Add pipeline tag, license, and link to paper

This PR improves the model card by:
- Adding `pipeline_tag: image-to-3d`, ensuring the model can be found at https://huggingface.co/models?pipeline_tag=image-to-3d.
- Adding the license (`cc-by-nc-4.0`), as stated in the [Github repository](https://github.com/HVision-NKU/DreamStyle3D).
- Linking the model card to the paper page [DreamStyle3D: Efficient 3D Stylized Asset Generation via Dual-Attention Disentanglement](https://huggingface.co/papers/2607.24721), so the model is indexed there.

README.md

@@ -1,16 +1,18 @@
 ---
 base_model: microsoft/TRELLIS-image-large
+pipeline_tag: image-to-3d
+license: cc-by-nc-4.0
 tags:
-  - image-to-3d
-  - 3d
-  - stylization
-  - trellis
+- image-to-3d
+- 3d
+- stylization
+- trellis
 ---
 
 # DreamStyle3D
 
 DreamStyle3D is an efficient framework for generating stylized 3D assets from a content image
-and a style image.
+and a style image, presented in the paper [DreamStyle3D: Efficient 3D Stylized Asset Generation via Dual-Attention Disentanglement](https://huggingface.co/papers/2607.24721).
 
 ## Files
 
@@ -42,4 +44,4 @@ The installer places both files under
 ```text
 d581edb3e57ef92dbe553651b9576ba1f536c274cb4d0e74d1d610513005103f  dreamstyle3d_slat_flow.json
 fd0e00fa691df80cb03befbec1f68bcf1f03d1323db367b0d129a4eb84921ee6  dreamstyle3d_slat_flow.safetensors
-```
+```