WanVideo TextEncode Cached

WanVideoTextEncodeCached

Encodes text prompts into text embeddings. This node loads and completely unloads the T5 after done, leaving no VRAM or RAM imprint. If prompts have been cached before T5 is not loaded at all. negative output is meant to be used with NAG, it contains only negative prompt embeddings. Additionally you can provide a Qwen LLM model to extend the positive prompt with either one of the original Wan templates or a custom system prompt.

Pack: ComfyUI-WanVideoWrapper

custom_nodes.ComfyUI-WanVideoWrapper

Inputs (8)

Name	Type	Required
model_name	COMBO	required
precision	COMBO	required
positive_prompt	STRING	required
negative_prompt	STRING	required
quantization	COMBO	required
use_disk_cache	BOOLEAN	required
device	COMBO	required
extender_args	WANVIDEOPROMPTEXTENDER_ARGS	optional

Outputs (3)

Name	Type
text_embeds	WANVIDEOTEXTEMBEDS
negative_text_embeds	WANVIDEOTEXTEMBEDS
positive_prompt	STRING