Update README.md

README.md

@@ -39,8 +39,8 @@ extra_gated_eu_disallowed: true
 
 ## **Performance on RTX 5090**
 > When using **HunyuanImage-2.1** with the **quantized encoder** + **quantized base model**,  
-> the VRAM usage on an **NVIDIA RTX 5090** typically ranges between **26 GB and 30 GB**,  
-> depending on resolution, batch size, and prompt complexity.
+> the VRAM usage on an **NVIDIA RTX 5090** typically ranges between **26 GB and 30 GB** with average   
+> 16 second inference time depending on resolution, batch size, and prompt complexity.
 
 ⚠ **Important Note:**  
 The **refiner** and **distilled model** are **not yet implemented** and are **not ready for use in ComfyUI**.