual_install) for other GPUs
 - **Installation fails**: Run installer as administrator, ensure at least 15GB disk space
 - **Maintenance page**: Check [mirror settings](/installation/desktop/usage/settings#advanced) if downloads fail
 - **Missing models**: Models are not copied during migration, only linked. Verify model paths
@@ -110,7 +110,7 @@
 ### Manual Installation Issues
 
 <Note>
 The documentation may be slightly out of date. If an issue occurs, please manually verify whether a newer stable version of pytorch or any of the listed libraries exists. Refer to resources like the [pytorch installation matrix](https://pytorch.org/get-started/locally/) or the [ROCm website](https://rocm.docs.amd.com/projects/install-on-linux/en/develop/install/3rd-party/pytorch-install.html#using-a-wheels-package).
 </Note>
 
 **Python version conflicts:**
@@ -132,7 +132,7 @@
 # Install dependencies
 pip install -r requirements.txt
 
 # For NVIDIA GPUs (CUDA 13.0)
 pip install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cu130
 
 # For AMD GPUs (Linux only - ROCm 7.2)
@@ -189,7 +189,7 @@
 echo 'export LD_LIBRARY_PATH=$(python -c "import site; print(site.getsitepackages()[0])")/nvidia/nvjitlink/lib:$LD_LIBRARY_PATH' >> ~/.bashrc
 ```
 
 4. **Alternative: Use ldconfig:**
 ```bash
 # Check current library cache
 ldconfig -p | grep cuda
@@ -285,7 +285,7 @@
 
 ### AMD GPU Issues
 
 **ROCm support (Linux only):**
 ```bash
 # Install stable ROCm PyTorch (7.2 at the time of writing)
 pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/rocm7.2
@@ -294,7 +294,7 @@
 pip install --pre torch torchvision torchaudio --index-url https://download.pytorch.org/whl/nightly/rocm7.2
 ```
 
 **Unsupported AMD GPUs:**
 ```bash
 # For RDNA2 or older (6700, 6600)
 HSA_OVERRIDE_GFX_VERSION=10.3.0 python main.py
@@ -340,7 +340,7 @@
 
 **"Torch not compiled with CUDA enabled" error:**
 
 On Intel GPUs this error means ComfyUI tried to use CUDA because the XPU backend was not available. Do not follow the NVIDIA CUDA reinstallation steps above. Intel GPUs use XPU, not CUDA.
 
 Check whether PyTorch can see the Intel GPU:
 
@@ -428,7 +428,7 @@
       <Tab title="Windows">
       ```bash
       # System info
       systeminfo | findstr /C:"OS Name" /C:"OS Version"
 
       # GPU info
       wmic path win32_VideoController get name
@@ -474,7 +474,7 @@
 **Error Messages:**
 - Full error text from console/terminal
 - Browser console errors (F12 → Console tab)
 - Any crash logs or error dialogs
 </Step>
 
 <Step title="Additional Context">

tutorials/3d/hunyuan3D-2.mdx

@@ -1,6 +1,6 @@
 ---
 title: "ComfyUI Hunyuan3D-2 Examples"
-description: "This guide will demonstrate how to use Hunyuan3D-2 in ComfyUI to generate 3D assets."
+description: "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."
 sidebarTitle: "Hunyuan3D-2"
 ---
 
@@ -8,19 +8,19 @@
 
 # Hunyuan3D 2.0 Introduction
 
 ![Hunyuan 3D 2](https://raw.githubusercontent.com/Tencent/Hunyuan3D-2/main/assets/images/e2e-1.gif)
 ![Hunyuan 3D 2](https://raw.githubusercontent.com/Tencent/Hunyuan3D-2/main/assets/images/e2e-2.gif)
 [Hunyuan3D 2.0](https://github.com/Tencent/Hunyuan3D-2) 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 2.0 adopts a two-stage generation approach, first generating a geometry model without textures, then synthesizing high-resolution texture maps. This effectively separates the complexity of shape and texture generation. Below are the two core components of Hunyuan3D 2.0:
 
 1. **Geometry Generation Model (Hunyuan3D-DiT)**: Based on a flow diffusion Transformer architecture, it generates untextured geometric models that precisely match input conditions.
 2. **Texture Generation Model (Hunyuan3D-Paint)**: Combines geometric conditions and multi-view diffusion techniques to add high-resolution textures to models, supporting PBR materials.
 
 **Key Advantages**
 
 - **High-Precision Generation**: Sharp geometric structures, rich texture colors, support for PBR material generation, achieving near-realistic lighting effects.
 - **Diverse Usage Methods**: Provides code calls, Blender plugins, Gradio applications, and online experience through the official website, suitable for different user needs.
 - **Lightweight and Compatibility**: The Hunyuan3D-2mini model requires only 5GB VRAM, the standard version needs 6GB VRAM for shape generation, and the complete process (shape + texture) requires only 12GB VRAM.
 
 Recently (March 18, 2025), Hunyuan3D 2.0 also introduced a multi-view shape generation model (Hunyuan3D-2mv), which supports generating more detailed geometric structures from inputs at different angles.
@@ -224,7 +224,7 @@
 ![Hunyuan3D-2 workflow](https://raw.githubusercontent.com/Comfy-Org/example_workflows/main/3d/hunyuan3d-2/hunyuan3d-non-multiview-train.webp)
 
 Download the image below we will use it as input image.
