diff --git a/README.md b/README.md
index 79dfed9..96be2ec 100644
--- a/README.md
+++ b/README.md
@@ -237,7 +237,7 @@ ComfyUI\python_embeded\python.exe -m pip install --upgrade diffusers
 - **Added**: Warning log for skipped LoRA weights - Added logging to display which LoRA files had weights automatically skipped for AWQ modulation layers.
 - **Merged**: [PR #48](https://github.com/ussoewwin/ComfyUI-QwenImageLoraLoader/pull/48) - feat(lora_qwen): improve format detection and add safety skip logs (proposed by [avan06](https://github.com/avan06))
 - **Related Issues**: [Issue #44](https://github.com/ussoewwin/ComfyUI-QwenImageLoraLoader/issues/44) - Module resolution failures and unsupported LoRA format issues
-- **Technical Details**: See [v2.3.8 Release Notes](RELEASE_NOTES/RELEASE_NOTES_V2.3.8.md) for complete explanation
+- **Technical Details**: See [v2.3.8 Release Notes](https://github.com/ussoewwin/ComfyUI-QwenImageLoraLoader/releases/tag/v2.3.8) for complete explanation
 
 ### v2.3.7
 - **Updated**: V3 nodes - AWQ modulation layer LoRA application is now **always enabled** (no switch needed). V3 nodes (`NunchakuQwenImageLoraStackV3`) automatically apply LoRA to AWQ quantized modulation layers (`img_mod.1` / `txt_mod.1`) without requiring the `apply_awq_mod` toggle that was needed in V2 nodes.