ComfyUI  >  Nodes  >  ComfyUI-AniPortrait >  AniPortraitRun

ComfyUI Node: AniPortraitRun

Class Name


chaojie (Account age: 4831 days)
Latest Updated
Github Stars

How to Install ComfyUI-AniPortrait

Install this extension via the ComfyUI Manager by searching for  ComfyUI-AniPortrait
  • 1. Click the Manager button in the main menu
  • 2. Select Custom Nodes Manager button
  • 3. Enter ComfyUI-AniPortrait 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
  • High-speed GPU machines
  • 200+ preloaded models/nodes
  • Freedom to upload custom models/nodes
  • 50+ ready-to-run workflows
  • 100% private workspace with up to 200GB storage
  • Dedicated Support

Run ComfyUI Online

AniPortraitRun Description

Node for creating lifelike animated portraits using AI models and various inputs for dynamic video output.


AniPortraitRun is a node designed to facilitate the creation of animated portraits by leveraging advanced AI models. This node integrates various inputs such as audio, images, and pose data to generate a dynamic and expressive video output. The primary goal of AniPortraitRun is to enable AI artists to create lifelike animations from static images, enhancing the creative process with minimal technical complexity. By utilizing this node, you can transform a simple portrait into a vivid animation that synchronizes with audio inputs, providing a powerful tool for storytelling and artistic expression.

AniPortraitRun Input Parameters:


This parameter represents the pipeline used for processing the inputs and generating the output. It is essential for coordinating the various stages of the animation creation process.


This parameter specifies the file path to the wav2vec2 model, which is used for audio processing. The model helps in extracting features from the audio input, which are then used to synchronize the animation with the audio. Ensure the path is correct to avoid errors in audio processing.


This parameter indicates the model used for audio-to-motion conversion. It plays a crucial role in mapping audio features to corresponding facial movements, ensuring that the animation accurately reflects the audio input.


This parameter is the input image that serves as the base for the animated portrait. The quality and resolution of the image can significantly impact the final animation output.


This parameter provides the pose data for the animation. It helps in defining the initial and subsequent positions of the facial features, contributing to the realism of the animation.


This parameter specifies the file path to the audio input. The audio file is used to drive the animation, making it essential for synchronizing the visual output with the sound.


This parameter defines the width of the output video. It is important to set this value according to the desired resolution of the final animation.


This parameter defines the height of the output video. Similar to the width, it should be set based on the desired resolution of the animation.


This parameter determines the length of the output video in seconds. It is crucial for defining the duration of the animation.


This parameter specifies the number of steps or frames in the animation. A higher number of steps can result in a smoother animation but may require more processing time.


This parameter stands for configuration settings that control various aspects of the animation process. It can include settings for model parameters, processing options, and other configurations.


This parameter is used for random number generation to ensure reproducibility of the animation. Setting a specific seed value allows you to recreate the same animation output.


This parameter defines the data type for the model weights. It is important for ensuring compatibility with the processing pipeline and can impact the performance and accuracy of the animation.


This parameter sets the minimum confidence level for face detection. It helps in filtering out low-confidence detections, ensuring that only reliable face data is used for the animation.

AniPortraitRun Output Parameters:


The primary output of the AniPortraitRun node is the animated video. This video is a dynamic representation of the input image, synchronized with the audio and pose data provided. The output video captures the essence of the input portrait, bringing it to life with realistic facial movements and expressions.

AniPortraitRun Usage Tips:

  • Ensure that the input image is of high quality and resolution to achieve the best animation results.
  • Use clear and well-recorded audio files to enhance the synchronization between the animation and the audio.
  • Experiment with different pose data to create varied and expressive animations.
  • Adjust the width and height parameters to match the desired resolution of your final output video.
  • Set a specific seed value if you need to reproduce the same animation output for consistency.

AniPortraitRun Common Errors and Solutions:

"Invalid wav2vec2 model path"

  • Explanation: The specified path to the wav2vec2 model is incorrect or the model file is missing.
  • Solution: Verify the file path and ensure that the wav2vec2 model file is present at the specified location.

"Audio file not found"

  • Explanation: The audio file specified in the audio_path parameter cannot be found.
  • Solution: Check the file path and ensure that the audio file exists and is accessible.

"Face detection confidence too low"

  • Explanation: The face detection confidence is below the minimum threshold set by the min_face_detection_confidence parameter.
  • Solution: Increase the min_face_detection_confidence value to filter out low-confidence detections and ensure reliable face data is used.

"Model weight data type mismatch"

  • Explanation: The data type specified in the weight_dtype parameter is incompatible with the model weights.
  • Solution: Ensure that the weight_dtype parameter matches the data type of the model weights used in the pipeline.

AniPortraitRun Related Nodes

Go back to the extension to check out more related nodes.

© Copyright 2024 RunComfy. All Rights Reserved.

RunComfy is the premier ComfyUI platform, offering ComfyUI online environment and services, along with ComfyUI workflows featuring stunning visuals.