 ![ComfyUI Hunyuan 3D 2 workflow](https://raw.githubusercontent.com/Comfy-Org/example_workflows/main/3d/hunyuan3d-2/hunyuan_3d_v2_non_multiview_train.png)
 
 ### 2. Manual Model Installation
 
@@ -260,20 +260,20 @@
 
 **Hunyuan3D-2mini Series**
 
 | Model                 | Description               | Date       | Parameters | Huggingface                                                                                |
 |-----------------------|---------------------------|------------|------------|--------------------------------------------------------------------------------------------|
 | Hunyuan3D-DiT-v2-mini | Mini Image to Shape Model | 2025-03-18 | 0.6B       | [Visit](https://huggingface.co/tencent/Hunyuan3D-2mini/tree/main/hunyuan3d-dit-v2-mini)    |
 
 **Hunyuan3D-2mv Series**
 
 | Model                    | Description                                                                                                 | Date       | Parameters | Huggingface                                                                              |
 |--------------------------|-------------------------------------------------------------------------------------------------------------|------------|------------|------------------------------------------------------------------------------------------|
 | Hunyuan3D-DiT-v2-mv-Fast | Guidance Distillation Version, can halve DIT inference time                                                 | 2025-03-18 | 1.1B       | [Visit](https://huggingface.co/tencent/Hunyuan3D-2mv/tree/main/hunyuan3d-dit-v2-mv-fast) |
 | Hunyuan3D-DiT-v2-mv      | Multi-view Image to Shape Model, suitable for 3D creation requiring multiple angles to understand the scene | 2025-03-18 | 1.1B       | [Visit](https://huggingface.co/tencent/Hunyuan3D-2mv/tree/main/hunyuan3d-dit-v2-mv)      |
 
 **Hunyuan3D-2 Series**
 
 | Model                   | Description                 | Date       | Parameters | Huggingface                                                                           |
 |-------------------------|-----------------------------|------------|------------|---------------------------------------------------------------------------------------|
 | Hunyuan3D-DiT-v2-0-Fast | Guidance Distillation Model | 2025-02-03 | 1.1B       | [Visit](https://huggingface.co/tencent/Hunyuan3D-2/tree/main/hunyuan3d-dit-v2-0-fast) |
 | Hunyuan3D-DiT-v2-0      | Image to Shape Model        | 2025-01-21 | 1.1B       | [Visit](https://huggingface.co/tencent/Hunyuan3D-2/tree/main/hunyuan3d-dit-v2-0)      |

tutorials/audio/ace-step/ace-step-v1.mdx

@@ -1,6 +1,6 @@
 ---
 title: "ComfyUI ACE-Step Native Example"
-description: "This guide will help you create dynamic music using the ACE-Step model in ComfyUI"
+description: "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."
 sidebarTitle: "ACE-Step 1.0"
 ---
 
@@ -44,7 +44,7 @@
 
 ## ACE-Step ComfyUI Audio-to-Audio Workflow
 
 Similar to image-to-image workflows, you can input a piece of music and use the workflow below to resample and generate music. You can also adjust the difference from the original audio by controlling the `denoise` parameter in the `Ksampler`.
 
 ### 1. Download Workflow File
 
@@ -145,7 +145,7 @@
 
 #### Lyric Structure Tags
 
 - [outro]
 - [verse]
 - [chorus]
 - [bridge]
@@ -189,15 +189,15 @@
 
 Currently, ACE-Step supports 19 languages, but the following ten languages have better support:
 - English
 - Chinese: [zh]
 - Russian: [ru]
 - Spanish: [es]
 - Japanese: [ja]
 - German: [de]
 - French: [fr]
 - Portuguese: [pt]
 - Italian: [it]
 - Korean: [ko]
 
 <Note>
 The language tags above have not been fully tested at the time of writing this documentation. If any language tag is incorrect, please [submit an issue to our documentation repository](https://github.com/Comfy-Org/docs/issues) and we will make timely corrections.

tutorials/basic/inpaint.mdx

@@ -1,26 +1,26 @@
 ---
 title: ComfyUI Inpainting Workflow
-description: This guide will introduce you to the inpainting workflow in ComfyUI, walk you through an inpainting example, and cover topics like using the mask editor
+description: "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."
 sidebarTitle: "Inpaint"
 ---
 
 This article will introduce the concept of inpainting in AI image generation and guide you through creating an inpainting workflow in ComfyUI. We'll cover:
 - Using inpainting workflows to modify images
 - Using the ComfyUI mask editor to draw masks
 - `VAE Encoder (for Inpainting)` node
 
 ## About Inpainting
 
 In AI image generation, we often encounter situations where we're satisfied with the overall image but there are elements we don't want or that contain errors. Simply regenerating might produce a completely different image, so using inpainting to fix specific parts becomes very useful.
 
 It's like having an **artist (AI model)** paint a picture, but we're still not satisfied with the specific details. We need to tell the artist **which areas to adjust (mask)**, and then let them **repaint (inpaint)** according to our requirements.
 
 Common inpainting scenarios include:
 - **Defect Repair:** Removing unwanted objects, fixing incorrect AI-generated body parts, etc.
 - **Detail Optimization:** Precisely adjusting local elements (like modifying clothing textures, adjusting facial expressions)
 - And other scenarios
 
 ## ComfyUI Inpainting Workflow Example
 
 ### Model and Resource Preparation
 
@@ -28,29 +28,29 @@
 
 Download the [512-inpainting-ema.safetensors](https://huggingface.co/Comfy-Org/stable_diffusion_2.1_repackaged/blob/main/512-inpainting-ema.safetensors)  file and put it in your `ComfyUI/models/checkpoints` folder:
 
 #### 2. Inpainting Asset
 
 Please download the following image which we'll use as input:
 
 ![ComfyUI Inpainting Input Image](/images/tutorial/basic/inpaint/input.png)
 
 <Note>This image already contains an alpha channel (transparency mask), so you don't need to manually draw a mask. This tutorial will also cover how to use the mask editor to draw masks.</Note>
 
 #### 3. Inpainting Workflow
 
 Download the image below and **drag it into ComfyUI** to load the workflow:
 
 ![ComfyUI Inpainting Workflow](https://raw.githubusercontent.com/Comfy-Org/example_workflows/refs/heads/main/image/basic/sd1.5_inpaint.png)
 
 <Tip>
 Images containing workflow JSON in their metadata can be directly dragged into ComfyUI or loaded using the menu `Workflows` -> `Open (ctrl+o)`.
