ComfyUI > Nodes > ComfyUI-HunyuanVideoWrapper > HunyuanVideo Empty Text Embeds

ComfyUI Node: HunyuanVideo Empty Text Embeds

Class Name

HyVideoEmptyTextEmbeds

Category
HunyuanVideoWrapper
Author
kijai (Account age: 2506days)
Extension
ComfyUI-HunyuanVideoWrapper
Latest Updated
2025-05-12
Github Stars
2.4K

How to Install ComfyUI-HunyuanVideoWrapper

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

HunyuanVideo Empty Text Embeds Description

Facilitates inverse sampling in HunyuanVideoWrapper by providing pre-encoded empty text embeddings for streamlined workflow efficiency.

HunyuanVideo Empty Text Embeds:

The HyVideoEmptyTextEmbeds node is designed to facilitate the process of inverse sampling in the HunyuanVideoWrapper by providing pre-encoded empty text embeddings. This node is particularly useful when you want to bypass the need to encode prompts manually, which can be a time-consuming process. By utilizing this node, you can streamline your workflow, especially in scenarios where the encoding of prompts is not necessary or when you want to maintain a consistent baseline for inverse sampling. The node achieves this by loading a pre-saved dictionary of empty prompt embeddings, ensuring that you have a ready-to-use set of embeddings without additional processing. This can be particularly beneficial in complex video generation tasks where efficiency and speed are crucial.

HunyuanVideo Empty Text Embeds Input Parameters:

HunyuanVideo Empty Text Embeds Output Parameters:

hyvid_embeds

The hyvid_embeds output parameter provides a dictionary of pre-encoded empty text embeddings. These embeddings are crucial for inverse sampling processes where you want to avoid the overhead of encoding prompts. The output is a ready-to-use set of embeddings that can be directly applied in your video generation tasks, ensuring consistency and efficiency. This output allows you to maintain a streamlined workflow by providing a baseline set of embeddings that can be used across various scenarios without the need for additional encoding steps.

HunyuanVideo Empty Text Embeds Usage Tips:

  • Utilize the HyVideoEmptyTextEmbeds node when you need to perform inverse sampling without the need for specific prompt encodings. This can save time and computational resources.
  • Ensure that the pre-saved dictionary of empty prompt embeddings is correctly loaded and accessible to avoid any disruptions in your workflow.

HunyuanVideo Empty Text Embeds Common Errors and Solutions:

FileNotFoundError: hunyuan_empty_prompt_embeds_dict.pt not found

  • Explanation: This error occurs when the node attempts to load the pre-saved dictionary of empty prompt embeddings, but the file is not found in the specified directory.
  • Solution: Verify that the hunyuan_empty_prompt_embeds_dict.pt file is present in the correct directory. If it is missing, ensure that it is correctly generated and saved in the expected location.

DeviceNotAvailableError: Text encoder device not available

  • Explanation: This error indicates that the specified device for the text encoder is not available, which can prevent the node from functioning correctly.
  • Solution: Check the device settings and ensure that the specified text encoder device is available and properly configured. If necessary, adjust the device settings to match the available hardware.

HunyuanVideo Empty Text Embeds Related Nodes

Go back to the extension to check out more related nodes.
ComfyUI-HunyuanVideoWrapper
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 Playground, enabling artists to harness the latest AI tools to create incredible art.