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-LongCat-Avatar

ComfyUI Extension: ComfyUI-LongCat-Avatar

Repo Name

ComfyUI-LongCat-Avatar

Author
rookiestar28 (Account age: 963 days)
Nodes
View all nodes(9)
Latest Updated
2026-07-11
Github Stars
0.03K

How to Install ComfyUI-LongCat-Avatar

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

ComfyUI-LongCat-Avatar Description

ComfyUI-LongCat-Avatar provides custom nodes for generating human video avatars driven by audio using LongCat Video Avatar 1.5, enhancing video creation with audio-responsive animations.

ComfyUI-LongCat-Avatar Introduction

The ComfyUI-LongCat-Avatar extension is a powerful tool designed to integrate the Avatar 1.5 pipeline into the ComfyUI framework. This extension is particularly focused on enhancing video generation capabilities by leveraging advanced audio-driven techniques. It supports CUDA inference, which is essential for efficient processing on NVIDIA GPUs, and utilizes Whisper-large-v3 for audio conditioning, ensuring accurate lip synchronization and natural audio-visual alignment. The extension is capable of generating avatars from both single and multiple audio inputs, making it versatile for various creative projects. By automating the download of official checkpoint assets, it simplifies the setup process, allowing AI artists to focus on their creative work without worrying about technical complexities.

How ComfyUI-LongCat-Avatar Works

At its core, ComfyUI-LongCat-Avatar operates by transforming audio inputs into dynamic video outputs. It uses a process called inference, where the model interprets audio data to generate corresponding video frames. The extension employs a technique known as distillation, which reduces the number of steps required for inference, thereby speeding up the process without compromising quality. This is particularly beneficial for artists who need quick iterations. The use of Whisper-large-v3 ensures that the audio input is accurately translated into visual movements, such as lip-syncing, enhancing the realism of the generated avatars.

ComfyUI-LongCat-Avatar Features

  • Audio-Driven Video Generation: Supports both single and multi-audio inputs, allowing for the creation of complex, dialogue-driven scenes.
  • Resolution Options: Offers 480p and 720p video generation, catering to different quality requirements.
  • Distill Inference: Utilizes a distilled model for faster processing, making it ideal for artists who need to generate content quickly.
  • Automatic Asset Download: Simplifies the setup by automatically downloading necessary model weights and assets.
  • Customizable Attention Backends: Provides options to select different attention mechanisms, such as FlashAttention and xFormers, to optimize performance based on available resources.

ComfyUI-LongCat-Avatar Models

The extension supports different model configurations to cater to various needs:

  • Single-File DiT: A straightforward setup using a single .safetensors file for diffusion models.
  • Official Sharded DiT: Utilizes sharded model files for more efficient memory usage and potentially better performance.
  • INT8 Sharded DiT: Offers an INT8 quantized version for reduced VRAM usage, suitable for systems with limited resources. Each model type is designed to optimize the balance between performance and resource consumption, allowing artists to choose based on their specific hardware capabilities.

What's New with ComfyUI-LongCat-Avatar

Recent updates have focused on improving installation reliability and compatibility with different system configurations. The latest version, 0.2.5, addresses startup issues by removing unnecessary dependencies and ensuring compatibility with the latest Python and ComfyUI versions. Additionally, a new branch for Apple Silicon testing has been introduced, expanding the extension's usability across different platforms.

Troubleshooting ComfyUI-LongCat-Avatar

If you encounter issues with missing nodes or installation errors, ensure that you have the latest version of the extension and that all dependencies are correctly installed. For model file warnings, verify that all required files are placed in the correct directories as specified in the documentation. If problems persist, consider checking community forums or the official GitHub repository for additional support and updates.

Learn More about ComfyUI-LongCat-Avatar

To further explore the capabilities of ComfyUI-LongCat-Avatar, you can visit the Official LongCat-Video Repo and the Official Avatar 1.5 Project Page. These resources provide comprehensive information on the underlying technology and offer additional insights into optimizing your creative projects with this extension.

ComfyUI-LongCat-Avatar Related Nodes

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.