 </Tip>
 
 ### ComfyUI Inpainting Workflow Example Explanation
 
 Follow the steps in the diagram below to ensure the workflow runs correctly.
 
 ![ComfyUI Inpainting Workflow](/images/tutorial/basic/inpaint/inpaint_workflow.png)
 
 1. Ensure `Load Checkpoint` loads `512-inpainting-ema.safetensors`
 2. Upload the input image to the `Load Image` node
@@ -58,10 +58,10 @@
 
 For comparison, here's the result using the [v1-5-pruned-emaonly-fp16.safetensors](https://huggingface.co/Comfy-Org/stable-diffusion-v1-5-archive/blob/main/v1-5-pruned-emaonly-fp16.safetensors) model:
 
 ![SD1.5 Inpainting Result](/images/tutorial/basic/inpaint/inpaint_sd1.5_pruned_emaonly.png)
 
 You will find that the results generated by the [512-inpainting-ema.safetensors](https://huggingface.co/Comfy-Org/stable_diffusion_2.1_repackaged/blob/main/512-inpainting-ema.safetensors) model have better inpainting effects and more natural transitions.
 This is because this model is specifically designed for inpainting, which helps us better control the generation area, resulting in improved inpainting effects.
 
 Do you remember the analogy we've been using? Different models are like artists with varying abilities, but each artist has their own limits. Choosing the right model can help you achieve better generation results.
 
@@ -94,16 +94,16 @@
 2. Use eraser to correct mistakes
 3. Click `Save` when finished
 
 The drawn content will be used as a Mask input to the VAE Encoder (for Inpainting) node for encoding
 
 Then try adjusting your prompts and generating again until you achieve satisfactory results.
 
 ## VAE Encoder (for Inpainting) Node
 
 Comparing this workflow with [Text-to-Image](/tutorials/basic/text-to-image) and [Image-to-Image](/tutorials/basic/image-to-image), you'll notice the main differences are in the VAE section's conditional inputs.
 In this workflow, we use the **VAE Encoder (for Inpainting)** node, specifically designed for inpainting to help us better control the generation area and achieve better results.
 
 ![VAE Encoder (for Inpainting) Node](/images/comfy_core/latent/inpaint/vae_encode_for_inpainting.jpg)
 
 **Input Types**
 
@@ -112,7 +112,7 @@
 | `pixels`       | Input image to be encoded into latent space.                                                                                                          |
 | `vae`          | VAE model used to encode the image from pixel space to latent space.                                                                                  |
 | `mask`         | Image mask specifying which areas need modification.                                                                                                  |
 | `grow_mask_by` | Pixel value to expand the original mask outward, ensuring a transition area around the mask to avoid hard edges between inpainted and original areas. |
 
 **Output Types**
 

tutorials/basic/outpaint.mdx

@@ -1,26 +1,26 @@
 ---
-title: "ComfyUI Outpainting Workflow Example"
-description: This guide will introduce you to the outpainting workflow in ComfyUI and walk you through an outpainting example
+title: "Outpainting Workflow Example"
+description: "Outpainting workflow in ComfyUI: extend an image beyond its borders using the Pad Image for Outpainting node and inpainting-model techniques."
 sidebarTitle: "Outpaint"
 ---
 
 This guide will introduce you to the concept of outpainting in AI image generation and how to create an outpainting workflow in ComfyUI. We will cover:
 - Using outpainting workflow to extend an image
 - Understanding and using outpainting-related nodes in ComfyUI
 - Mastering the basic outpainting process
 
 ## About Outpainting
 
 In AI image generation, we often encounter situations where an existing image has good composition but the canvas area is too small, requiring us to extend the canvas to get a larger scene. This is where outpainting comes in.
 
 Basically, it requires similar content to [Inpainting](/tutorials/basic/inpaint), but we use different nodes to **build the mask**.
 
 Outpainting applications include:
 - **Scene Extension:** Expand the scene range of the original image to show a more complete environment
 - **Composition Adjustment:** Optimize the overall composition by extending the canvas
 - **Content Addition:** Add more related scene elements to the original image
 
 ## ComfyUI Outpainting Workflow Example Explanation
 
 ### Preparation
 
@@ -33,23 +33,23 @@
 
 Prepare an image you want to extend. In this example, we will use the following image:
 
 ![ComfyUI Outpainting Input Image](/images/tutorial/basic/outpaint/input.png)
 
 #### 3. Outpainting Workflow
 
 Download the image below and **drag it into ComfyUI** to load the workflow:
 
 ![ComfyUI Outpainting Workflow](https://raw.githubusercontent.com/Comfy-Org/example_workflows/refs/heads/main/image/basic/outpaint.png)
 
 <Tip>
 Images containing workflow JSON in their metadata can be directly dragged into ComfyUI or loaded using the menu `Workflows` -> `Open (ctrl+o)`.
