Update README.md

README.md

@@ -80,7 +80,7 @@ widget:
 ## **workflow**
 - for i2v model, drag **clip-vision-h** to > `./ComfyUI/models/clip_vision`
 - run the .bat file in the main directory (assume you are using gguf pack below)
-- if you opt to use [**fp8 scaled umt5xxl**](https://huggingface.co/calcuis/wan-gguf/blob/main/t5xxl_um_fp8_e4m3fn_scaled.safetensors) encoder (if applies to any fp8 scale t5 actually), please use cpu offload (switch from default to **cpu** under **device** in **gguf clip loader**); btw, it works fine for both [**gguf umt5xxl**](https://huggingface.co/calcuis/wan-1.3b-gguf/blob/main/umt5-xxl-encoder-q4_k_m.gguf) and [**gguf vae**](https://huggingface.co/calcuis/wan-1.3b-gguf/blob/main/pig_wan_vae_fp32-f16.gguf)
+- if you opt to use [**fp8 scaled umt5xxl**](https://huggingface.co/calcuis/wan-gguf/blob/main/t5xxl_um_fp8_e4m3fn_scaled.safetensors) encoder (if applies to any fp8 scale t5 actually), please use cpu offload (switch from default to **cpu** under **device** in **gguf clip loader**; won't affect speed); btw, it works fine for both [**gguf umt5xxl**](https://huggingface.co/calcuis/wan-1.3b-gguf/blob/main/umt5-xxl-encoder-q4_k_m.gguf) and [**gguf vae**](https://huggingface.co/calcuis/wan-1.3b-gguf/blob/main/pig_wan_vae_fp32-f16.gguf)
 - drag any demo video (below) to > your browser for workflow
 
 <Gallery />