Save 4 hours! We auto-setup your workflow! Free!

Drop your workflow.json — we handle every dependency, custom node, and model. Just open the link and run.

Auto-Setup Workflow Json (Free) Now!
ComfyUI > Nodes > ComfyUI-PoseAtlas > PoseAtlas 图库

ComfyUI Node: PoseAtlas 图库

Class Name

PoseAtlasLoader

Category
PoseAtlas
Author
mugicha-AI (Account age: 1123days)
Extension
ComfyUI-PoseAtlas
Latest Updated
2026-11-05
Github Stars
0.08K

How to Install ComfyUI-PoseAtlas

Install this extension via the ComfyUI Manager by searching for ComfyUI-PoseAtlas
  • 1. Click the Manager button in the main menu
  • 2. Select Custom Nodes Manager button
  • 3. Enter ComfyUI-PoseAtlas in the search bar
After installation, click the Restart button to restart ComfyUI. Then, manually refresh your browser to clear the cache and access the updated list of nodes.

Visit ComfyUI Online for ready-to-use ComfyUI environment

  • Free trial available
  • 16GB VRAM to 80GB VRAM GPU machines
  • 400+ preloaded models/nodes
  • Freedom to upload custom models/nodes
  • 200+ ready-to-run workflows
  • 100% private workspace with up to 200GB storage
  • Dedicated Support

Run ComfyUI Online

PoseAtlas 图库 Description

PoseAtlasLoader enables selection and retrieval of diverse visual references from RuiC-PoseAtlas.

PoseAtlas 图库:

PoseAtlasLoader is a versatile node designed to facilitate the selection and retrieval of images from the RuiC-PoseAtlas library, which encompasses a diverse collection of poses, costumes, and portraits. This node allows you to access a comprehensive database of 4,345 entries, each meticulously categorized and described. The PoseAtlasLoader node is particularly beneficial for AI artists seeking to incorporate detailed and varied visual references into their projects. By providing options to select different collections and rendering styles, it enables you to tailor the output to your specific artistic needs, whether you're looking for line sketches, grayscale depth maps, or full-color images. The node's functionality is seamlessly integrated into the ComfyUI environment, ensuring a smooth and efficient workflow for accessing and utilizing these rich visual resources.

PoseAtlas 图库 Input Parameters:

collection

The collection parameter allows you to choose from three distinct categories within the RuiC-PoseAtlas library: poses, costumes, and portraits. Each category offers a unique set of images tailored to different artistic needs. The default value is "姿势" (poses), which includes 1,439 entries. Selecting a different collection will require you to reselect the specific item you wish to use. This parameter is crucial for narrowing down the type of visual reference you need for your project.

pose

The pose parameter lets you select a specific image from the chosen collection. This parameter is populated with labels from the entire library, allowing you to choose the exact visual reference you need. The default value is the first label in the list, if available. This selection directly impacts the image that will be loaded and used in your project, making it essential for obtaining the desired visual output.

render

The render parameter determines the rendering style of the image, specifically for the poses collection. You can choose between "线稿" (line sketch) and "深度" (depth map). The default is "线稿," which provides a line sketch of the pose. The depth map option offers a grayscale image where white areas are closer to the camera. This parameter is not applicable to the costumes and portraits collections, which only have original images.

invert_mask

The invert_mask parameter is a boolean option that allows you to invert the mask of the image. By default, this is set to False, meaning the mask is not inverted. When set to True, the mask will be inverted, which can be useful for certain compositional techniques or effects where the inverse of the mask is required.

PoseAtlas 图库 Output Parameters:

image

The image output provides the selected visual reference as an image tensor. This output is crucial for integrating the chosen image into your AI art project, allowing you to manipulate or analyze it further within the ComfyUI environment.

mask

The mask output delivers a mask tensor corresponding to the selected image. This mask can be used for various purposes, such as isolating specific parts of the image or applying effects selectively. The mask is particularly useful when working with images that have transparency or require compositional adjustments.

item_name

The item_name output is a string that describes the selected image, including its category and specific attributes. This output is valuable for keeping track of the images used in your project, providing a clear reference to the source and characteristics of each visual element.

PoseAtlas 图库 Usage Tips:

  • Ensure that you have downloaded the necessary images by running the provided download script before using the node to avoid missing file errors.
  • Utilize the render parameter to switch between line sketches and depth maps for poses, depending on the visual style you aim to achieve in your project.

PoseAtlas 图库 Common Errors and Solutions:

PoseAtlas: 找不到条目 '<pose>'

  • Explanation: This error occurs when the specified pose cannot be found in the library.
  • Solution: Double-check the pose name for typos or ensure that the correct collection is selected.

PoseAtlas: 图片未下载 —— <path>

  • Explanation: This error indicates that the image file has not been downloaded to your local system.
  • Solution: Run the python scripts/download_images.py script in the node directory to download the necessary images, then restart ComfyUI.

PoseAtlas 图库 Related Nodes

Go back to the extension to check out more related nodes.
ComfyUI-PoseAtlas
RunComfy
Copyright 2025 RunComfy. All Rights Reserved.

RunComfy is the premier ComfyUI platform, offering ComfyUI online environment and services, along with ComfyUI workflows featuring stunning visuals. RunComfy also provides AI Models, enabling artists to harness the latest AI tools to create incredible art.

PoseAtlas 图库