 </Tip>
 
 ### Outpainting Workflow Usage Explanation
 
 ![ComfyUI Outpainting Workflow Diagram](/images/tutorial/basic/outpaint/outpainting_workflow.jpg)
 
 The key steps of the outpainting workflow are as follows:
 
 1. Load the locally installed model file in the `Load Checkpoint` node
 2. Click the `Upload` button in the `Load Image` node to upload your image
@@ -57,9 +57,9 @@
 
 In this workflow, we mainly use the `Pad Image for outpainting` node to control the direction and range of image extension. This is actually an [Inpaint](/tutorials/basic/inpaint) workflow, but we use different nodes to build the mask.
 
 ### Pad Image for outpainting Node
 
 ![Pad Image for outpainting Node](/images/comfy_core/image/pad_image_for_outpainting.jpg)
 
 This node accepts an input image and outputs an extended image with a corresponding mask, where the mask is built based on the node parameters.
 
@@ -85,7 +85,7 @@
 
 After processing by the `Pad Image for outpainting` node, the output image and mask preview are as follows:
 
 ![Pad Image for outpainting Node Results](/images/tutorial/basic/outpaint/pad_Image_for_outpainting_result.jpg)
 
 You can see the corresponding output results:
 - The `Image` output is the extended image

tutorials/controlnet/controlnet.mdx

@@ -1,6 +1,6 @@
 ---
 title: "ComfyUI ControlNet Usage Example"
-description: "This guide will introduce you to the basic concepts of ControlNet and demonstrate how to generate corresponding images in ComfyUI"
+description: "ControlNet in ComfyUI: control image generation with condition images instead of trial-and-error prompting, plus a step-by-step workflow example."
 sidebarTitle: "ControlNet"
 ---
 
@@ -8,10 +8,10 @@
 It typically requires numerous generation attempts to produce a satisfactory image. However, the emergence of **ControlNet** has effectively addressed this challenge.
 
 ControlNet is a conditional control generation model based on diffusion models (such as Stable Diffusion), 
 first proposed by [Lvmin Zhang](https://lllyasviel.github.io/) and Maneesh Agrawala et al. in 2023 in the paper [Adding Conditional Control to Text-to-Image Diffusion Models](https://arxiv.org/abs/2302.05543).
 
 ControlNet models significantly enhance the controllability of image generation and the ability to reproduce details by introducing multimodal input conditions,
 such as edge detection maps, depth maps, and pose keypoints.
 
 These conditioning constraints make image generation more controllable, allowing multiple ControlNet models to be used simultaneously during the drawing process for better results.
 
@@ -40,8 +40,8 @@
 
 > Image source: [ComfyUI ControlNet aux](https://github.com/Fannovel16/comfyui_controlnet_aux)
 
 Since the current **Comfy Core** nodes do not include all types of **preprocessors**, in the actual examples in this documentation, we will provide pre-processed images.
 However, in practical use, you may need to use custom nodes to preprocess images to meet the requirements of different ControlNet models. Below are some relevant custom nodes:
 
 - [ComfyUI-Advanced-ControlNet](https://github.com/Kosinkadink/ComfyUI-Advanced-ControlNet)
 - [ComfyUI ControlNet aux](https://github.com/Fannovel16/comfyui_controlnet_aux)
@@ -101,13 +101,13 @@
 ## Related Node Explanations
 ### Load ControlNet Node Explanation
 
 ![load controlnet](/images/comfy_core/loaders/load_controlnet_model.jpg)
 
 Models located in `ComfyUI\models\controlnet` will be detected by ComfyUI and can be loaded through this node.
 
 ### Apply ControlNet Node Explanation
 
 ![apply controlnet](/images/comfy_core/conditioning/controlnet/apply_controlnet.jpg)
 
 This node accepts the ControlNet model loaded by `load controlnet` and generates corresponding control conditions based on the input image.
 
@@ -132,11 +132,11 @@
 | `negative`     | Negative conditioning data processed by ControlNet |
 
 You can use chain connections to apply multiple ControlNet models, as shown in the image below. You can also refer to the [Mixing ControlNet Models](/tutorials/controlnet/mixing-controlnets) guide to learn more about combining multiple ControlNet models.
 ![apply controlnet chain link](/images/tutorial/controlnet/apply_controlnet_chain_link.jpg)
 
 <Note>
 You might see the `Apply ControlNet(Old)` node in some early workflows, which is an early version of the ControlNet node. It is currently deprecated and not visible by default in search and node lists.
 ![apply controlnet old](/images/comfy_core/conditioning/controlnet/apply_controlnet_old.jpg)
 To enable it, go to **Settings** --> **comfy** --> **Node** and enable the `Show deprecated nodes in search` option. However, it's recommended to use the new node.
 </Note>
 

tutorials/controlnet/depth-controlnet.mdx

@@ -1,12 +1,12 @@
 ---
-title: "ComfyUI Depth ControlNet Usage Example"
-description: "This guide will introduce you to the basic concepts of Depth ControlNet and demonstrate how to generate corresponding images in ComfyUI"
+title: "Depth ControlNet Workflow Example"
+description: "Depth ControlNet workflow in ComfyUI: how depth maps encode distance, and how to use one to control scene structure during image generation."
 sidebarTitle: "Depth ControlNet"
 ---
 
 ## Introduction to Depth Maps and Depth ControlNet
 
 A depth map is a special type of image that uses grayscale values to represent the distance between objects in a scene and the observer or camera. In a depth map, the grayscale value is inversely proportional to distance: brighter areas (closer to white) indicate objects that are closer, while darker areas (closer to black) indicate objects that are farther away.
