ComfyUI Node
Video Text Encode Cached_KJ (QQ)
Cached text encoding that outputs standard ComfyUI conditioning (positive/negative) using WanVideo caching logic
Video Text Encode Cached_KJ (QQ)
- extender_args
- positive
- negative
◄model_name▾►
◄precisionbf16►
◄positive_prompt►
◄negative_prompt►
◄quantizationfp8_e4m3fn►
◄use_disk_cachetrue►
◄devicegpu►
◄skip_cputrue►
CategoryWanVideoWrapper
Inputs (9)
| Name | Type | Default | Description |
|---|---|---|---|
| model_name | COMBO | These models are loaded from 'ComfyUI/models/text_encoders' | |
| precision | COMBO | bf16 | 3 options: fp32, bf16, fp8 |
| positive_prompt | STRING | — | |
| negative_prompt | STRING | — | |
| quantization | COMBO | fp8_e4m3fn | optional quantization method |
| use_disk_cache | BOOLEAN | true | Cache the text embeddings to disk for faster re-use, under the customnodes/ComfyUI-WanVideoWrapper/text_embed_cache directory |
| device | COMBO | gpu | Device to run the text encoding on. |
| skip_cpu | BOOLEAN | true | If True, loads the model directly to VRAM, skipping the initial load to RAM. This can be faster but may use more VRAM. |
| extender_argsopt | WANVIDEOPROMPTEXTENDER_ARGS | Use this node to extend the prompt with additional text. |
Outputs (2)
| Name | Type | Description |
|---|---|---|
| positive | CONDITIONING | — |
| negative | CONDITIONING | — |