Update README.md

README.md

@@ -27,6 +27,8 @@ pipeline_tag: image-to-image
 ### This fp8_scaled model is faster than the official one released by ComfyOrg when used with the Loader in the workflow.
 ### The custom node that loads the model in the workflow is necessary to obtain fastest inference on lower VRAM GPU.
 
+### If you want to use the int8 model, then you need to use [silveroxides/ComfyUI-QuantOps](https://github.com/silveroxides/ComfyUI-QuantOps) custom node until official support is merged.
+
 ![Workflow](./workflow_assets/fp8_scaled_flux2_w_enhanced_prompting-overview.png)
 
 ![Sample](./workflow_assets/fp8_scaled_flux2_w_enhanced_prompting-sample.png)