 
 ![Depth Image](https://raw.githubusercontent.com/Comfy-Org/example_workflows/main/controlnet/depth_input.png)
 
@@ -71,7 +71,7 @@
 
 Based on different creative needs, you can combine Depth ControlNet with other types of ControlNet to achieve better results:
 
 1. **Depth + Lineart**: Maintain spatial relationships while reinforcing outlines, suitable for architecture, products, and character design
 2. **Depth + Pose**: Control character posture while maintaining correct spatial relationships, suitable for character scenes
 
 For more information on using multiple ControlNet models together, please refer to the [Mixing ControlNet](/tutorials/controlnet/mixing-controlnets) example.

tutorials/flux/flux-1-controlnet.mdx

@@ -1,11 +1,11 @@
 ---
 title: "ComfyUI Flux.1 ControlNet Examples"
-description: "This guide will demonstrate workflow examples using Flux.1 ControlNet."
+description: "FLUX.1 Canny and Depth workflow examples for ComfyUI: add ControlNet-style structural control to FLUX.1 with Black Forest Labs' FLUX.1 Tools."
 sidebarTitle: "Flux.1 ControlNet"
 ---
 
 ![Flux.1 Canny Controlnet](/images/tutorial/flux/flux-1-canny-controlnet.png)
 ![Flux.1 Depth Controlnet](/images/tutorial/flux/flux-1-depth-controlnet.png)
 
 ## FLUX.1 ControlNet Model Introduction
 
@@ -27,13 +27,13 @@
 We will use the full version of **FLUX.1-Canny-dev** and **FLUX.1-Depth-dev-lora** to complete the workflow examples.
 
 <Tip>
 All workflow images's Metadata contains the corresponding model download information. You can load the workflows by:
 - Dragging them directly into ComfyUI
 - Or using the menu `Workflows` -> `Open（ctrl+o）`
 
 If you're not using the Desktop Version or some models can't be downloaded automatically, please refer to the manual installation sections to save the model files to the corresponding folder.
 
 For image preprocessors, you can use the following custom nodes to complete image preprocessing. In this example, we will provide processed images as input.
 - [ComfyUI-Advanced-ControlNet](https://github.com/Kosinkadink/ComfyUI-Advanced-ControlNet)
 - [ComfyUI ControlNet aux](https://github.com/Fannovel16/comfyui_controlnet_aux)
 </Tip>
@@ -100,7 +100,7 @@
 
 ### 3. Step-by-Step Workflow Execution
 
 ![ComfyUI Flux.1 Canny Controlnet Step Process](/images/tutorial/flux/flow_diagram_flux_1_canny_dev.jpg)
 
 1. Make sure `ae.safetensors` is loaded in the `Load VAE` node
 2. Make sure `flux1-canny-dev.safetensors` is loaded in the `Load Diffusion Model` node
@@ -184,7 +184,7 @@
 
 ### 3. Step-by-Step Workflow Execution
 
 ![ComfyUI Flux.1 Depth Controlnet Step Process](/images/tutorial/flux/flow_diagram_flux_1_depth_dev_lora.jpg)
 
 1. Make sure `flux1-dev.safetensors` is loaded in the `Load Diffusion Model` node
 2. Make sure `flux1-depth-dev-lora.safetensors` is loaded in the `LoraLoaderModelOnly` node
@@ -201,16 +201,16 @@
 
 Use [ComfyUI-Advanced-ControlNet](https://github.com/Kosinkadink/ComfyUI-Advanced-ControlNet) or [ComfyUI ControlNet aux](https://github.com/Fannovel16/comfyui_controlnet_aux) to complete image preprocessing
 
 ## Community Versions of Flux Controlnets
 
 XLab and InstantX + Shakker Labs have released Controlnets for Flux.
 
 **InstantX:**
 - [FLUX.1-dev-Controlnet-Canny](https://huggingface.co/InstantX/FLUX.1-dev-Controlnet-Canny/blob/main/diffusion_pytorch_model.safetensors)
 - [FLUX.1-dev-ControlNet-Depth](https://huggingface.co/Shakker-Labs/FLUX.1-dev-ControlNet-Depth/blob/main/diffusion_pytorch_model.safetensors)
 - [FLUX.1-dev-ControlNet-Union-Pro](https://huggingface.co/Shakker-Labs/FLUX.1-dev-ControlNet-Union-Pro/blob/main/diffusion_pytorch_model.safetensors)
 
 **XLab**: [flux-controlnet-collections](https://huggingface.co/XLabs-AI/flux-controlnet-collections) 
 
 Place these files in the `ComfyUI/models/controlnet` directory.
 

tutorials/flux/flux-1-kontext-dev.mdx

@@ -1,7 +1,7 @@
 ---
 title: "ComfyUI Flux Kontext Dev Native Workflow Example"
-description: "ComfyUI Flux Kontext Dev Native Workflow Example."
+description: "FLUX.1 Kontext Dev workflow for ComfyUI: edit images with text and image input using Black Forest Labs' open-source 12B multimodal editing model."
 sidebarTitle: "Flux.1 Kontext Dev"
 ---
 
 import PromptTechniques from "/snippets/tutorials/flux/prompt-techniques.mdx";

tutorials/image/ideogram/ideogram-v4.mdx

@@ -1,6 +1,6 @@
 ---
 title: "ComfyUI Ideogram 4.0 Open-Source Model Tutorial"
-description: "Learn how to use the Ideogram 4.0 open-source model in ComfyUI"
+description: "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."
 sidebarTitle: "Ideogram 4.0"
 ---
 
@@ -82,7 +82,7 @@
 
 <CardGroup cols={2}>
   <Card title="Learn about Subgraph" icon="book-open" href="/interface/features/subgraph">
     This workflow uses Subgraph nodes for modular processing. Check the Subgraph documentation to learn how to customize and extend.
