Add library_name, project page, and code links

README.md

@@ -1,22 +1,26 @@
 ---
-license: apache-2.0
 base_model: ChenDY/NitroFusion2
-base_model_relation: quantized
+license: apache-2.0
 pipeline_tag: text-to-image
+library_name: diffusers
 tags:
-  - comfyui
-  - nitrofusion2
-  - z-image-turbo
-  - one-step
-  - few-step
-  - int8
-  - w6a8
-  - w4a8
-  - quantized
+- comfyui
+- nitrofusion2
+- z-image-turbo
+- one-step
+- few-step
+- int8
+- w6a8
+- w4a8
+- quantized
+base_model_relation: quantized
 ---
 
 # NitroFusion2 for ComfyUI: int8, W6A8, W4A8
 
+**Project page:** [https://chendaryen.github.io/NitroFusion2.github.io/](https://chendaryen.github.io/NitroFusion2.github.io/)
+**GitHub:** [https://github.com/ChenDarYen/NitroFusion2](https://github.com/ChenDarYen/NitroFusion2)
+
 **[NitroFusion2](https://huggingface.co/ChenDY/NitroFusion2)** (Dar-Yen Chen and Yi-Zhe Song), the 1–2 step
 distillation of Z-Image-Turbo, in three smaller files that run in **stock ComfyUI**: no custom nodes, the normal
 **Load Diffusion Model** node, and ComfyUI's own int8 / W6A8 / W4A8 kernels. They are about **1.7× faster** per step
@@ -89,4 +93,4 @@ workflows are the publisher's. Paper: [arXiv 2611.05648](https://arxiv.org/abs/2
     journal={arXiv preprint arXiv:2611.05648},
     year={2026}
 }
-```
+```