ComfyUI > Nodes > ComfyUI-UniRig > MIA: Auto Rig

ComfyUI Node: MIA: Auto Rig

Class Name

MIAAutoRig

Category
UniRig/MIA
Author
PozzettiAndrea (Account age: 2326days)
Extension
ComfyUI-UniRig
Latest Updated
2026-03-04
Github Stars
0.36K

How to Install ComfyUI-UniRig

Install this extension via the ComfyUI Manager by searching for ComfyUI-UniRig
  • 1. Click the Manager button in the main menu
  • 2. Select Custom Nodes Manager button
  • 3. Enter ComfyUI-UniRig 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

MIA: Auto Rig Description

MIAAutoRig automates rigging of humanoid models, converting static meshes to animation-ready FBX.

MIA: Auto Rig:

MIAAutoRig is a sophisticated node designed to streamline the process of rigging humanoid models, making them animatable with ease. Utilizing the Make-It-Animatable (MIA) framework, this node automates the complex task of creating a rig for 3D models, which is essential for animation. The node's primary function is to convert static 3D meshes into fully rigged models by sampling points from the mesh surface, normalizing and localizing joints, predicting blend weights, joint positions, and poses, and finally exporting the rigged model in FBX format. This automation significantly reduces the time and effort required for manual rigging, allowing artists to focus more on creative aspects rather than technical details. The MIAAutoRig node is particularly beneficial for AI artists who want to bring their static models to life without delving into the intricacies of rigging, offering a fast and efficient solution to achieve high-quality animation-ready models.

MIA: Auto Rig Input Parameters:

trimesh

This parameter represents the 3D mesh that you want to rig. It is crucial as it serves as the base model from which the rigging process begins. The mesh should be well-defined and clean to ensure accurate rigging results. There are no specific minimum or maximum values, but the quality of the mesh can significantly impact the final rigging outcome.

model

The model parameter is a configuration dictionary that contains settings for the rigging process. It includes details such as the data type (dtype) used during the rigging, which can affect the precision and performance of the operation. The default value for dtype is "fp32", which balances performance and precision.

fbx_name

This optional parameter allows you to specify a custom name for the output FBX file. If not provided, the node generates a default name based on the current timestamp. This parameter does not affect the rigging process itself but helps in organizing and identifying output files.

no_fingers

A boolean parameter that determines whether finger bones should be included in the rigging process. When set to True, finger bones are excluded, simplifying the rig for models where detailed hand animation is not required. The default value is True.

use_normal

This boolean parameter indicates whether to use normal vectors during the rigging process. Enabling this option can improve the accuracy of joint placement by considering the surface normals of the mesh. The default value is False.

reset_to_rest

A boolean parameter that, when set to True, resets the model to a rest pose after rigging. This is useful for ensuring that the rigged model starts from a neutral position, which can be beneficial for animation. The default value is True.

MIA: Auto Rig Output Parameters:

fbx_output_path

This output parameter provides the file path to the rigged FBX model. It is the final result of the rigging process, containing the fully rigged and animatable model. This file can be imported into various 3D software for further animation and rendering.

MIA: Auto Rig Usage Tips:

  • Ensure your 3D mesh is clean and well-defined to achieve the best rigging results. Meshes with errors or poor topology can lead to suboptimal rigging outcomes.
  • Use the no_fingers parameter to simplify the rig if detailed hand animation is not necessary, which can save processing time and resources.
  • Consider enabling use_normal for models with complex surfaces to improve joint placement accuracy, especially if the model has intricate details.

MIA: Auto Rig Common Errors and Solutions:

Mesh Visual Type Error

  • Explanation: This error occurs when the mesh does not have a visual type or material attribute, which is necessary for the rigging process.
  • Solution: Ensure that your mesh has a defined visual type and material. Check the mesh properties and add a material if necessary.

Model Configuration Error

  • Explanation: This error arises when the model configuration dictionary is missing required settings or contains invalid values.
  • Solution: Verify that the model configuration dictionary includes all necessary settings, such as dtype, and that they are correctly defined.

Output Directory Error

  • Explanation: This error happens when the output directory for the FBX file does not exist or cannot be created.
  • Solution: Check the output directory path and ensure that the application has permission to create directories and write files in the specified location.

MIA: Auto Rig Related Nodes

Go back to the extension to check out more related nodes.
ComfyUI-UniRig
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.

MIA: Auto Rig