   </Card>
 </CardGroup>
 
@@ -90,7 +90,7 @@
 
 1. Download and place the models in the correct directories (see table above)
 2. Download and drag the workflow file into ComfyUI
 3. Enter your prompt (natural language or structured JSON) in the Ideogram4 subgraph node
 4. (Optional) Adjust resolution using the `ResolutionSelector` node
 5. Click `Run` or use shortcut `Ctrl(cmd) + Enter` to generate the image
 6. View the result in the `Save Image` node. Output files are saved to `ComfyUI/output/`
@@ -103,7 +103,7 @@
 
 ## Live Conversation with Ideogram & ComfyOrg
 
 A special live conversation with Mohammad Norouzi (CEO, Ideogram) and Yoland Yan (CEO, ComfyOrg), hosted by Purz & Rob.
 
 <iframe
   className="w-full aspect-video rounded-xl"

tutorials/partner-nodes/luma/luma-image-to-video.mdx

@@ -1,28 +1,28 @@
 ---
-title: "Luma Image to Video Partner Nodes ComfyUI Official Example"
-description: "Learn how to use the Luma Image to Video Partner node in ComfyUI"
+title: "Luma Image to Video Partner Node"
+description: "Luma Image to Video Partner node workflow: convert a static image into video in ComfyUI, including required credits and node parameters."
 sidebarTitle: "Luma Image to Video"
 ---
 
 import ReqHint from "/snippets/tutorials/partner-nodes/req-hint.mdx";
 import UpdateReminder from "/snippets/tutorials/update-reminder.mdx";
 
 The Luma Image to Video node allows you to convert static images into smooth, dynamic videos using Luma AI's advanced technology, bringing life and motion to your images.
 
 In this guide, we'll show you how to set up a workflow for image-to-video conversion using this node.
 
 <ReqHint/>
 <UpdateReminder/>
 
 ## Image to Video Workflow with Luma Partner Nodes
 
 The Luma Image to Video node requires at least one image input (`first_image` or `last_image`) along with text prompts to determine the video's motion effects. In this guide, we've created an example using `first_image` and `luma_concepts` to showcase Luma AI's video generation capabilities.
 
 ### 1. Download the Workflow
 
 The workflow information is included in the metadata of the video below. Download and drag it into ComfyUI to load the workflow.
 
 ![Luma Image to Video Workflow](https://raw.githubusercontent.com/Comfy-Org/example_workflows/main/api_nodes/luma/i2v/luma_i2v.mp4)
 
 Download the following image to use as input:
 
@@ -30,11 +30,11 @@
 
 ### 2. Follow the Workflow Steps
 
 ![Luma Image to Video Workflow Steps](/images/tutorial/api_nodes/luma/luma_i2v_step_guide.jpg)
 
 Follow these basic steps to run the workflow:
 1. Upload your input image in the `first_image` node
 2. (Optional) Write prompts in the Luma Image to Video node to describe how you want the image animated
 3. (Optional) Modify the `Luma Concepts` node to control camera movement for professional cinematography
 4. Click `Run` or use `Ctrl(cmd) + Enter` to generate the video
 5. Once the API returns results, view the generated video in the `Save Video` node. The video will also be saved to the `ComfyUI/output/` directory
@@ -42,7 +42,7 @@
 ### 3. Additional Notes
 
 - **Image Input Requirements**: At least one of `first_image` or `last_image` is required, with a maximum of 1 image per input
 - **Luma Concepts**: Controls camera movement for professional video effects
 - **Seed Parameter**: Only determines if the node should rerun, doesn't affect generation results
 - **Enable Input Nodes**: Right-click on purple "Bypass" mode nodes and set "mode" to "always" to enable inputs
 - **Model Selection**: Different video generation models have unique characteristics, adjustable via the model parameter

tutorials/partner-nodes/overview.mdx

@@ -1,6 +1,6 @@
 ---
 title: "Partner Nodes"
-description: "In this article, we will introduce ComfyUI's Partner Nodes and related information."
+description: "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."
 sidebarTitle: "Overview"
 ---
 
@@ -82,7 +82,7 @@
 A powerful application of Partner Nodes is combining the output of external models with local nodes. For example:
 
 - Using GPT-Image-1 to generate a base image, then transforming it into video with a local `wan` node
 - Combining externally generated images with local upscaling or style transfer nodes
 - Creating hybrid workflows that leverage the advantages of both closed-source and open-source models
 
 This flexibility makes ComfyUI a truly universal generative AI interface, integrating various AI capabilities into a unified workflow, opening up more possibilities

tutorials/partner-nodes/pricing.mdx

@@ -1,6 +1,6 @@
 ---
-title: "Pricing"
-description: "This article lists the pricing of the current Partner Nodes."
+title: "Partner Node Pricing"
+description: "Partner Node pricing in credits for every provider, including Anthropic, OpenAI, Kling, and Luma, broken down by model, token type, and generation type."
 sidebarTitle: "Pricing"
 mode: "wide"
 ---
@@ -19,18 +19,18 @@
 
 Optional images add tokens billed at the same model input rates.
 
 ## Beeble
 
 ### Video: SwitchX Video Edit
 
 | max_resolution | Credits           |
 | :------------- | :---------------- |
 | 720p           | 30.17 / 30 frames |
 | 1080p          | 90.52 / 30 frames |
 
 ### Image: SwitchX Image Edit
 
 | max_resolution | Credits     |
 | :------------- | :---------- |
 | 720p           | 30.17 / run |
 | 1080p          | 90.52 / run |
@@ -42,8 +42,8 @@
 | Node                       |            Credits            |
 | :------------------------- | :---------------------------: |
 | Flux 1.1 [pro] Ultra Image |          12.66 / run          |
 | Flux.1 Kontext [pro] Image |          8.44 / run           |
 | Flux.1 Kontext [max] Image |          16.88 / run          |
 | Flux.1 Expand Image        |          10.55 / run          |
 | Flux.1 Fill Image          |          10.55 / run          |
 | Flux Erase Image           | 6.33 / run + 0.84 / extra MP  |
@@ -73,27 +73,27 @@
 | Flux Video Upscale | creative  | 30.17              |
 | Flux Video Upscale | precise   | 21.12              |
 
 ## Bria
 
 ### Image
 
 | Node                         | Credits    |
 | :--------------------------- | :--------- |
 | Bria Generative Fill         | 9.05 / run |
 | Bria Eraser                  | 6.03 / run |
 | Bria Expand Image            | 6.03 / run |
 | Bria Increase Resolution     | 6.03 / run |
 | Bria FIBO Image Edit         | 8.44 / run |
 | Bria Remove Image Background | 3.8 / run  |
 
 ### Video
 
 | Node                                       | Credits      |
 | :----------------------------------------- | :----------- |
 | Bria Remove Video Background               | 10.55 / sec  |
 | Bria Video Green Screen                    | 10.55 / sec  |
 | Bria Video Replace Background              | 10.55 / sec  |
 | Bria Remove Video Background (Transparent) | 10.55 / sec  |
 
 ## ByteDance
 
@@ -109,19 +109,19 @@
 
 Optional images and videos add input tokens at the input rate.
 
 ### Image: ByteDance Seedream
 
 Per successfully generated image.
 
 | model                                               | Credits / image      |
 | :-------------------------------------------------- | :------------------- |
 | seedream 5.0 pro (`seedream-5-0-pro-260628`)        | 9.50 (1K) / 18.99 (2K) |
 | seedream 5.0 lite (`seedream-5-0-260128`)           | 7.39                 |
 | seedream-4-5-251128                                 | 8.44                 |
 | seedream-4-0-250828                                 | 6.33                 |
 | Seedream 5.0 Pro Layer Separation                   | 6.79 (1K, 1.5K) / 13.58 (2K) |
 
 Seedream 5.0 Pro uses resolution-based billing: **1K** (≤2.61 MP, **9.50 credits**) and **2K** (>2.61 MP, **18.99 credits**). The first image in each request is free. Each additional image beyond the first (including both output and input/reference images) adds **0.63 credits**.
 
 ### Image: ByteDance Image (deprecated)
 
@@ -129,16 +129,16 @@
 | :---------------------- | :-------------- |
 | seedream-3-0-t2i-250415 | 6.33            |
 
 ### Video: Seedance 2.5
 
 Token-based billing. Estimated token consumption = **(input video duration + output video duration) × output video width × output video height × output video frame rate ÷ 1024**. When input is text, image, or audio only, input video duration = 0. Actual usage from the API is authoritative.
 
 | Model        | Resolution | Video input | Credits / 1K tokens |
 | :----------- | :--------- | :---------- | ------------------: |
 | Seedance 2.5 | 480p, 720p | no          | 3.229               |
 | Seedance 2.5 | 480p, 720p | yes         | 1.931               |
 | Seedance 2.5 | 1080p      | no          | 3.530               |
 | Seedance 2.5 | 1080p      | yes         | 2.112               |
 
 **Video input** means a reference video is connected. Text, image, and audio references count as no video input. Minimum token consumption limits apply when the input includes video: if the estimated consumption is below the limit, billing uses the minimum.
 
@@ -149,7 +149,7 @@
 | 480p       | 155.1                     | 166.9 – 649.3                 |
 | 720p       | 348.8                     | 375.4 – 1459.8                |
 | 1080p      | 857.8                     | 923.9 – 3592.7                |
 ### Video: Seedance 2.0
 
 480p and 720p share the same rate. Fast and Mini do not support 1080p or 4K.
 
@@ -161,24 +161,24 @@
 
 | Model             | Resolution | Video input | Credits / 1K tokens |
 | :---------------- | :--------- | :---------- | ------------------: |
 | Seedance 2.0      | 480p, 720p | no          | 2.112               |
 | Seedance 2.0      | 480p, 720p | yes         | 1.297               |
 | Seedance 2.0      | 1080p      | no          | 2.323               |
 | Seedance 2.0      | 1080p      | yes         | 1.418               |
 | Seedance 2.0      | 4k         | no          | 1.207               |
 | Seedance 2.0      | 4k         | yes         | 0.724               |
 | Seedance 2.0 Fast | 480p, 720p | no          | 1.690               |
 | Seedance 2.0 Fast | 480p, 720p | yes         | 0.996               |
 | Seedance 2.0 Mini | 480p, 720p | no          | 1.056               |
 | Seedance 2.0 Mini | 480p, 720p | yes         | 0.634               |
 
 **Video input** means reference video is connected. Text, image, and audio references count as no video input.
 
 For video-to-video inputs, a minimum token usage may apply. Seedance 2.0 outputs at 24fps.
 
 ### Video: Seedance 1.x
 
 Billed by tokens (same estimation formula as Seedance 2.0). Unlike Seedance 2.0, the **token rate does not change by resolution**; resolution changes how many tokens a clip uses (via width × height in the formula), so higher resolutions cost more.
 
 **Token rate**
 
@@ -191,7 +191,7 @@
 
 **Approximate credits / 10 sec** (scale with `duration ÷ 10`. Ranges reflect aspect ratio.)
 
 | model                        | resolution | generate_audio | Credits / 10 sec |
 | :--------------------------- | :--------- | :------------- | :--------------- |
 | seedance-1-5-pro-251215      | 480p       | off            | 25.32            |
 | seedance-1-5-pro-251215      | 480p       | on             | 50.64            |
@@ -218,11 +218,11 @@
 | seedance-1-0-lite-i2v-250428 | 480p       | 35.87 – 37.98    |
 | seedance-1-0-lite-i2v-250428 | 720p       | 78.07 – 86.51    |
 
 ### Video: ByteDance vCube Video Enhance
 
 Billed per second of enhanced output. The rates below are per second at 30 fps or below. Rates from 31 to 60 fps double the rate, and rates above 60 fps quadruple it. With **source** resolution or frame rate selected, the rate scales with the source video (approximately 1× to 4×).
 
 | tool_version | Resolution | Credits / second |
 | :----------- | :--------- | :--------------- |
 | standard     | 720p       | ~1.04            |
 | standard     | 1080p      | ~2.08            |
@@ -267,7 +267,7 @@
 
 ### Image: Upscale
 
 **Magnific Image Upscale (Creative)** and **Magnific Image Upscale (Precise V2)** share the same billing. Upscaling runs in 2x steps (`2x` = 1 step, `4x` = 2, `8x` = 3, `16x` = 4). After each step, pixel count ×4; each step is priced by the input megapixels at that step.
 
 | Input MP at step | Credits / 2x step |
 | :--------------- | :---------------- |
@@ -303,30 +303,30 @@
 | Gemini 2.5 Pro (`gemini-2.5-pro`)                       |            0.26375 | 2.11                |
 | Gemini 2.5 Flash (`gemini-2.5-flash`)                   |             0.0633 | 0.5275              |
 
 ### Image: Nano Banana
 
 Token-based billing.
 
 | Model                                            | Input credits / 1K | Output (text) credits / 1K | Output (image) credits / 1K |
 | :----------------------------------------------- | -----------------: | -------------------------: | :-------------------------- |
 | Nano Banana (`gemini-2.5-flash-image`)           |             0.0633 |                     0.5275 | 6.33                        |
 | Nano Banana Pro (`gemini-3-pro-image`)           |             0.5064 |                      3.0384 | 30.38                       |
 | Nano Banana 2 (`gemini-3.1-flash-image`)         |             0.1266 |                      0.7596 | 15.19                       |
 | Nano Banana 2 Lite (`gemini-3.1-flash-lite-image`) |           0.0633 |                     0.3798 | 7.60                        |
 
 ### Video: Google Gemini Omni
 
 Token-based billing with separate rates for text and video output tokens. Approximate cost: **~30.8 credits/second** (~$0.146/s).
 
 | Model                                                          | Input credits / 1K | Output (text) credits / 1K | Output (video) credits / 1K |
 | :------------------------------------------------------------- | -----------------: | -------------------------: | :-------------------------- |
 | Gemini Omni Flash (`gemini-omni-flash-preview`)                |              0.453 |                      2.716 | 5.28                        |
 
 ### Video: Google Veo
 
 Total credits = **(credits / sec) × duration**.
 
 | Model                                  | Resolution  | generate_audio | Credits / sec |
 | :------------------------------------- | :---------- | :------------- | :------------ |
 | veo-2.0-generate-001                   | —           | —              | 105.5         |
 | veo-3.1-lite                           | 720p        | false          | 6.33          |
@@ -376,7 +376,7 @@
 | HeyGen Video Translate      | precision mode                                 | 20.13 / sec       |
 | HeyGen Text to Speech       | N/A                                            | ~0.20 / sec       |
 
 ## Hitpaw
 
 ### Video: HitPaw Video Enhance
 
@@ -475,7 +475,7 @@
 
 ## Ideogram
 
 | Node           | turbo | Character reference | rendering_speed | Credits / image |
 | :------------- | :---- | :------------------ | :-------------- | :-------------- |
 | Ideogram V1    | false | —                   | —               | 18.1            |
 | Ideogram V1    | true  | —                   | —               | 6.03            |
@@ -487,16 +487,16 @@
 
 | Node              | quality   | resolution | Credits / image |
 | :---------------- | :-------- | :--------- | :-------------- |
 | Ideogram & Pruna P-Image  | VERY_LOW  | 1K         | 0.91            |
 | Ideogram & Pruna P-Image  | VERY_LOW  | 2K         | 1.81            |
 | Ideogram & Pruna P-Image  | LOW       | 1K         | 2.26            |
 | Ideogram & Pruna P-Image  | LOW       | 2K         | 4.53            |
 | Ideogram & Pruna P-Image  | MEDIUM    | 1K         | 3.02            |
 | Ideogram & Pruna P-Image  | MEDIUM    | 2K         | 6.03            |
 | Ideogram & Pruna P-Image  | HIGH      | 1K         | 4.53            |
 | Ideogram & Pruna P-Image  | HIGH      | 2K         | 9.05            |
 
 ## Krea
 
 | Model               | Style reference | Moodboard | Credits / run |
 | :------------------ | :-------------- | :-------- | :------------ |

tutorials/video/wan/wan-ati.mdx

@@ -1,6 +1,6 @@
 ---
-title: "Wan ATI ComfyUI Native Workflow Tutorial"
-description: "Using trajectory control for video generation."
+title: "Wan ATI Native Workflow"
+description: "Wan ATI trajectory control in ComfyUI: draw trajectories to direct object, region, and camera motion in generated video, built on Wan2.1."
 sidebarTitle: "WAN2l1 ATI"
 ---